Professional Documents
Culture Documents
Internal Examiner:
External Examiner
INTRODUCTION
User login
Text-Prompted system
Playback attack
OUR SYSTEM
Feature : MFCC
Modeling and Classifications : both statistical
Carries both Speech Content and Speaker identity What makes Speech Signal Unique ?
Each phoneme resonates at its own fundamental frequency and harmonics of it Studied over short period : short time spectral analysis
Studied over long period : all the variations from that speaker
UNIQUENESS IN PHONEME
Phoneme /ah/
0.15
0.1
0.05
Amplitude
-0.05
-0.1
-0.15
Phoneme /i:/
0 500 1000 Samples 1500 2000 2500
-0.2
PREPROCESSING : STEPS
1)Silence Removal
1
0.5
-0.5
-1
8 x 10
9
4
Silence Signal
1
0.5
Silence Removed
-0.5
-1
0.5
1.5
2.5
3.5
4
4
2)Pre-Emphasis
Suppressed high Frequencies
|Y(f)|
2000
4000
8000
10000
12000
5 4 3 2 1 0
x 10
-3
|Y(f)|
2000
4000
8000
10000
12000
3)Framing
4)Windowing
0.04 0.03
Hamming Window
-0.02 -0.03
200
400
600
800
1000
1200
FEATURE EXTRACTION
Perceptual approach
Steps :
FFT Mel Filter Log DCT CMS
Mel Filter : 12
Filtering of absolute fft coefficients using triangular filter bank in Mel scale
Speech Recognition/Verification by
HMM/VQ
HMM is the extension of Markov Process Markov Process consist of observable states HMM has hidden states and observable symbols per states HMM is the stochastic model
HMM (CONTD)
Parameters
1) The initial state distribution () 2) State transition probability distribution (A) 3) Observation symbol probability distribution (B)
( A, B, )
( A, B, )
HMM IMPLEMENTATION
Feature Vector observation symbols , 256 Phonemes hidden states, 6 Left to right HMM Discrete Hidden Markov Model (DHMM) with Vector Quantization (VQ) technique
VECTOR QUANTIZATION
Speaker Recognition/Verification by
GMM
Mixture Model
Parametric probability density function Based on soft clustering technique Mixture of Gaussian components
= ( , , )
SPEAKER VERIFICATION
Based on likelihood ratio =
TOOLS USED
Languages:
Servers:
Versioning
Tortoise SVN
APPLICATION AREAS
Telephone transaction
Telephone credit card purchase, Telephone stock trading
Access control
Forensics
Thanks
Any queries ?