EEL 6586-Automatic Speech Processing Hidden Markov Models for Speech Recognition - PowerPoint PPT Presentation

View by Category
About This Presentation
Title:

EEL 6586-Automatic Speech Processing Hidden Markov Models for Speech Recognition

Description:

Calibri Arial Office Theme 1_Office Theme 2_Office Theme Equation EEL 6586-Automatic Speech Processing Hidden Markov Models for Speech ... method Practical Pitfalls ... – PowerPoint PPT presentation

Number of Views:33
Avg rating:3.0/5.0
Slides: 21
Provided by: Savy6
Learn more at: http://www.cnel.ufl.edu
Category:

less

Write a Comment
User Comments (0)
Transcript and Presenter's Notes

Title: EEL 6586-Automatic Speech Processing Hidden Markov Models for Speech Recognition


1
EEL 6586-Automatic Speech ProcessingHidden
Markov Models for Speech Recognition
  • Savyasachi Singh
  • Computational NeuroEngineering Lab
  • March 28, 2007

2
Introduction
3
Model Parameters
4
Assumptions
5
Three basic problems
6
Evaluation Problem
7
Forward Algorithm
8
Backward Algorithm
9
Decoding Problem
10
Viterbi Algorithm
11
Learning Problem
12
ML Estimation EM algorithm
13
Baum Welch Algorithm
14
Re-estimation formulae
15
Gradient based method
16
Practical Pitfalls
17
Limitations
18
Isolated Word Recognition
HMM Word 1
HMM Word 2
FEATURE EXTRACTION
SELECT MAXIMUM
HMM Word 3
HMM Word K
19
Typical Implementations
20
HW 4 part c pseudocode
  • Chop speech signal into frames and extract
    features. (preferably MFCC)
  • Choose HMM parameters N, M, cov. type, A etc.
  • Start learning procedure for train set
  • for each word repeat following steps
  • for each state
  • Initialize GMMs and get parameters (use
    mixgauss_init.m)
  • end
  • Train HMM with EM (use mhmm_em.m)
  • end
  • Start testing procedure for test set
  • for each test utterance
  • Compare with all trained models and get log
    likelihood (score) using forward backward
    algorithm. (use mhmm_logprob.m)
  • Select model with highest score as recognized
    word.
  • end
  • 5. Tabulate confusion matrix.
About PowerShow.com