Digit%20Recognition%20Using%20the%20SPEECHDAT%20Corpus

1
Robust Recognition of Digits and Natural Numbers
Frederico Rodrigues and Isabel Trancoso
INESC/IST, 2000
2
Summary

• Problem overview
• Baseline system
• Extensions to the baseline system
• Conclusions and future work

3
The Problem
4
Corpus Description

• Multilingual telephone speech corpus
• SPEECHDAT(M) 1000 speakers
• SPEECHDAT(II) 4000 speakers
• Orthographically transcribed including noise
  events

5
Noise events

• spk Speaker related noises
• sta Stationary noises
• int Intermittent noises

6
(No Transcript)
7
Train and Test Set Definition

• Selection procedure
• Age, gender and region distribution are
  approximately equal in both train and test sets
• SPEECHDAT II
• Fixed 500 speakers evaluation set
• Additional 300 speakers development set
• SPEECHDAT(M)
• 200 speakers evaluation set
• Overall ratio of 80 Train/20 Test

8
Sub-corpus Used

• I1 - Isolated digit strings
• B1 - Sequences of 10 digits
• N - Natural numbers

9
Feature Extraction

• MFCC (Mel Frequency Cepstral Coefficients)
• 14 Cepstra 14 ? Cepstra Energy ? Energy
• Speech signal band-limited between 200 and 3800
  Hz
• Hamming Window 25 ms each 10 ms
• Cepstral Mean Substraction
• Simple but effective technique for channel and
  speaker normalization

10
Acoustic Modeling

• Left-right continuous density HMMs
• Word models for each digit. No skips.
• Silence and filler models with forward and
  backward skips
• Gender dependent models

HMM Hidden Markov Model
11
Model Topology
Fillers and silence models topology
12
Baseline System - Isolated Digits

• Choose isolated digits with no noise marks
• HMM parameters initialized with the global mean
  and variance of the training data
• Embedded Baum-Welch Reestimation
• Evaluate performance withViterbi decoding
• Grammar allowing one digit and initial and final
  silence
• Grammar allowing one digit and any number of
  fillers or silence

13
Baseline System - Isolated Digits
14
Baseline System - Isolated Digits

• Increment Gaussian mixtures per state up to 3 for
  the digit models
• Introduce files with noise marks
• Repeat re-estimation/evaluation process
• Increment Gaussian mixtures per state up to 3 for
  the filler and digit models

15
Connected vs Isolated Digits
Example Number 3 1 2 6 said as Isolated
Digits t r e S u d o j S s 6 j S Connected
Digits t r e z u d o j S _ 6 j S
16
Baseline System - Connected Digits

• Use best isolated digit models as bootstrap
  models
• Repeat re-estimation/evaluation process
• Increment gradually Gaussian mixtures per state
  up to 5 for the digit models

17
Baseline System - Results
18
Extension to the Baseline System

• New way of modelling the filler models
• Same training/evaluation process
• Train the 9 filler and silence models with no
  skips
• Build a unique filler model concatenating all
  filler and silence models

19
New Filler Model Arquitecture
20
Results With New Filler Model
21
Natural Numbers

• Phone models with 3 states and no skips
• Larger vocabulary size
• May be adapted to other tasks
• Phones initialized from models already trained
  for a directory assistance task
• Digits are still modeled by word models
• Grammar for natural numbers ranging from zero to
  hundreds of millions

22
Natural Numbers Example
Number 25 Hypothesis 1 vinte e cinco (Twenty
and five) Hypotesis 2 vinte cinco (Twenty
five) But vinte cinco could also be the
sequence of natural numbers 20 5
23
Natural Numbers - Results
24
Sample Application
25
Conclusions and Future Work

• Explicitly modeling fillers is a difficult task
• Improved filler model decreases error rate up to
  50
• Develop context dependent models
• Solve vowel reduction and co-articulation
  problems
• Results may be improved through the use of
  discriminative training techniques