Syllabus for Speech Processing (CPE 464C, CPE 644) Course Objective This course is designed to provide the background knowledge of speech processing including the acoustic of speech sound, the review of speech production in human beings, and the fundamental of speech recognition and synthesis. Course Description Basic knowledge from several fields is required to effectively pursue research in automatic speech processing. We study the acoustic content of the speech signal. Students will use the spectrographic display to examine the signal and discover its variable properties. Phones in increasingly larger contents will be studied with the goal of understanding co-articulation. Phonological rules will be studied as a contextual aid in understanding the spectrographic display. Time and Place: Thursday 6.00-9.00 pm CB4 40805 Instructor: Dr. Santitham Prom-on, Dept. of Computer Engineering, KMUTT. Email santitham@cpe.kmutt.ac.th, appointment by email. Website: http://www.cpe.kmutt.ac.th/~promon Dr. Suthathip Maneewongvatana, Dept. of Computer Engineering, KMUTT. Email fay@cpe.kmutt.ac.th , appointment by email. Website: http://www.cpe.kmutt.ac.th/~fay, download materials via this page. Workload: There will be in-class labs and assignments. Grading: In-class labs 15%, Assignments 15%, Midterm 30%, and Final 40%. Student can request for regrading within 24 hours after the grades are posted. Academic Integrity: All work that you submit in this course must be your own. You must not copy/modify work of other. You must protect your own work from being copied by other. Academic dishonesty issue will be taken seriously. If the cheating is discovered, you will receive no credit of that particular task for the first time (at least). Second occurrence of cheating results in F grade and the incident will be sent to the faculty for further reviews. Text: L. Rabiner, B.W. Juang, Fundamental of Speech Recognition, Prentice Hall, 1993 K.N. Stevens, Acoustic Phonetics, Cambridge, MA : MIT Press, 1998 Software: Matlab, PRATT, Audacity Tentative Schedule: Date Topic Comment 5/11 Introduction to Speech Processing A. Santitham+ A.Suthathip 12/11 Basic Acoustic of Sound A. Santitham 19/11 Human Speech A. Santitham 26/11 Computer Speech 3/12 Source Filter Model of Speech Production A. Suthathip 10/12 Phonetic 1 A. Suthathip 17/12 Phonetic 2 A. Suthathip 24/12 ----------------Midterm Exam-----------------------7/1 ASR: Feature Extraction 1 A. Santitham 14/1 ASR: Feature Extraction 2 A. Santitham 21/1 28/1 4/2 11/2 18/2 25/2 4/3 ASR: Classification 1 ASR: Classification 2 Text Processing Wave form Speech Prosody Voice Conversion, modification ----------------Final Exam------------------------ A. Suthathip A. Suthathip A. Suthathip A. Santitham A. Santitham A. Suthathip