Some activities on Non-linear Speech Processing at ENST/CNRS-LTCI

1
Some activities on Non-linear Speech Processing
at ENST/CNRS-LTCI
Gérard CHOLLETchollet_at_tsi.enst.fr
ENST/CNRS-LTCI46 rue Barrault75634 PARIS cedex
13http//www.tsi.enst.fr/chollet
2
Outline

• What is ENST/CNRS-LTCI ?
• Research and application topics related to
  COST-277
• Speech production and perception,
• Speech analysis and synthesis,
• Speech coding
• The SYMPATEX project
• Automatic speech recognition
• The SIROCCO project
• Speaker characterisation and verification
• Perspectives within COST-277

3
Our affiliations
ENST Ecole Nationale Supérieure des
Télécommunicationshttp//www.enst.fr CNRS
Centre National de la Recherche
Scientifiquehttp//www.cnrs.fr LTCI
Laboratoire de Traitement et Communication de
lInformation http//www.enst.fr/externe/ura.html
4
What is ENST?Ecole Nationale de
Télécommunications

• classed among the
• Grandes Ecoles d'Ingénieurs.
• 250 state certified engineers
• each year .
• part of Groupement des Ecoles
• de Télécommunications

5
GET Groupement des Ecoles de Télécommunications

• ENST-Paris ( )
• ENST-Bretagne in Brest
• Institut National des Télécommunications in Evry
• EURECOM in Sophia-Antipolis
• ENIC (Ecole Nouvelle dIngénieurs en Télécoms) in
  Lille
• Internet school in Marseille

6
Speech Production and Perception

• Parametric Vocal Tract model (Shinji Maeda)
• Non-linear Production model using Distinctive
  Regions and Modes (René Carré)
• Quantal nature of speech (R. Carré and S. Maeda)
• Perceptual filter (Nicolas Moreau)
• Auditory prosthesis (Alain Goyé and Jacques Prado)

7
Speech analysis and synthesis

• Time-Frequency representations, Wavelets
• Time-dependent spectral models (Yves Grenier)
• HNM (Harmonics Noise Model)(Olivier Cappé,
  Eric Moulines, Maurice Charbit)
• Glottal Excited LPC

8
Time-dependent Spectral Models

• Temporal Decomposition (B. Atal, 1983)
• Vectorial Autoregressive models with detection of
  model ruptures (A. DeLima, Y. Grenier)
• Segmental parameterisation using a time-dependent
  polynomial expansion (Y. Grenier)

9
Temporal Decomposition
10
HNM Harmonics Noise Model
11
A L I S P

• A utomatic
• L anguage
• I ndependent
• S peech
• P rocessing

Automatic discovery of segmental units for
speech coding, synthesis, recognition,
language identification and speaker verification.
12
Speech Coding by indexing
SYMPATEX
SYstème de Messagerie unifiée avec présentation
vocale des messages (PArole et TEXte)
Thomson-CSF, ELAN TTS, Irius
GET, ESIEE
13
Coding principle ?
14
? Decoding
15
Automatic Speech Recognition

• Recognition of proper names and spellings
• Keyword spotting, noise robustness, adaptation
• Large Vocabulary Speech Recognition (SIROCCO)
• http//perso.enst.fr/sirocco/index-en.htm
  l
• Markov Random Fields, Bayesian Networks and
  Graphical Models

16
Markov Random Fields Bayesian Networks and
Graphical Models

• Speech modelling with state constrained
• Markov Random Field over Frequency bands
• (Guillaume Gravier and Marc Sigelle)
• http//perso.enst.fr/ggravier/recherche.h
  tmlthese
• Comparative framework to study MRF,
• Bayesian Networks and Graphical Models.
• http//www.cs.berkeley.edu/murphyk/Bayes/bay
  es.html

17
Speaker Verification

• Typology of approaches (EAGLES Handbook)
• Text dependent
• Public password
• Private password
• Customized password
• Text prompted
• Text independent
• Incremental enrolment
• Evaluation

18
Speaker Verification (text independent)

• The ELISA consortium
• ENST, LIA, IRISA, ...
• http//www.lia.univ-avignon.fr/equipes/RAL/elisa/i
  ndex_en.html
• NIST evaluations
• http//www.nist.gov/speech/tests/spk/index.htm

19
Support Vector Machines and Speaker
Verification

• Hybrid GMM-SVM system is proposed
• SVM scoring model trained on development data to
  classify true-target speakers access and
  impostors access,using new feature
  representation based on GMMs

20
SVM principles
21
Results
22
Voice technology in Majordome

• Server side background tasks
• continuous speech recognition applied to voice
  messages upon reception
• Detection of senders name and subject
• User interaction
• Speaker identification and verification
• Speech recognition (receiving user commands
  through voice interaction)
• Text-to-speech synthesis (reading text summaries,
  E-mails or faxes)

23
Perspectives within COST-277

• Text-book on Speech Processing
• Evaluation of parametric representations of
  speech for diverse applications
• Fundamental work on voice transformations with
  applications in coding, synthesis, recognition
  and speaker characterisation
• Fundamental work on noise robustness with
  applications in coding, recognition and speaker
  verification