Speaker Independent Arabic Speech
Recognition Using Support Vector
Machine
By
Eng. Shady Yehia El-Mashad
Supervised By
Ass. Prof. Dr. Hala Helmy Zayed
Dr. Mohamed Ibrahim Sharawy
Agenda
Introduction
Characteristics of Speech Signal
History of Speech & Previous Research
The Proposed System
Results and Conclusions
Introduction
Characteristics of Speech Signal
History of Speech & Previous Research
The Proposed System
Results and Conclusions
Recognition
Is one of the basic memory tasks. It involves
identifying objects or events that have been
encountered before. It is the easiest of the memory
tasks.
It is easier to recognize something, than to come up
with it on your own
Speech Recognition System
 Also Known as Automatic Speech Recognition or
Computer Speech
 Automatic Speech Recognition (ASR) is the process of
converting captured speech signals into the corresponding
sequence of words in text.
 ASR systems accomplish three basic tasks:
1- Pre-processing
2- Recognition
3-Communication
How do humans do it?
• Articulation produces sound
waves which the ear conveys
to the brain for processing
How might computers do it?
Acoustic Waveform
Acoustic Signal
Speech Recognition
 Introduction
Characteristics of Speech Signal
History of Speech & Previous Research
The Proposed System
Results and Conclusions
Types of Speech Recognition
There are two main types of speaker models:
(1) Speaker independent
Speaker independent models recognize the speech patterns of a
large group of people.
(2) Speaker dependent
Speaker dependent models recognize speech patterns from only
one person.
Speech Recognition Usually Concern Three
Types of Speech
(1) Isolated Word Recognition
Is the simplest speech type because it requires the user to pause between each word.
(2) Connected Word Recognition
Is capable of analyzing a string of words spoken together, but not at normal speech rate.
(3) Connected Speech Recognition (Continuous Speech Recognition)
Allows for normal conversational speech.
Factors that affect the speech signal
- Speaker gender
- Speaker identity
- Speaker language
- Psychological conditions
- Speaking style
- Environmental conditions
Some of the difficulties related to speech
recognition
- Digitization:
Converting analogue signal into digital representation
- Signal processing:
Separating speech from background noise
- Phonetics:
Variability in human speech
- Continuity:
Natural speech is continuous.
The Three-State Representation
Three-state representation is one way to classify events in
speech.
The events of interest for the three-state representation are:
• Silence (S) - No speech is produced.
• Unvoiced (U) - Vocal cords are not vibrating, resulting in an aperiodic or
random speech waveform.
• Voiced (V) - Vocal cords are vibrating periodically, resulting in a speech
waveform that is quasi-periodic.
Fig. Three State Speech Representation
Applications of Speech Recognition
(1) Security
(2) Education
(3) Control
(4) Diagnosis
(5) Dictation
 Introduction
 Characteristics of Speech Signal
History of Speech & Previous Research
The Proposed System
Results and Conclusions
History of Speech
Previous Research(Arabic Speech)
Combined Classifier
Based Arabic Speech
Recognition
Comparative
Analysis of Arabic
Vowels using
Formants and an
Automatic Speech
Recognition System
HMM AUTOMATIC
SPEECH
RECOGNITION
SYSTEM OF
ARABIC
ALPHADIGITS
Phonetic
Recognition
of Arabic Alphabet
letters using Neural
Networks
INFOS2008, March 2729, 2008 Cairo-Egypt ©
2008 Faculty of
Computers &
Information-Cairo
University
International Journal of
Signal Processing,
Image Processing and
Pattern RecognitionVol. 3, No. 2; June-2010
the Arabian Journal for
Science and
Engineering, Volume
35, Number 2C;
December- 2010
International Journal of
Electric & Computer
Sciences IJECS-IJENS,
Vol: 11, No: 01;
February-2011
The technique
used
ANN
HMM
HMM
ANN
Type of neural
network
combined classifier
-----------------
-----------------
PCA
The scope of
speech
6 isolated word
from Holy Quran
Arabic vowels
(10 words)
Alpha Digits
“Saudi Accented “
Arabic Alphabet
Performance
93%
91.6%
76%
96%
Title
Source
Previous Research(Arabic Digits)
Title
Source
Recognition of Spoken
Arabic Digits Using
Neural Predictive
Hidden Markov Models
Efficient System for
Speech Recognition
using General
Regression Neural
Network
Speech Recognition
System of Arabic Digits
based on A Telephony
Arabic Corpus
Radial Basis Functions
With Wavelet Packets
For Recognizing
Arabic Speech
The International Arab
Journal of Information
Technology, Vol. 1;
International Journal of
Intelligent Systems and
Technologies 1; 2 ©
www.waset.org Spring
Intensive Program on
Computer Vision
(IPCV'08), Joensuu,
Finland;
2006
August-2008
CSECS '10 Proceedings
of the 9th WSEAS
international
conference on Circuits,
systems, electronics,
control and signal
July-2004
processing; 2010
The technique
used
Neural Network
and Hidden
Markov Model
ANN
HMM
ANN
MLP
general regression
neural network
(GRNN)
---------------
RBF
The scope of
speech
Arabic Digits
Arabic Digits
Arabic Digits
“Saudi accented “
Arabic Digits
Performance
88%
85- 91%
93.72%
87-93 %
Type of neural
network
 Introduction
 Characteristics of Speech Signal
 History of Speech & Previous Research
The Proposed System
Results and Conclusions
The Proposed System
The Proposed System
1.Recording System
The Proposed System
2. Data Set
Creating of a speech database is important for the development researcher.
For English language: we don't need to create a database because
there is already more than one have been created to help the researcher on
their research like sphinx1,2,3&4 and Australian English
For Arabic language, we should try to create a database that help us.
The Proposed System
2. Data Set
The Proposed System
3. The Segmentation System
Segmentation process is implemented by two techniques; semi-automatic
and fully-automatic.
Semi-automatic technique:
We adopt the segmentation parameters which are window size, minimum
amplitude, minimum frequency, maximum frequency, minimum silence,
minimum speech, and minimum word manually by trial and error.
In this technique, we achieve only 70 percent performance, which is not very
high and with this technique we can’t continue in our system because we still
have two stages after that which is the feature extraction and the recognition
The Proposed System
3. The Segmentation System
0
1
6
5
3
2 0 4 0 3
X
0
1 6 5 3 2
0
4 0
3 -
The Proposed System
3. The Segmentation System
Fully-automatic techniques
These parameters are set automatically to get better performance by using the K-Mean
clustering.
By this technique we achieve nearly 100 percent in the segmentation of the digits.
The K-Means Algorithm process is as follows:
•The dataset is partitioned into K clusters and the data points are randomly assigned
to the clusters.
•For each data point:
•Calculate the distance from the data point to each cluster.
•If the data point is closest to its own cluster, we leave it, and if not
move it into the closest cluster.
•Repeating the above step until a complete pass through all the data points resulting
in no data point moving from one cluster to another.
The Proposed System
4. Feature Extraction
When the input data to an algorithm is too large to be processed and it is
suspected to be notoriously redundant (much data, but not much
information) then the input data will be transformed into a reduced
representation set of features (also named features vector).
Transforming the input data into the set of features is called Feature
extraction.
The feature vector must contain information that is
- useful to identify and differentiate speech sounds
- identify and differentiate between speakers
There are some methods such as FFT, LPC, Real Cepstrum and MFCC.
The Proposed System
Mel Frequency Cepstrum Coefficients (MFCC):
 Take the Fourier transform of a signal.
 Map the powers of the spectrum obtained above onto
the mel scale, using triangular overlapping windows.
 Take the logs of the powers at each of the mel frequencies.
 Take the discrete cosine transform of the list of mel log
powers, as if it were a signal.
 The MFCCs are the amplitudes of the resulting spectrum.
The Proposed System
5. Neural Network Classifier
There are many Neural Models, Each
model has advantages and disadvantages
depending on the application. According
to our application we choose
Support Vector Machine (SVM)
The Proposed System
Support Vector Machine (SVM):
A Support Vector Machine (SVM) is implemented using
the kernel Adatron algorithm which constructs a
hyperplane or set of hyperplanes in a high dimensional
space, which can be used for classification, regression or
other tasks. Intuitively, a good separation is achieved by
the hyperplane that has the largest distance to the
nearest training data points of any class (so-called
functional margin), since in general the larger the margin
the lower the generalization error of the classifier.
The Proposed System
Support Vector Machine (SVM):
H3 (green) doesn’t separate the two classes; H1 (blue) separates the
two classes but with a small margin and H2 (red) separates the two
classes with the maximum margin.
 Introduction
 Characteristics of Speech Signal
 History of Speech & Previous Research
 The Proposed System
Results and Conclusions
Results and Conclusions
Training and Testing
Support Vector Machine (SVM)
We use the SVM network and adapting its parameter as
follows:
no hidden layers.
The output layer has 10 neurons.
 And we train with maximum epochs of 1000.
We have 10000 samples, we divide them into:
 Training: 70%
 Cross Validation: 15%
 Testing: 15%
Results and Conclusions
Results
Cross Validation Confusion Matrix of the SVM
0
1
2
3
4
5
6
7
8
9
0
100.00
0.00
0.00
0.00
0.00
0.00
0.00
0.00
0.00
0.00
1
0.00
96.00
0.00
0.00
0.00
0.00
0.00
0.00
4.00
0.00
2
0.00
0.00
90.00
0.00
0.00
0.00
0.00
0.00
10.00
0.00
3
0.00
0.00
0.00
100.00
0.00
0.00
0.00
0.00
0.00
0.00
4
4.00
0.00
0.00
0.00
94.00
0.00
0.00
0.00
2.00
0.00
5
7.00
0.00
0.00
0.00
0.00
89.00
0.00
0.00
0.00
4.00
6
0.00
0.00
0.00
0.00
0.00
0.00
92.00
0.00
0.00
8.00
7
0.00
0.00
0.00
0.00
0.00
2.00
4.00
90.00
0.00
4.00
8
0.00
0.00
0.00
0.00
0.00
0.00
0.00
0.00
100.00
0.00
9
0.00
0.00
0.00
0.00
0.00
0.00
6.00
0.00
0.00
94.00
Results and Conclusions
Results
The Testing Confusion Matrix of the SVM
Output /
Desired
0
1
2
3
4
5
6
7
8
9
0
1
2
3
4
5
6
7
8
9
255
5
0
4
0
0
6
0
0
3
0
313
0
0
1
0
0
0
6
0
2
0
122
0
0
0
0
0
0
0
2
4
0
105
0
0
1
0
2
0
0
0
0
0
135
0
0
6
0
1
0
0
0
0
0
90
3
0
1
1
4
0
0
1
0
0
83
0
0
0
0
6
2
2
1
4
0
119
2
2
0
5
0
5
0
0
6
0
95
0
0
0
0
0
0
0
0
0
0
95
Results and Conclusions
Results
Performance =
(255+313+122+105+135+90+83+119+95+95) / 1500
= 1412 / 1500 = 94.13 %
Results and Conclusions
•Conclusion
A spoken Arabic digits recognizer is designed to investigate the
process of automatic digits recognition.
The Segmentation process is implemented by two techniques;
semi-automatic and fully-automatic.
The feature extracted by using MFCC technique.
This system is based on NN and by using Colloquial Egyptian
dialect within a noisy environment and carried out by neuro
solution tools.
The performance of the system is nearly 94% when we use
(SVM).
THANK YOU!