From Here to Utility Melding Phonetic Insight With Speech Technology Steven Greenberg International Computer Science Institute 1947 Center Street, Berkeley, CA 94704 http://www.icsi.berkeley.edu/~steveng steveng@icsi.berkeley.edu Acknowledgements and Thanks Automatic Feature Classification and Analysis Joy Hollenback, Shawn Chang, Leah Hitchcock Research Funding U.S. National Science Foundation U.S. Department of Defense Road Map of the Presentation What is Truth? • The story of Rashomon, a film by Akira Kurosawa • Its application to spoken language Road Map of the Presentation What is Truth? • The story of Rashomon, a film by Akira Kurosawa • Its application to spoken language The Varieties of Scientific Experience • The Fundamental Duality • The Eternal Pentangle • The Inner Triangle Road Map of the Presentation What is Truth? • The story of Rashomon, a film by Akira Kurosawa • Its application to spoken language The Varieties of Scientific Experience • The Fundamental Duality • The Eternal Pentangle • The Inner Triangle The Importance of Being Phonetically Annotated • A Corpus-Centric Perspective on Spoken Language • Phonetic Annotation of Spontaneous American English Discourse Road Map of the Presentation What is Truth? • The story of Rashomon, a film by Akira Kurosawa • Its application to spoken language The Varieties of Scientific Experience • The Fundamental Duality • The Eternal Pentangle • The Inner Triangle The Importance of Being Phonetically Annotated • A Corpus-Centric Perspective on Spoken Language • Phonetic Annotation of Spontaneous American English Discourse Phonetic Dissection of Automatic Speech Recognition Systems • Stress Accent and Word Error Rate • Syllable Structure and Word Error Rate Road Map of the Presentation What is Truth? • The story of Rashomon, a film by Akira Kurosawa • Its application to spoken language The Varieties of Scientific Experience • The Fundamental Duality • The Eternal Pentangle • The Inner Triangle The Importance of Being Phonetically Annotated • A Corpus-Centric Perspective on Spoken Language • Phonetic Annotation of Spontaneous American English Discourse Phonetic Dissection of Automatic Speech Recognition Systems • Stress Accent and Word Error Rate • Syllable Structure and Word Error Rate The Relation Between Stress Accent and Vocalic Identity • The Relation Between Segmental Duration and Vowel Height • Durational Differences Between Stressed and Unstressed Vowels • The Relation Between Vowel Height and Stress Accent Road Map of the Presentation What is Truth? • The story of Rashomon, a film by Akira Kurosawa • Its application to spoken language The Varieties of Scientific Experience • The Fundamental Duality • The Eternal Pentangle • The Inner Triangle The Importance of Being Phonetically Annotated • A Corpus-Centric Perspective on Spoken Language • Phonetic Annotation of Spontaneous American English Discourse Phonetic Dissection of Automatic Speech Recognition Systems • Stress Accent and Word Error Rate • Syllable Structure and Word Error Rate The Relation Between Stress Accent and Vocalic Identity • The Relation Between Segmental Duration and Vowel Height • Durational Differences Between Stressed and Unstressed Vowels • The Relation Between Vowel Height and Stress Accent Spoken Language – What is Truth? • Fundamental Questions Remain Unanswered Part One WHAT IS TRUTH? The Story of Rashomon Its Moral for the Study of Spoken Language Rashomon – What is Truth? It is twelfth-century Japan, and a nobleman has died …. Rashomon – What is Truth? This we learn from a conversation between a woodcutter, a priest and a peasant under a gate in the ancient city of Kyoto …. Rashomon – What is Truth? The woodcutter and the priest have just come from a judicial inquest into the death, and are telling the peasant what they have heard Rashomon – What is Truth? The woodcutter and the priest have just come from a judicial inquest into the death, and are telling the peasant what they have heard The woodcutter testified at the inquest, having witnessed the sequence of events resulting in the Nobleman’s death Rashomon – What is Truth? The story begins with the capture of the notorious bandit, Tajomaru, who is the accused in the nobleman’s death …. Rashomon – What is Truth? The nobleman and his wife had been traveling through the forest …. Rashomon – What is Truth? When, all of a sudden, Rashomon – What is Truth? When, all of a sudden, they are confronted by Tajomaru, who halts their progress …. Rashomon – What is Truth? The nobleman and bandit go off alone into a thicket, where the former winds up being subdued by the latter Rashomon – What is Truth? The nobleman is tied to a tree and forced to watch as his wife is violated by the bandit Rashomon – What is Truth? The wife, at first, resists …. Rashomon – What is Truth? But eventually drops the dagger and submits Rashomon – What is Truth? So far, all parties concerned agree (roughly) as to the course of events, but from this point on the picture becomes murky, with each participant telling a somewhat different version of the story Rashomon – What is Truth? In two versions (Tajomaru’s and the woodcutter’s) the wife insists that her husband and the bandit fight for her honor. The nobleman’s death results from losing the duel. Rashomon – What is Truth? In the wife’s version, the bandit departs, with the husband still tied to the tree. The husband proceeds to taunt his wife, telling her how ashamed he is – of her! Rashomon – What is Truth? She cuts the rope binding her husband to the tree and asks to be killed! The wife promptly faints and when she awakens, finds the dagger in the chest of her (now very dead) husband Rashomon – What is Truth? In yet another version (the husband’s through a spirit medium) his wife betrays him and tries to convince the bandit to kill the husband Rashomon – What is Truth? However, the bandit is repulsed by this suggestion and quickly departs …. Rashomon – What is Truth? However, the bandit is repulsed by this suggestion and quickly departs …. The nobleman, still tied to the tree, picks up the dagger and plunges it into his chest, thus taking his own life Rashomon – What is Truth? However, the bandit is repulsed by this suggestion and quickly departs …. The nobleman, still tied to the tree, picks up the dagger and plunges it into his chest, thus taking his own life Some time later the (now very dead) nobleman is aware of someone (it is not clear who) removing the dagger from his chest Rashomon – What is Truth? The film ends as the priest, woodcutter and peasant mull over the significance of the disparate accounts of the nobleman’s death, seeking some kernel of truth in the morass of ambiguity and uncertainty Rashomon – What is Truth? The film ends as the priest, woodcutter and peasant mull over the significance of the disparate accounts of the nobleman’s death, seeking some kernel of truth in the morass of ambiguity and uncertainty It is unclear whether ANY witness has been entirely truthful Rashomon – What is Truth? The film ends as the priest, woodcutter and peasant mull over the significance of the disparate accounts of the nobleman’s death, seeking some kernel of truth in the morass of ambiguity and uncertainty It is unclear whether ANY witness has been entirely truthful (probably not) Rashomon – What is Truth? The story of Rashomon is cited often in philosophical discussions of “truth” Rashomon – What is Truth? The story of Rashomon is cited often in philosophical discussions of “truth” As nothing is known (or knowable) with absolute certainty, all knowledge is relative (and hence ephemeral) Rashomon – What is Truth? The story of Rashomon is cited often in philosophical discussions of “truth” As nothing is known (or knowable) with absolute certainty, all knowledge is relative (and hence ephemeral) The concept of truth is a chimera Rashomon – What is Truth? The story of Rashomon is cited often in philosophical discussions of “truth” As nothing is known (or knowable) with absolute certainty, all knowledge is relative (and hence ephemeral) The concept of truth is a chimera Rashomon – What is Truth? The story of Rashomon is cited often in philosophical discussions of “truth” As nothing is known (or knowable) with absolute certainty, all knowledge is relative (and hence ephemeral) The concept of truth is a chimera and therefore unworthy of pursuit Rashomon – What is Truth? Yet, there is an alternative interpretation, one that questions not the concept of truth itself, but rather the capacity of its assimilation through a single vantage point Rashomon – What is Truth? Yet, there is an alternative interpretation, one that questions not the concept of truth itself, but rather the capacity of its assimilation through a single vantage point Perhaps the “true” message of Rashomon is that deep and ever-lasting knowledge can only be gained through exposure to a variety of perspectives, Rashomon – What is Truth? Yet, there is an alternative interpretation, one that questions not the concept of truth itself, but rather the capacity of its assimilation through a single vantage point Perhaps the “true” message of Rashomon is that deep and ever-lasting knowledge can only be gained through exposure to a variety of perspectives, No single source providing sufficient depth and detail to comprehend a situation as complex (and as tragic) as the murder of a man Spoken Language – What is Truth? Can an intellectual domain as complex as spoken language be fully understood through the testimony of a single perspective? Spoken Language – What is Truth? Can an intellectual domain as complex as spoken language be fully understood through the testimony of a single perspective? Or must orthogonal varieties of evidence be sought with which to reconstruct the “truth”? Spoken Language – What is Truth? Can an intellectual domain as complex as spoken language be fully understood through the testimony of a single perspective? Or must orthogonal varieties of evidence be sought with which to reconstruct the “truth”? How does true insight proceed from “objective” study of spoken language? Spoken Language – What is Truth? Can an intellectual domain as complex as spoken language be fully understood through the testimony of a single perspective? Or must orthogonal varieties of evidence be sought with which to reconstruct the “truth”? How does true insight proceed from “objective” study of spoken language? Is it possible to fully comprehend the multivocal nature of a scientific domain from the sole vantage point of a laboratory? Spoken Language – What is Truth? Can an intellectual domain as complex as spoken language be fully understood through the testimony of a single perspective? Or must orthogonal varieties of evidence be sought with which to reconstruct the “truth”? How does true insight proceed from “objective” study of spoken language? Is it possible to fully comprehend the multivocal nature of a scientific domain from the sole vantage point of a laboratory? Or does the spirit of Rashomon compel us to seek testimony from other sources in the pursuit of objective knowledge? Part Two THE VARIETIES OF SCIENTIFIC EXPERIENCE The Fundamental Duality The Eternal Pentangle The Inner Triangle The Fundamental Duality Technology and science appear to oppose each other in perspective The Fundamental Duality Technology and science appear to oppose each other in perspective • Technology is concerned with what works The Art of the Workable The Fundamental Duality Technology and science appear to oppose each other in perspective • Technology is concerned with what works (and can sell) The Art of the Sellable The Art of the Workable The Fundamental Duality Technology and science appear to oppose each other in perspective • Technology is concerned with what works (and can sell) • Science is concerned with what is The Art of the Sellable The Art of the Workable The Art of the Soluble The Fundamental Duality Technology and science appear to oppose each other in perspective • Technology is concerned with what works (and can sell) • Science is concerned with what is (and can be published) The Art of the Sellable The Art of the Publishable The Art of the Workable The Art of the Soluble The Fundamental Duality There is an essential “tension” between Science and Technology The Art of the Sellable The Art of the Publishable The Art of the Workable The Art of the Soluble The Fundamental Duality There is an essential “tension” between Science and Technology • Science is often deemed “pure” The Art of the Sellable The Art of the Publishable The Art of the Workable The Art of the Soluble The Fundamental Duality There is an essential “tension” between Science and Technology • Science is often deemed “pure” • Technology is usually perceived as “applied” The Art of the Sellable The Art of the Publishable The Art of the Workable The Art of the Soluble The Fundamental Duality There is an essential “tension” between Science and Technology • Science is often deemed “pure” • Technology is usually perceived as “applied” (and therefore not quite as pure) The Art of the Sellable The Art of the Publishable The Art of the Workable The Art of the Soluble The Eternal Pentangle Speech Research Provides an Excellent Example of the Tension between Science and Technology The Eternal Pentangle Speech Research Provides an Excellent Example of the Tension between Science and Technology The Eternal Pentangle Speech Research Provides an Excellent Example of the Tension between Science and Technology • “Phonetic insight” is on the side of the angels The Eternal Pentangle Speech Research Provides an Excellent Example of the Tension between Science and Technology · “Phonetic insight” is on the side of the angels (a.k.a. “science”) Phonetic Insight The Eternal Pentangle Speech Research Provides an Excellent Example of the Tension between Science and Technology · “Phonetic insight” is on the side of the angels (a.k.a. “science”) · While “speech technology” is on the side of the apes Phonetic Insight The Eternal Pentangle Speech Research Provides an Excellent Example of the Tension between Science and Technology • “Phonetic insight” is on the side of the angels (a.k.a. “science”) • While “speech technology” is on the side of the apes (a.k.a. “the real world”) The Real World Phonetic Insight The Inner Triangle The Inner Triangle of the Eternal Pentangle Can Potentially Shed Light on this Philosophical (and Methodological) Conundrum The Inner Triangle The Inner Triangle of the Eternal Pentangle Can Potentially Shed Light on this Philosophical (and Methodological) Conundrum • Manual annotation provides the empirical foundation with which to train machine algorithms The Inner Triangle The Inner Triangle of the Eternal Pentangle Can Potentially Shed Light on this Philosophical (and Methodological) Conundrum • Manual annotation provides the empirical foundation with which to train machine algorithms • Statistical characterization of the annotated material provides the basis for structuring the machine learning regime The Inner Triangle The Inner Triangle of the Eternal Pentangle Can Potentially Shed Light on this Philosophical (and Methodological) Conundrum • Manual annotation provides the empirical foundation with which to train machine algorithms • Statistical characterization of the annotated material provides the basis for structuring the machine learning regime • Machine learning provides a method for evaluating phonetic knowledge The Inner Triangle The Inner Triangle of the Eternal Pentangle Can Potentially Shed Light on this Philosophical (and Methodological) Conundrum • Manual annotation provides the empirical foundation with which to train machine algorithms • Statistical characterization of the annotated material provides the basis for structuring the machine learning regime • Machine learning provides a method for evaluating phonetic knowledge • Phonetic knowledge can be used to efficiently train machine algorithms The Inner Triangle The Inner Triangle of the Eternal Pentangle Can Potentially Shed Light on this Philosophical (and Methodological) Conundrum • Manual annotation provides the empirical foundation with which to train machine algorithms • Statistical characterization of the annotated material provides the basis for structuring the machine learning regime • Machine learning provides a method for evaluating phonetic knowledge • Phonetic knowledge can be used to efficiently train machine algorithms • Statistical characterization can serve as a “reality check” on phonetic knowledge The Inner Triangle Thus, the three apices of the Inner Triangle feed into each other and provide insight and perspective difficult to achieve from a single vantage point The Inner Triangle Thus, the three apices of the Inner Triangle feed into each other and provide insight and perspective difficult to achieve from a single vantage point • In a manner analogous to Rashomon, insight may be gained from this multidimensional perspective that deepens our knowledge of spoken language The Inner Triangle Thus, the three apices of the Inner Triangle feed into each other and provide insight and perspective difficult to achieve from a single vantage point • In a manner analogous to Rashomon, insight may be gained from this multidimensional perspective that deepens our knowledge of spoken language • And thus enables the development of superior technology that truly works in the “real world” The Inner Triangle Thus, the three apices of the Inner Triangle feed into each other and provide insight and perspective difficult to achieve from a single vantage point • In a manner analogous to Rashomon, insight may be gained from this multidimensional perspective that deepens our knowledge of spoken language • And thus enables the development of superior technology that truly works in the “real world” • The development of sterling technology provides (in principle) a means to fund further basic technology-driven research The Inner Triangle Thus, the three apices of the Inner Triangle feed into each other and provide insight and perspective difficult to achieve from a single vantage point • In a manner analogous to Rashomon, insight may be gained from this multidimensional perspective that deepens our knowledge of spoken language • And thus enables the development of superior technology that truly works in the “real world” • The development of sterling technology provides (in principle) a means to fund further basic technology-driven research • And that, in turn, results in further technological advances The Inner Triangle Thus, the three apices of the Inner Triangle feed into each other and provide insight and perspective difficult to achieve from a single vantage point • In a manner analogous to Rashomon, insight may be gained from this multidimensional perspective that deepens our knowledge of spoken language • And thus enables the development of superior technology that truly works in the “real world” • The development of sterling technology provides (in principle) a means to fund further basic technology-driven research • And that, in turn, results in further technological advances • And so on The Inner Triangle Thus, the three apices of the Inner Triangle feed into each other and provide insight and perspective difficult to achieve from a single vantage point • In a manner analogous to Rashomon, insight may be gained from this multidimensional perspective that deepens our knowledge of spoken language • And thus enables the development of superior technology that truly works in the “real world” • The development of sterling technology provides (in principle) a means to fund further basic technology-driven research • And that, in turn, results in further technological advances • And so on (forever after) Part Three THE IMPORTANCE OF BEING PHONETICALLY ANNOTATED A Corpus-Centric Perspective on Spoken Language Phonetic Annotation of Spontaneous American English Discourse Phonetic Annotation is Useful, Because … Many Properties of Spontaneous Spoken Language Differ from Those of Laboratory and Citation Speech Phonetic Annotation is Useful, Because … Many Properties of Spontaneous Spoken Language Differ from Those of Laboratory and Citation Speech There are systematic patterns in “real” speech that potentially reveal underlying principles of linguistic organization Phonetic Annotation is Useful, Because … Many Properties of Spontaneous Spoken Language Differ from Those of Laboratory and Citation Speech There are systematic patterns in “real” speech that potentially reveal underlying principles of linguistic organization Such Corpora Provide Empirical Material for the Study of Spoken Language Phonetic Annotation is Useful, Because … Many Properties of Spontaneous Spoken Language Differ from Those of Laboratory and Citation Speech There are systematic patterns in “real” speech that potentially reveal underlying principles of linguistic organization Such Corpora Provide Empirical Material for the Study of Spoken Language Such data provide an important basis for scientific insight and understanding Phonetic Annotation is Useful, Because … Many Properties of Spontaneous Spoken Language Differ from Those of Laboratory and Citation Speech There are systematic patterns in “real” speech that potentially reveal underlying principles of linguistic organization Such Corpora Provide Empirical Material for the Study of Spoken Language Such data provide an important basis for scientific insight and understanding And facilitate development of new models of spoken language Phonetic Annotation is Useful, Because … Many Properties of Spontaneous Spoken Language Differ from Those of Laboratory and Citation Speech There are systematic patterns in “real” speech that potentially reveal underlying principles of linguistic organization Such Corpora Provide Empirical Material for the Study of Spoken Language Such data provide an important basis for scientific insight and understanding And facilitate development of new models of spoken language They Also Provide Training Material for Technology Applications in: Phonetic Annotation is Useful, Because … Many Properties of Spontaneous Spoken Language Differ from Those of Laboratory and Citation Speech There are systematic patterns in “real” speech that potentially reveal underlying principles of linguistic organization Such Corpora Provide Empirical Material for the Study of Spoken Language Such data provide an important basis for scientific insight and understanding And facilitate development of new models of spoken language They Also Provide Training Material for Technology Applications in: Automatic speech recognition, particularly pronunciation models Phonetic Annotation is Useful, Because … Many Properties of Spontaneous Spoken Language Differ from Those of Laboratory and Citation Speech There are systematic patterns in “real” speech that potentially reveal underlying principles of linguistic organization Such Corpora Provide Empirical Material for the Study of Spoken Language Such data provide an important basis for scientific insight and understanding And facilitate development of new models of spoken language They Also Provide Training Material for Technology Applications in: Automatic speech recognition, particularly pronunciation models Speech synthesis, in pronunciation models as well as in Phonetic Annotation is Useful, Because … Many Properties of Spontaneous Spoken Language Differ from Those of Laboratory and Citation Speech There are systematic patterns in “real” speech that potentially reveal underlying principles of linguistic organization Such Corpora Provide Empirical Material for the Study of Spoken Language Such data provide an important basis for scientific insight and understanding And facilitate development of new models of spoken language They Also Provide Training Material for Technology Applications in: Automatic speech recognition, particularly pronunciation models Speech synthesis, in pronunciation models as well as in Cross-linguistic transfer of technology algorithms, etc. Phonetic Annotation is Useful, Because … Many Properties of Spontaneous Spoken Language Differ from Those of Laboratory and Citation Speech There are systematic patterns in “real” speech that potentially reveal underlying principles of linguistic organization Such Corpora Provide Empirical Material for the Study of Spoken Language Such data provide an important basis for scientific insight and understanding And facilitate development of new models of spoken language They Also Provide Training Material for Technology Applications in: Automatic speech recognition, particularly pronunciation models Speech synthesis, in pronunciation models as well as in Cross-linguistic transfer of technology algorithms, etc. They Promote Development of NOVEL Algorithms for Speech Technology Phonetic Annotation is Useful, Because … Many Properties of Spontaneous Spoken Language Differ from Those of Laboratory and Citation Speech There are systematic patterns in “real” speech that potentially reveal underlying principles of linguistic organization Such Corpora Provide Empirical Material for the Study of Spoken Language Such data provide an important basis for scientific insight and understanding And facilitate development of new models of spoken language They Also Provide Training Material for Technology Applications in: Automatic speech recognition, particularly pronunciation models Speech synthesis, in pronunciation models as well as in Cross-linguistic transfer of technology algorithms, etc. They Promote Development of NOVEL Algorithms for Speech Technology Including pronunciation models and lexical representations for Phonetic Annotation is Useful, Because … Many Properties of Spontaneous Spoken Language Differ from Those of Laboratory and Citation Speech There are systematic patterns in “real” speech that potentially reveal underlying principles of linguistic organization Such Corpora Provide Empirical Material for the Study of Spoken Language Such data provide an important basis for scientific insight and understanding And facilitate development of new models of spoken language They Also Provide Training Material for Technology Applications in: Automatic speech recognition, particularly pronunciation models Speech synthesis, in pronunciation models as well as in Cross-linguistic transfer of technology algorithms, etc. They Promote Development of NOVEL Algorithms for Speech Technology Including pronunciation models and lexical representations for automatic speech recognition and speech synthesis, as well as Phonetic Annotation is Useful, Because … Many Properties of Spontaneous Spoken Language Differ from Those of Laboratory and Citation Speech There are systematic patterns in “real” speech that potentially reveal underlying principles of linguistic organization Such Corpora Provide Empirical Material for the Study of Spoken Language Such data provide an important basis for scientific insight and understanding And facilitate development of new models of spoken language They Also Provide Training Material for Technology Applications in: Automatic speech recognition, particularly pronunciation models Speech synthesis, in pronunciation models as well as in Cross-linguistic transfer of technology algorithms, etc. They Promote Development of NOVEL Algorithms for Speech Technology Including pronunciation models and lexical representations for automatic speech recognition and speech synthesis, as well as Multi-tier representations of spoken language Phonetic Annotation is Useful, Because … Many Properties of Spontaneous Spoken Language Differ from Those of Laboratory and Citation Speech There are systematic patterns in “real” speech that potentially reveal underlying principles of linguistic organization Such Corpora Provide Empirical Material for the Study of Spoken Language Such data provide an important basis for scientific insight and understanding And facilitate development of new models of spoken language They Also Provide Training Material for Technology Applications in: Automatic speech recognition, particularly pronunciation models Speech synthesis, in pronunciation models as well as in Cross-linguistic transfer of technology algorithms, etc. They Promote Development of NOVEL Algorithms for Speech Technology Including pronunciation models and lexical representations for automatic speech recognition and speech synthesis, as well as Multi-tier representations of spoken language All of Which Can be Used for Gaining Further Insight into Spoken Language Corpus-Centric View of Spoken Language Each Tier of Linguistic Organization Provides a Unique Perspective Corpus-Centric View of Spoken Language Each Tier of Linguistic Organization Provides a Unique Perspective However, integrating the annotated material across levels is tricky … Corpus-Centric View of Spoken Language Each Tier of Linguistic Organization Provides a Unique Perspective However, integrating the annotated material across levels is tricky …. And a lot of work!! Corpus-Centric View of Spoken Language Each Tier of Linguistic Organization Provides a Unique Perspective However, integrating the annotated material across levels is tricky …. And a lot of work!! Let’s Focus on a Specific Aspect of Linguistic Organization in Order to Exemplify the Concepts Involved Corpus-Centric View of Spoken Language Each Tier of Linguistic Organization Provides a Unique Perspective However, integrating the annotated material across levels is tricky …. And a lot of work!! Let’s Focus on a Specific Aspect of Linguistic Organization in Order to Exemplify the Concepts Involved In order to do so, we first consider the nature of the transcription material used Phonetic Transcription of Spontaneous English Telephone Dialogues of 5-10 minutes duration, from the SWITCHBOARD CORPUS, have been phonetically annotated (labeled and segmented) Phonetic Transcription of Spontaneous English Telephone Dialogues of 5-10 minutes duration, from the SWITCHBOARD CORPUS, have been phonetically annotated (labeled and segmented) Most of this Material has been Manually Annotated Phonetic Transcription of Spontaneous English Telephone Dialogues of 5-10 minutes duration, from the SWITCHBOARD CORPUS, have been phonetically annotated (labeled and segmented) Most of this Material has been Manually Annotated 4 hours labeled at the phone level and segmented at the syllabic level Phonetic Transcription of Spontaneous English Telephone Dialogues of 5-10 minutes duration, from the SWITCHBOARD CORPUS, have been phonetically annotated (labeled and segmented) Most of this Material has been Manually Annotated 4 hours labeled at the phone level and segmented at the syllabic level 1 hour labeled and segmented at the phonetic-segment level Phonetic Transcription of Spontaneous English Telephone Dialogues of 5-10 minutes duration, from the SWITCHBOARD CORPUS, have been phonetically annotated (labeled and segmented) Most of this Material has been Manually Annotated 4 hours labeled at the phone level and segmented at the syllabic level 1 hour labeled and segmented at the phonetic-segment level The remaining material has been segmented at the phonetic-segment level using automatic methods Phonetic Transcription of Spontaneous English Telephone Dialogues of 5-10 minutes duration, from the SWITCHBOARD CORPUS, have been phonetically annotated (labeled and segmented) Most of this Material has been Manually Annotated 4 hours labeled at the phone level and segmented at the syllabic level 1 hour labeled and segmented at the phonetic-segment level The remaining material has been segmented at the phonetic-segment level using automatic methods 45 minutes of stress-accent-labeled material Phonetic Transcription of Spontaneous English Telephone Dialogues of 5-10 minutes duration, from the SWITCHBOARD CORPUS, have been phonetically annotated (labeled and segmented) Most of this Material has been Manually Annotated 4 hours labeled at the phone level and segmented at the syllabic level 1 hour labeled and segmented at the phonetic-segment level The remaining material has been segmented at the phonetic-segment level using automatic methods 45 minutes of stress-accent-labeled material An additional four hours of material automatically labeled with respect to accent (this latter material not used in the current analysis, but will be available soon) Phonetic Transcription of Spontaneous English Telephone Dialogues of 5-10 minutes duration, from the SWITCHBOARD CORPUS, have been phonetically annotated (labeled and segmented) Most of this Material has been Manually Annotated 4 hours labeled at the phone level and segmented at the syllabic level 1 hour labeled and segmented at the phonetic-segment level The remaining material has been segmented at the phonetic-segment level using automatic methods 45 minutes of stress-accent-labeled material An additional four hours of material automatically labeled with respect to accent (this latter material not used in the current analysis, but will be available soon) There is a Lot of Diversity in the Material Transcribed Phonetic Transcription of Spontaneous English Telephone Dialogues of 5-10 minutes duration, from the SWITCHBOARD CORPUS, have been phonetically annotated (labeled and segmented) Most of this Material has been Manually Annotated 4 hours labeled at the phone level and segmented at the syllabic level 1 hour labeled and segmented at the phonetic-segment level The remaining material has been segmented at the phonetic-segment level using automatic methods 45 minutes of stress-accent-labeled material An additional four hours of material automatically labeled with respect to accent (this latter material not used in the current analysis, but will be available soon) There is a Lot of Diversity in the Material Transcribed Spans speech of both genders (ca. 50/50%), reflecting a wide range of American dialectal variation, speaking rate and voice quality Phonetic Transcription of Spontaneous English Telephone Dialogues of 5-10 minutes duration, from the SWITCHBOARD CORPUS, have been phonetically annotated (labeled and segmented) Most of this Material has been Manually Annotated 4 hours labeled at the phone level and segmented at the syllabic level 1 hour labeled and segmented at the phonetic-segment level The remaining material has been segmented at the phonetic-segment level using automatic methods 45 minutes of stress-accent-labeled material An additional four hours of material automatically labeled with respect to accent (this latter material not used in the current analysis, but will be available soon) There is a Lot of Diversity in the Material Transcribed Spans speech of both genders (ca. 50/50%), reflecting a wide range of American dialectal variation, speaking rate and voice quality Transcription System A variant of Arpabet, with phonetic diacritics such as:_gl,_cr, _fr, _n, _vl, _vd Phonetic Transcription of Spontaneous English The Data are Available at …. Phonetic Transcription of Spontaneous English The Data are Available at …. http://www.icsi/berkeley.edu/real/stp Phonetic Transcription of Spontaneous English The Data are Available at …. http://www.icsi/berkeley.edu/real/stp This Means there is Phonetically Validated Material at the Level of the: Phonetic Transcription of Spontaneous English The Data are Available at …. http://www.icsi/berkeley.edu/real/stp This Means there is Phonetically Validated Material at the Level of the: WORD Phonetic Transcription of Spontaneous English The Data are Available at …. http://www.icsi/berkeley.edu/real/stp This Means there is Phonetically Validated Material at the Level of the: WORD SYLLABLE Phonetic Transcription of Spontaneous English The Data are Available at …. http://www.icsi/berkeley.edu/real/stp This Means there is Phonetically Validated Material at the Level of the: WORD SYLLABLE PHONETIC SEGMENT Phonetic Transcription of Spontaneous English The Data are Available at …. http://www.icsi/berkeley.edu/real/stp This Means there is Phonetically Validated Material at the Level of the: WORD SYLLABLE ARTICULATORY-ACOUSTIC FEATURE PHONETIC SEGMENT Phonetic Transcription of Spontaneous English The Data are Available at …. http://www.icsi/berkeley.edu/real/stp This Means there is Phonetically Validated Material at the Level of the: WORD SYLLABLE ARTICULATORY-ACOUSTIC FEATURE PHONETIC SEGMENT and STRESS ACCENT Phonetic Transcription of Spontaneous English The Data are Available at …. http://www.icsi/berkeley.edu/real/stp This Means there is Phonetically Validated Material at the Level of the: WORD SYLLABLE ARTICULATORY-ACOUSTIC FEATURE (as well as at the utterance level) PHONETIC SEGMENT and STRESS ACCENT The Eternal Pentangle (Redux) Let’s re-examine the eternal triangle from the perspective of manual annotation for three linguistic tiers…. Phonetic Transcription How was the Labeling and Segmentation Performed? Phonetic Transcription How was the Labeling and Segmentation Performed? VERY carefully …. by UC-Berkeley linguistics students Phonetic Transcription How was the Labeling and Segmentation Performed? VERY carefully …. by UC-Berkeley linguistics students Using a display of the signal waveform, Phonetic Transcription How was the Labeling and Segmentation Performed? VERY carefully …. by UC-Berkeley linguistics students Using a display of the signal waveform, spectrogram, Phonetic Transcription How was the Labeling and Segmentation Performed? VERY carefully …. by UC-Berkeley linguistics students Using a display of the signal waveform, spectrogram, word transcription Phonetic Transcription How was the Labeling and Segmentation Performed? VERY carefully …. by UC-Berkeley linguistics students Using a display of the signal waveform, spectrogram, word transcription and “forced alignments” (automatic estimates of phones and boundaries) Phonetic Transcription How was the Labeling and Segmentation Performed? VERY carefully …. by UC-Berkeley linguistics students Using a display of the signal waveform, spectrogram, word transcription and “forced alignments” (automatic estimates of phones and boundaries) + audio (listening at multiple time scales - phone, word, utterance) Phonetic Transcription How was the Labeling and Segmentation Performed? VERY carefully …. by UC-Berkeley linguistics students Using a display of the signal waveform, spectrogram, word transcription and “forced alignments” (automatic estimates of phones and boundaries) + audio (listening at multiple time scales - phone, word, utterance) on Sun workstations Phonetic Transcription How was the Labeling and Segmentation Performed? VERY carefully …. by UC-Berkeley linguistics students Using a display of the signal waveform, spectrogram, word transcription and “forced alignments” (automatic estimates of phones and boundaries) + audio (listening at multiple time scales - phone, word, utterance) on Sun workstations Additionally, automatic segmentation and labeling of articulatory manner was used as a guide for phonetic labeling and segmentation in the current year Phonetic Transcription In addition to phonetic labels and syllabic segmentation, Phonetic Transcription In addition to phonetic labels and syllabic segmentation, 45 minutes of this material was labeled with respect to stress accent for each syllable Three levels of stress were marked - FULLY Stressed, Unstressed and Intermediate Stress Phonetic Transcription Such material can be used to perform statistical characterization of spontaneous speech as well as train machine algorithms to label and segment additional material Phonetic Transcription Such material can be used to perform statistical characterization of spontaneous speech as well as train machine algorithms to label and segment additional material In addition, the transcription material can be used to evaluate the performance of automatic speech recognition systems Phonetic Transcription Such material can be used to perform statistical characterization of spontaneous speech as well as train machine algorithms to label and segment additional material In addition, the transcription material can be used to evaluate the performance of automatic speech recognition systems Let’s first consider how this transcription can be used for ASR evaluation Phonetic Transcription Such material can be used to perform statistical characterization of spontaneous speech as well as train machine algorithms to label and segment additional material In addition, the transcription material can be used to evaluate the performance of automatic speech recognition systems Let’s first consider how this transcription can be used for ASR evaluation We’ll focus on stress-accent, but then relate this to syllable structure Part Four PHONETIC DISSECTION OF AUTOMATIC SPEECH RECOGNITION SYSTEMS A Case Study Stress Accent and Word Error Rate Syllable Structure and Word Error Rate In Collaboration with Shawn Chang The Eternal Pentangle (Redux) Let’s re-examine the eternal triangle from the perspective of automatic speech recognition …. Generation of Evaluation Data - 1 A complex sequence of data formatting was required to place the speech recognition data of 8 separate sites into register with the transcription material (and vice versa) Generation of Evaluation Data - 2 But, let’s not sweat the details during this presentation Generation of Evaluation Data - 2 Let’s not sweat the details during this presentation Interested parties may consult the relevant papers (Greenberg, Hollenback and Chang, 2000; Greenberg and Chang, 2000) at www.icsi.berkeley.edu/~steveng Generation of Evaluation Data - 3 Recognition performance was analyzed with reference to ca. 50 separate acoustic, linguistic and structural parameters Summary of Corpus Acoustic Properties • LEXICAL PROPERTIES – Lexical Identity – Unigram Frequency – Number of Syllables in Word – Number of Phones in Word – Word Duration – Speaking Rate – Prosodic Prominence – Energy Level – Lexical Compounds – Non-Words – Word Position in Utterance • SYLLABLE PROPERTIES – Syllable Structure – Syllable Duration – Syllable Energy – Prosodic Prominence – Prosodic Context • PHONE PROPERTIES – Phonetic Identity – Phone Frequency – Position within the Word – Position within the Syllable – Phone Duration – Speaking Rate – Phonetic Context – Contiguous Phones Correct – Contiguous Phones Wrong – Phone Segmentation – Articulatory Features – Articulatory Feature Distance – Phone Confusion Matrices • OTHER PROPERTIES – Speaker (Dialect, Gender) – Utterance Difficulty – Utterance Energy – Utterance Duration Summary of Corpus Acoustic Properties • LEXICAL PROPERTIES – Lexical Identity – Unigram Frequency – Number of Syllables in Word – Number of Phones in Word – Word Duration – Speaking Rate – Prosodic Prominence – Energy Level – Lexical Compounds – Non-Words – Word Position in Utterance • SYLLABLE PROPERTIES – Syllable Structure – Syllable Duration – Syllable Energy – Prosodic Prominence – Prosodic Context • PHONE PROPERTIES – Phonetic Identity – Phone Frequency – Position within the Word – Position within the Syllable – Phone Duration – Speaking Rate – Phonetic Context – Contiguous Phones Correct – Contiguous Phones Wrong – Phone Segmentation – Articulatory Features – Articulatory Feature Distance – Phone Confusion Matrices • OTHER PROPERTIES – Speaker (Dialect, Gender) – Utterance Difficulty – Utterance Energy – Utterance Duration Summary of Corpus Acoustic Properties • LEXICAL PROPERTIES – Lexical Identity – Unigram Frequency – Number of Syllables in Word – Number of Phones in Word – Word Duration – Speaking Rate – Prosodic Prominence – Energy Level – Lexical Compounds – Non-Words – Word Position in Utterance • SYLLABLE PROPERTIES – Syllable Structure – Syllable Duration – Syllable Energy – Prosodic Prominence – Prosodic Context • PHONE PROPERTIES – Phonetic Identity – Phone Frequency – Position within the Word – Position within the Syllable – Phone Duration – Speaking Rate – Phonetic Context – Contiguous Phones Correct – Contiguous Phones Wrong – Phone Segmentation – Articulatory Features – Articulatory Feature Distance – Phone Confusion Matrices • OTHER PROPERTIES – Speaker (Dialect, Gender) – Utterance Difficulty – Utterance Energy – Utterance Duration Summary of Corpus Acoustic Properties • LEXICAL PROPERTIES – Lexical Identity – Unigram Frequency – Number of Syllables in Word – Number of Phones in Word – Word Duration – Speaking Rate – Prosodic Prominence – Energy Level – Lexical Compounds – Non-Words – Word Position in Utterance • SYLLABLE PROPERTIES – Syllable Structure – Syllable Duration – Syllable Energy – Prosodic Prominence – Prosodic Context • PHONE PROPERTIES – Phonetic Identity – Phone Frequency – Position within the Word – Position within the Syllable – Phone Duration – Speaking Rate – Phonetic Context – Contiguous Phones Correct – Contiguous Phones Wrong – Phone Segmentation – Articulatory Features – Articulatory Feature Distance – Phone Confusion Matrices • OTHER PROPERTIES – Speaker (Dialect, Gender) – Utterance Difficulty – Utterance Energy – Utterance Duration What is (usually) Meant by Stress Accent? Prosody is supposed to pertain to extra-phonetic cues in the acoustic signal What is (usually) Meant by Stress Accent? Prosody is supposed to pertain to extra-phonetic cues in the acoustic signal The pattern of variation over a sequence of SYLLABLES pertaining to: syllabic DURATION, AMPLITUDE and PITCH (fo) variation over time What is (usually) Meant by Stress Accent? Prosody is supposed to pertain to extra-phonetic cues in the acoustic signal The pattern of variation over a sequence of SYLLABLES pertaining to: syllabic DURATION, AMPLITUDE and PITCH (fo) variation over time But, the plot thickens (considerably) .… as we’ll shortly see Stress Accent and Word Error Rate The effect of stress accent is most discernable among word-deletion errors Unstressed Data are averaged across all eight sites Intermediate Stress Fully Stressed Stress Accent and Word Error Rate The effect of stress accent is most discernable among word-deletion errors There is no essential relation between accent and word-substitution errors Unstressed Data are averaged across all eight sites Intermediate Stress Fully Stressed Syllable Structure and Word Error Rate Let’s now consider syllable structure with respect to ASR word error Syllable Structure and Word Error Rate Let’s now consider syllable structure with respect to ASR word error There is a certain similarity with the pattern observed for stress accent …. Syllable Structure and Word Error Rate Vowel-initial forms show the greatest error, particularly for word deletions C = Consonant V = Vowel Data are averaged across all eight sites Syllable Structure and Word Error Rate Vowel-initial forms show the greatest error, particularly for word deletions Polysyllabic forms manifest the lowest error, especially for word deletions C = Consonant V = Vowel Data are averaged across all eight sites Syllable Structure and Word Error Rate Vowel-initial forms show the greatest error, particularly for word deletions Polysyllabic forms manifest the lowest error, especially for word deletions The vowel-initial forms tend to be unstressed, so …. C = Consonant V = Vowel Data are averaged across all eight sites Syllable Structure and Word Error Rate Vowel-initial forms show the greatest error, particularly for word deletions Polysyllabic forms manifest the lowest error, especially for word deletions The vowel-initial forms tend to be unstressed, so …. Perhaps the similarity in pattern is not so surprising after all C = Consonant V = Vowel Data are averaged across all eight sites The Plot … So Far The Proportion of Word (Deletion) Errors is Much Higher Among Unstressed Syllables The Plot … So Far The Proportion of Word (Deletion) Errors is Much Higher Among Unstressed Syllables (Relative to Fully and even Partially Stressed Syllables) The Plot … So Far The Proportion of Word (Deletion) Errors is Much Higher Among Unstressed Syllables (Relative to Fully and even Partially Stressed Syllables) The Proportion of Word (Deletion) Errors is Much Higher Among Syllables that Begin with a Vowel The Plot … So Far The Proportion of Word (Deletion) Errors is Much Higher Among Unstressed Syllables (Relative to Fully and even Partially Stressed Syllables) The Proportion of Word (Deletion) Errors is Much Higher Among Syllables that Begin with a Vowel The exception being words composed of more than a single syllable The Plot … So Far The Proportion of Word (Deletion) Errors is Much Higher Among Unstressed Syllables (Relative to Fully and even Partially Stressed Syllables) The Proportion of Word (Deletion) Errors is Much Higher Among Syllables that Begin with a Vowel The exception being words composed of more than a single syllable Polysyllabic Words Exhibit the Lowest Word Deletion Error Rate The Plot … So Far The Proportion of Word (Deletion) Errors is Much Higher Among Unstressed Syllables (Relative to Fully and even Partially Stressed Syllables) The Proportion of Word (Deletion) Errors is Much Higher Among Syllables that Begin with a Vowel The exception being words composed of more than a single syllable Polysyllabic Words Exhibit the Lowest Word Deletion Error Rate Such words usually have at least one syllable that is highly stressed The Plot … So Far The Proportion of Word (Deletion) Errors is Much Higher Among Unstressed Syllables (Relative to Fully and even Partially Stressed Syllables) The Proportion of Word (Deletion) Errors is Much Higher Among Syllables that Begin with a Vowel The exception being words composed of more than a single syllable Polysyllabic Words Exhibit the Lowest Word Deletion Error Rate Such words usually have at least one syllable that is highly stressed Suggesting that deletion errors reflect the general stress pattern within the word The Plot … So Far The Proportion of Word (Deletion) Errors is Much Higher Among Unstressed Syllables (Relative to Fully and even Partially Stressed Syllables) The Proportion of Word (Deletion) Errors is Much Higher Among Syllables that Begin with a Vowel The exception being words composed of more than a single syllable Polysyllabic Words Exhibit the Lowest Word Deletion Error Rate Such words usually have at least one syllable that is highly stressed Suggesting that deletion errors reflect the general stress pattern within the word Syllable Structure and Stress Accent are not Salient Properties in (most) ASR Systems The Plot … So Far The Proportion of Word (Deletion) Errors is Much Higher Among Unstressed Syllables (Relative to Fully and even Partially Stressed Syllables) The Proportion of Word (Deletion) Errors is Much Higher Among Syllables that Begin with a Vowel The exception being words composed of more than a single syllable Polysyllabic Words Exhibit the Lowest Word Deletion Error Rate Such words usually have at least one syllable that is highly stressed Suggesting that deletion errors reflect the general stress pattern within the word Syllable Structure and Stress Accent are not Salient Properties in (most) ASR Systems As ASR systems know about phones and words, but not syllables and stress (at least in American English) The Plot … So Far The Proportion of Word (Deletion) Errors is Much Higher Among Unstressed Syllables (Relative to Fully and even Partially Stressed Syllables) The Proportion of Word (Deletion) Errors is Much Higher Among Syllables that Begin with a Vowel The exception being words composed of more than a single syllable Polysyllabic Words Exhibit the Lowest Word Deletion Error Rate Such words usually have at least one syllable that is highly stressed Suggesting that deletion errors reflect the general stress pattern within the word Syllable Structure and Stress Accent are not Salient Properties in (most) ASR Systems As ASR systems know about phones and words, but not syllables and stress (at least in American English) Could There Therefore be a Link Between Syllable Structure, Stress Accent and Some Other Linguistic Properties that ASR Systems “Know About”? The Plot … So Far The Proportion of Word (Deletion) Errors is Much Higher Among Unstressed Syllables (Relative to Fully and even Partially Stressed Syllables) The Proportion of Word (Deletion) Errors is Much Higher Among Syllables that Begin with a Vowel The exception being words composed of more than a single syllable Polysyllabic Words Exhibit the Lowest Word Deletion Error Rate Such words usually have at least one syllable that is highly stressed Suggesting that deletion errors reflect the general stress pattern within the word Syllable Structure and Stress Accent are not Salient Properties in (most) ASR Systems As ASR systems know about phones and words, but not syllables and stress (at least in American English) Could There Therefore be a Link Between Syllable Structure, Stress Accent and Some Other Linguistic Properties that ASR Systems “Know About”? Let’s Find Out …. Part Five The Relation Between Stress Accent and Vocalic Identity Yet Another Case Study The Relation Between Segmental Duration and Vowel Height Durational Differences Between Stressed and Unstressed Vowels The Relation Between Vowel Height and Stress Accent In Collaboration with Leah Hitchcock The Eternal Pentangle (Redux) Let’s re-examine the eternal triangle from the perspective of statistical characterization of the annotated Switchboard corpus The Eternal Pentangle (Redux) Let’s re-examine the eternal triangle from the perspective of statistical characterization of the annotated Switchboard corpus These data were originally collected to improve the quality of speech recognition systems, but are now being pressed into service for SCIENCE The Eternal Pentangle (Redux) But first …. A Brief Primer on Vocalic Acoustics A Brief Primer on Vocalic Acoustics Vowel quality is generally thought to be a function primarily of two articulatory properties – both related to the motion of the tongue A Brief Primer on Vocalic Acoustics Vowel quality is generally thought to be a function primarily of two articulatory properties – both related to the motion of the tongue • The front-back plane is most closely associated with the second formant frequency (or more precisely F2 - F1) and the volume of the front-cavity resonance A Brief Primer on Vocalic Acoustics Vowel quality is generally thought to be a function primarily of two articulatory properties – both related to the motion of the tongue • The front-back plane is most closely associated with the second formant frequency (or more precisely F2 - F1) and the volume of the front-cavity resonance • The height parameter is closely linked to the frequency of F1 A Brief Primer on Vocalic Acoustics Vowel quality is generally thought to be a function primarily of two articulatory properties – both related to the motion of the tongue • The front-back plane is most closely associated with the second formant frequency (or more precisely F2 - F1) and the volume of the front-cavity resonance • The height parameter is closely linked to the frequency of F1 In the classic vowel “triangle,” segments are positioned in terms of the tongue positions associated with their production, as follows: A Brief Primer on Vocalic Acoustics Vowel quality is generally thought to be a function primarily of two articulatory properties – both related to the motion of the tongue • The front-back plane is most closely associated with the second formant frequency (or more precisely F2 - F1) and the volume of the front-cavity resonance • The height parameter is closely linked to the frequency of F1 In the classic vowel “triangle,” segments are positioned in terms of the tongue positions associated with their production, as follows: Spatial Patterning of Duration and Amplitude Let’s return to the vowel triangle and see if it can shed light on certain patterns in the vocalic data Spatial Patterning of Duration and Amplitude Let’s return to the vowel triangle and see if it can shed light on certain patterns in the vocalic data The duration will be plotted on a 2-D grid , where the x-axis will always be in terms of hypothetical front-back tongue position Spatial Patterning of Duration and Amplitude Let’s return to the vowel triangle and see if it can shed light on certain patterns in the vocalic data The duration will be plotted on a 2-D grid , where the x-axis will always be in terms of hypothetical front-back tongue position (and hence remain a constant throughout the plots to follow) Spatial Patterning of Duration and Amplitude Let’s return to the vowel triangle and see if it can shed light on certain patterns in the vocalic data The duration will be plotted on a 2-D grid , where the x-axis will always be in terms of hypothetical front-back tongue position (and hence remain a constant throughout the plots to follow) The y-axis will serve as the dependent measure expressed in terms of duration or the proportion of fully stressed (or unstressed) nuclei Spatial Patterning of Duration et al. Let’s return to the vowel triangle and see if it can shed light on certain patterns in the vocalic data The duration will be plotted on a 2-D grid , where the x-axis will always be in terms of hypothetical front-back tongue position (and hence remain a constant throughout the plots to follow) The y-axis will serve as the dependent measure expressed in terms of duration or the proportion of fully stressed (or unstressed) nuclei Vocalic Duration and Vowel Height The spatial patterning of vocalic segments is systematic with respect to duration Vocalic Duration and Vowel Height The spatial patterning of vocalic segments is systematic with respect to duration Low vowels, be they diphthongs or monophthongs, are longer (on average) than high vowels Vocalic Duration and Vowel Height The spatial patterning of vocalic segments is systematic with respect to duration Low vowels, be they diphthongs or monophthongs, are longer (on average) than high vowels All nuclei Diphthongs Monophthongs Vocalic Duration and Vowel Height The spatial patterning of vocalic segments is systematic with respect to duration Low vowels, be they diphthongs or monophthongs, are longer (on average) than high vowels Thus, duration appears to be highly correlated with vowel height All nuclei Diphthongs Monophthongs Vocalic Duration and Vowel Height The spatial patterning of vocalic segments is systematic with respect to duration Low vowels, be they diphthongs or monophthongs, are longer (on average) than high vowels Thus, duration appears to be highly correlated with vowel height But … the situation is a little more complicated than first appearances would suggest All nuclei Diphthongs Monophthongs Durational Differences - Stressed/Unstressed There is a large dynamic range in duration between stressed and unstressed nuclei Durational Differences - Stressed/Unstressed There is a large dynamic range in duration between stressed and unstressed nuclei Moreover, diphthongs and tense, low monophthongs tend to exhibit a larger dynamic range than the lax monophthongs Durational Differences - Stressed/Unstressed There is a large dynamic range in duration between stressed and unstressed nuclei Moreover, diphthongs and tense, low monophthongs tend to exhibit a larger dynamic range than the lax monophthongs Lax monophthongs Vocalic Identity Among Unstressed Nuclei The high, lax monophthongs are almost always unstressed Vocalic Identity Among Unstressed Nuclei The high, lax monophthongs are almost always unstressed The low vowels, be they monophthongs or diphthongs, are rarely unstressed Vocalic Identity Among Unstressed Nuclei The high, lax monophthongs are almost always unstressed The low vowels, be they monophthongs or diphthongs, are rarely unstressed The high diphthongs and high/mid, tense monophthongs occupy an intermediate position Vocalic Identity Among Fully Stressed Nuclei The high vowels are rarely fully stressed Vocalic Identity Among Fully Stressed Nuclei The high vowels are rarely fully stressed The low vowels, be they monophthongs or diphthongs, are far more likely to be fully stressed Vocalic Identity Among Fully Stressed Nuclei The high vowels are rarely fully stressed The low vowels, be they monophthongs or diphthongs, are far more likely to be fully stressed An intermediate degree of stress accounts for the other vocalic instances Vocalic Identity Among Fully Stressed Nuclei The high vowels are rarely fully stressed The low vowels, be they monophthongs or diphthongs, are far more likely to be fully stressed An intermediate degree of stress accounts for the other vocalic instances (but will not be addressed here) Is It Stress? Vocalic Identity? Or What? Duration Appears to Play An Important (but certainly not exclusive) Role in Stress Accent for Spontaneous American English Discourse Is It Stress? Vocalic Identity? Or What? Duration Appears to Play An Important (but certainly not exclusive) Role in Stress Accent for Spontaneous American English Discourse For any given vocalic class, stressed segments are longer (on average) Is It Stress? Vocalic Identity? Or What? Duration Appears to Play An Important (but certainly not exclusive) Role in Stress Accent for Spontaneous American English Discourse For any given vocalic class, stressed segments are longer (on average) The durational disparity is most pronounced among the low vowels and the diphthongs Is It Stress? Vocalic Identity? Or What? Duration Appears to Play An Important (but certainly not exclusive) Role in Stress Accent for Spontaneous American English Discourse For any given vocalic class, stressed segments are longer (on average) The durational disparity is most pronounced among the low vowels and the diphthongs Low Vowels Tend to be Much Longer in Duration than High Vowels Is It Stress? Vocalic Identity? Or What? Duration Appears to Play An Important (but certainly not exclusive) Role in Stress Accent for Spontaneous American English Discourse For any given vocalic class, stressed segments are longer (on average) The durational disparity is most pronounced among the low vowels and the diphthongs Low Vowels Tend to be Much Longer in Duration than High Vowels This is the case even for diphthongs Is It Stress? Vocalic Identity? Or What? Duration Appears to Play An Important (but certainly not exclusive) Role in Stress Accent for Spontaneous American English Discourse For any given vocalic class, stressed segments are longer (on average) The durational disparity is most pronounced among the low vowels and the diphthongs Low Vowels Tend to be Much Longer in Duration than High Vowels This is the case even for diphthongs Low Vowels are Rarely without Some Measure of Stress Accent Is It Stress? Vocalic Identity? Or What? Duration Appears to Play An Important (but certainly not exclusive) Role in Stress Accent for Spontaneous American English Discourse For any given vocalic class, stressed segments are longer (on average) The durational disparity is most pronounced among the low vowels and the diphthongs Low Vowels Tend to be Much Longer in Duration than High Vowels This is the case even for diphthongs Low Vowels are Rarely without Some Measure of Stress Accent This is true for monophthongs as well as diphthongs Is It Stress? Vocalic Identity? Or What? Duration Appears to Play An Important (but certainly not exclusive) Role in Stress Accent for Spontaneous American English Discourse For any given vocalic class, stressed segments are longer (on average) The durational disparity is most pronounced among the low vowels and the diphthongs Low Vowels Tend to be Much Longer in Duration than High Vowels This is the case even for diphthongs Low Vowels are Rarely without Some Measure of Stress Accent This is true for monophthongs as well as diphthongs High Vowels are Fully Stressed Extremely Rarely Is It Stress? Vocalic Identity? Or What? Duration Appears to Play An Important (but certainly not exclusive) Role in Stress Accent for Spontaneous American English Discourse For any given vocalic class, stressed segments are longer (on average) The durational disparity is most pronounced among the low vowels and the diphthongs Low Vowels Tend to be Much Longer in Duration than High Vowels This is the case even for diphthongs Low Vowels are Rarely without Some Measure of Stress Accent This is true for monophthongs as well as diphthongs High Vowels are Fully Stressed Extremely Rarely This is particularly so for monophthongs, but also applies to diphthongs Is It Stress? Vocalic Identity? Or What? Duration Appears to Play An Important (but certainly not exclusive) Role in Stress Accent for Spontaneous American English Discourse For any given vocalic class, stressed segments are longer (on average) The durational disparity is most pronounced among the low vowels and the diphthongs Low Vowels Tend to be Much Longer in Duration than High Vowels This is the case even for diphthongs Low Vowels are Rarely without Some Measure of Stress Accent This is true for monophthongs as well as diphthongs High Vowels are Fully Stressed Extremely Rarely This is particularly so for monophthongs, but also applies to diphthongs Thus, Stress Accent Appears to Be Intricately Involved with Vocalic Identity Is It Stress? Vocalic Identity? Or What? Duration Appears to Play An Important (but certainly not exclusive) Role in Stress Accent for Spontaneous American English Discourse For any given vocalic class, stressed segments are longer (on average) The durational disparity is most pronounced among the low vowels and the diphthongs Low Vowels Tend to be Much Longer in Duration than High Vowels This is the case even for diphthongs Low Vowels are Rarely without Some Measure of Stress Accent This is true for monophthongs as well as diphthongs High Vowels are Fully Stressed Extremely Rarely This is particularly so for monophthongs, but also applies to diphthongs Thus, Stress Accent Appears to Be Intricately Involved with Vocalic Identity This relation is likely to have an important impact on pronunciation variation Is It Stress? Vocalic Identity? Or What? Duration Appears to Play An Important (but certainly not exclusive) Role in Stress Accent for Spontaneous American English Discourse For any given vocalic class, stressed segments are longer (on average) The durational disparity is most pronounced among the low vowels and the diphthongs Low Vowels Tend to be Much Longer in Duration than High Vowels This is the case even for diphthongs Low Vowels are Rarely without Some Measure of Stress Accent This is true for monophthongs as well as diphthongs High Vowels are Fully Stressed Extremely Rarely This is particularly so for monophthongs, but also applies to diphthongs Thus, Stress Accent Appears to Be Intricately Involved with Vocalic Identity This relation is likely to have an important impact on pronunciation variation And Thus Could be Useful for Modeling Pronunciation Variation for BOTH Scientific and Technological Applications Part Six SPOKEN LANGUAGE WHAT IS TRUTH? Fundamental Questions Remain Unanswered Spoken Language – What is Truth? The Current Story Raises More Questions than it Answers …. Spoken Language – What is Truth? Is It Possible to Dissociate Vocalic Identity from Stress Accent? Spoken Language – What is Truth? Is It Possible to Dissociate Vocalic Identity from Stress Accent? Is Duration an Essential Component of Stress Accent and Vowel Height? Spoken Language – What is Truth? Is It Possible to Dissociate Vocalic Identity from Stress Accent? Is Duration an Essential Component of Stress Accent and Vowel Height? How Should Words (and other organizational units) be Represented in ASR Lexicons to Exploit Such Interrelations? Spoken Language – What is Truth? Is It Possible to Dissociate Vocalic Identity from Stress Accent? Is Duration an Essential Component of Stress Accent and Vowel Height? How Should Words (and other organizational units) be Represented in ASR Lexicons to Exploit Such Interrelations? Can Speech Technology Afford to View Language as a Mere Concatenation of Phones and Words (or analogous units)? Spoken Language – What is Truth? Is It Possible to Dissociate Vocalic Identity from Stress Accent? Is Duration an Essential Component of Stress Accent and Vowel Height? How Should Words (and other organizational units) be Represented in ASR Lexicons to Exploit Such Interrelations? Can Speech Technology Afford to View Language as a Mere Concatenation of Phones and Words (or analogous units)? Perhaps No Single Perspective Can Truly Capture the Essence of Spoken Language, or Spoken Language – What is Truth? Is It Possible to Dissociate Vocalic Identity from Stress Accent? Is Duration an Essential Component of Stress Accent and Vowel Height? How Should Words (and other organizational units) be Represented in ASR Lexicons to Exploit Such Interrelations? Can Speech Technology Afford to View Language as a Mere Concatenation of Phones and Words (or analogous units)? Perhaps No Single Perspective Can Truly Capture the Essence of Spoken Language, or Portray It with the Depth and Clarity Required to Produce “Flawless” Technology and Enduring Scientific Insight That’s All, Folks Many Thanks for Your Time and Attention