Upload
bozica
View
20
Download
0
Embed Size (px)
DESCRIPTION
Speaker Identification Using Wavelet Analysis and ANN. Dr. Anupam Shukla Dr. Ritu Tiwari Hemant Kumar Meena Rahul Kala. - PowerPoint PPT Presentation
Citation preview
Indian Institute of Information Technology and Management Gwalior 24/12/2008
DR. ANUPAM SHUKLADR. RITU TIWARI
HEMANT KUMAR MEENARAHUL KALA
Speaker Identification Using Wavelet Analysis and
ANN
Shukla, Anupam; Tiwari, Ritu; Meena, Hemant Kumar & Kala, Rahul; “Speaker Identification using Wavelet Analysis and Artificial Neural Networks”, proceedings of the National Symposium on Acoustics (NSA) 2008
Indian Institute of Information Technology and Management Gwalior 24/12/2008
1. INTRODUCTION2. TECHNIQUES USED3. PROCEDURE4. RESULTS5. CONCLUSION
Index
Indian Institute of Information Technology and Management Gwalior 24/12/2008
IntroductionIdentification of a person is a very traditional
problem.
Finger print recognition, face recognition, signature recognition are common techniques.
Speaker recognition or Automatic Speaker Identification (ASI) identifies an author based on the words spoken.
We have used wavelet analysis to extract the various features and Artificial Neural Networks to identify the speaker by the extracted features.
Indian Institute of Information Technology and Management Gwalior 24/12/2008
Common Techniques
1. Analysis techniquesFourier AnalysisShort Time Fourier AnalysisWavelet Analysis
2. Artificial Neural Networks
Indian Institute of Information Technology and Management Gwalior 24/12/2008
Analysis Techniques
We have used Wavelet transform to extract characteristics, which is an advancement over Fourier analysis and Short Time Fourier Analysis (STFT).
Indian Institute of Information Technology and Management Gwalior 24/12/2008
Fourier Analysis
Indian Institute of Information Technology and Management Gwalior 24/12/2008
Short Time Fourier Analysis
Indian Institute of Information Technology and Management Gwalior 24/12/2008
Wavelet Analysis
It is a windowing technique with variable-sized regions.
Wavelet analysis allows the use of different time intervals for different type frequency information.
Indian Institute of Information Technology and Management Gwalior 24/12/2008
Wavelet Analysis(Cont..)
Indian Institute of Information Technology and Management Gwalior 24/12/2008
Wavelet Analysis(Cont..)
Capable of revealing aspects of data
Wavelet packet methodSignal decomposition
Indian Institute of Information Technology and Management Gwalior 24/12/2008
Wavelet Packet Analysis
Indian Institute of Information Technology and Management Gwalior 24/12/2008
Artificial Neural Network
Excellent means of machine learning
Reputed training of the system to learn the given data
Testing
Performance
Indian Institute of Information Technology and Management Gwalior 24/12/2008
Procedure
Collection of data sets
Analysis of data sets (feature extraction)
Training of ANN
Testing
Result
Indian Institute of Information Technology and Management Gwalior 24/12/2008
Normalization of Data
Ii=(Vi - Mean(Vij) ) / (Max(Vij) - Mean(Vij) ), for all j
Here Ii is th ith input of the neural network
Vi is the ith feature extracted from Wavelet Analysis
Mean(Vi) is the mean of all Vij found in the training data set
Max(Vi) is the maximum of all Vij found in training data set for all j in data set
Indian Institute of Information Technology and Management Gwalior 24/12/2008
Feature Extracted
Indian Institute of Information Technology and Management Gwalior 24/12/2008
Result
Performance of 97.5%
This clearly shows that the algorithm works well and gives correct results on almost all inputs.
20 speakers and 40 test cases (39 correctly identified)
Indian Institute of Information Technology and Management Gwalior 24/12/2008
Conclusions