Speaker Recognition

1
Speaker Recognition

• Sharat.S.Chikkerur
• Center for Unified Biometrics and Sensors
• http//www.cubs.buffalo.edu

2
Speech Fundamentals

• Characterizing speech
• Content (Speech recognition)
• Signal representation (Vocoding)
• Waveform
• Parametric( Excitation, Vocal Tract)
• Signal analysis (Gender determination, Speaker
  recognition)
• Terminologies
• Phonemes
• Basic discrete units of speech.
• English has around 42 phonemes.
• Language specific
• Types of speech
• Voiced speech
• Unvoiced speech(Fricatives)
• Plosives
• Formants

3
Speech production
17 cm
Speech production mechanism
Speech production model
4
Nature of speech
Spectrogram
5
Vocal Tract modeling
Smoothened Signal Spectrum
Signal Spectrum

• The smoothened spectrum indciates the locations
  of the formants of each user
• The smoothened spectrum is obtained by cepstral
  coefficients

6
Parametric Representations Formants

• Formant Frequencies
• Characterizes the frequency response of the vocal
  tract
• Used in characterization of vowels
• Can be used to determine the gender

7
Parametric RepresentationsLPC

• Linear predictive coefficients
• Used in vocoding
• Spectral estimation

20
2
40
5
200
8
Parametric RepresentationsCepstrum
10
5
40
9
Speaker Recognition

• Definition
• It is the method of recognizing a person based on
  his voice
• It is one of the forms of biometric
  identification
• Depends of speaker dependent characteristics.

10
Generic Speaker Recognition System
Speech signal
Score
Analysis Frames
Feature Vector
Preprocessing
Feature Extraction
Pattern Matching
Verification
Preprocessing
Feature Extraction
Speaker Model
Enrollment

• Stochastic Models
• GMM
• HMM
• Template Models
• DTW
• Distance Measures

• LAR
• Cepstrum
• LPCC
• MFCC

• A/D Conversion
• End point detection
• Pre-emphasis filter
• Segmentation

• Choice of features
• Differentiating factors b/w speakers include
  vocal tract shape and behavioral traits
• Features should have high inter-speaker and low
  intra speaker variation

11
Our Approach

• Preprocessing
• Feature Extraction
• Speaker model
• Matching

12
Silence Removal

• Preprocessing
• Feature Extraction
• Speaker model
• Matching

13
Pre-emphasis

• Preprocessing
• Feature Extraction
• Speaker model
• Matching

14
Segmentation

• Preprocessing
• Feature Extraction
• Speaker model
• Matching

• Short time analysis
• The speech signal is segmented into overlapping
  Analysis Frames
• The speech signal is assumed to be stationary
  within this frame

Q31
Q32
Q33
Q34
15
Feature Representation

• Preprocessing
• Feature Extraction
• Speaker model
• Matching

Speech signal and spectrum of two users uttering
ONE
16
Speaker Model
17
Dynamic Time Warping

• Preprocessing
• Feature Extraction
• Speaker model
• Matching

• The DTW warping path in the n-by-m matrix is the
  path which has minimum average cumulative cost.
  The unmarked area is the constrain that path is
  allowed to go.

18
Results

• Distances are normalized w.r.t. length of the
  speech signal
• Intra speaker distance less than inter speaker
  distance
• Distance matrix is symmetric

19
Matlab Implementation
20
THANK YOU