Speaker Verification System using SVM

1
Speaker Verification System using SVM
Jun-Won Suh Intelligent Electronic Systems Human
and Systems Engineering Department of Electrical
and Computer Engineering
2
Outline Summary of Ph.d Dissertation of Vincent
Wan

• Speaker verification system
• Extracting features
• Creating models of speakers
• Generative models, discriminative models
• Making generative models discriminative
• Developing speaker verification using SVMs
• My interest to improve our system.

3
Speaker verification system

• Authenticate a persons claimed identity
• Text dependent and independent
• The system models the sound of the clients
  voice. (based on physical characteristics of the
  clients vocal tract.)

• Feature extraction
• Enrolment
• Creates a model for clients voice
• Pattern matching
• Decision theory

A generic speaker verification system
4
Extracting features

• Building models of speakers depends on frequency
  analysis of the speakers voice.
• Linear predictive coding (LPC)
• LPC assumes that speech can be modelled as the
  output of periodic pulses or random noise.
• The solutions for these LPC coefficients is
  obtained by minimizing MSE.
• Perceptual linear prediction (PLP)
• PLP combines LPC analysis with psychophysics
  knowledge of the human auditory system.
• Ex Human ear has a higher frequency resolution
  at low frequencies.

5
Creating models of speakers

• Generative models
• Gaussian Mixture Model (GMM), Hidden Markov
  Model (HMM)
• Models are probability density estimators that
  attempt to capture all of the fluctuations and
  variations of the data.
• Discriminative models
• Polynomial classifiers, Support Vector Machines
  (SVM)
• Models are optimized to minimize the error on a
  set of training samples.
• Models draw the boundary between classes and
  ignores the fluctuations within each class.
• Generative models discriminative
• Generative models use to estimate the within
  class probability densities and do not minimize a
  classification error.
• Discriminative models achieves the highest
  performance in classification tasks.

6
Making generative models discriminative

• GMM-LR/SVM combination
• GMM likelihood ratio
• Bengio proposed that the probability estimates
  are not perfect and a better version would be
• Bayes decision rule

• The input to the SVM is the two dimensional
  vector made up of the log likelihoods of the
  client and world models.
• A limitation of these approaches arises from
  frame basis discrimination.

7
Importance of kernels

• Early SVM using polynomial and RBF kernels
• Optimization problems requiring significant
  computational resources that were unsustainable.
• Employing cluster algorithms to reduce the
  accuracy.
• Frame level training inputs discard the useful
  speaker classification information.
• SVM using score-space kernels
• The variable length of utterance can be
  classified by sequence level.

8
Classifying sequences using score-space kernels

• The score-space kernel enables SVMs to classify
  whole sequences.
• A variable length sequence of input vectors is
  mapped explicitly onto a single point in a space
  of fixed dimension.
• The score-space is derived from the likelihood
  score.
• The likelihood ratio score-space

9
Computing the score-space vectors
Define the global likelihood of a sequence X
x1, , xNl
10
Computing the score-space vectors

• The fixed length vectors of the likelihood ration
  kernel can be expressed as
• The final likelihood ratio kernel is
• The dimensionality of the score-space is equal to
  the total number of parameters in the generative
  models. Hence the SVM can classify the complete
  utterance sequences.

11
Experiment Results on PolyVar

• The data has a noise.
• The data has a much more clients tests than YOHO.

12
Conclusion

• Add GMM-LR/SVM model in our verification system
• Add score-space kernel on SVM
• Need to compare the computation requirement for
  Fisher and LR kernels.

13
References

• V. Wan, Speaker Verification using Support
  Vector Machines, University of Sheffield, June
  2003
• V. Wan, Building Sequence Kernels for Speaker
  Verificaiton and Speech Recognition, University
  of Sheffield
• S. Bengio, and J. Marithoz, Learning the
  Decision Function for the Speaker Verification,
  IDIAP, 2001