ROBUST SPEECH RECOGNITION FOR UNKNOWN COMMUNICATION CHANNELS

11:30 Thursday Posters

12:30 Lunch

Second Session: Robust features and environmental compensation

Chairman: Herve Bourlard, Idiap Switzerland

• 2:30 First Keynote Speaker
  Steven Greenberg: International Computer Science Institute, U.S.A.
  On the Origins of Speech Intelligibility in the Real World

• 3:05 Second Keynote Speaker
  Richard M. Stern: Carnegie Mellon University, U.S.A.
  Compensation for environmental degradation in automatic speech recognition
  • 3:40 Coffee Break

  • 4:00 Discussant: John Hansen Duke University, U.S.A.

  • 4:15 Discussant: Nelson Morgan, International Computer Science Institute, U.S.A.

  • 4:30 General discussion

    ---

    5:00 Thursday Posters

  ---

  7:00 Reception and Dinner

  A welcome reception will take place at the City Hall of Nancy on "Place Stanislas" on Thursday, April 17, followed by the conference dinner in a restaurant on "Place Stanislas".

  ---

  Friday April 18th 1997

  Third Session: Stochastic Modeling, Adaptation and Model Compensation

  Chairman: Roger Moore, DRA, England

  • 9:00: First Keynote Speaker
    Chin Lee: Bell Laboratories, Lucent Technologies, U.S.A.
    On Feature and Model Compensation Approach to Robust Speech Recognition

  • 9:35: Second Keynote Speaker
    Mark Gales: Cambridge University Engineering Department, England
    "Nice" Model-Based Compensation Schemes for Robust Speech Recognition
    • 10:10: Coffee break

    • 10:30 Discussant: Hynek Hermansky: OGI, U.S.A.

    • 10:45 Discussant: Rick Rose, AT&T Laboratories, U.S.A.

    • 11:00 General Discussion

    ---

    11:30 Friday Posters

    ---

    12:30 Lunch

    ---

    Fourth Session: Multi-Microphone, Hands-Free and Telephone Speech Recognition

    Chairman: Rick Rose, AT&T Labs, U.S.A

    • 2:30 First Keynote Speaker
      Maurizio Omologo: Istituto per la Ricerca Scientifica e Tecnologica, Italy
      On the future trends of hands-free ASR: variabilities in the environmental conditions and in the acoustic transduction
    • 3:05 Second Keynote Speaker
      Shigeki Sagayama: Speech & Acoustics Lab, NTT Human Interface Laboratories, Japan
      Issues Relating to the Future of ASR for Telecommunications Applications
      • 3:40 Coffee Break
      • 4:00 Discussant: Denis Jouvet, CNET, France
      • 4:10 Discussant: Philipp Lockwood, Matra, France
      • 4:20 Discussant: Mohan Sondhi, Bell Laboratories, Lucent Technologies
      • 4:30 General discussion

        ---

        5:00 Friday Posters

        ---

        6:00 Summary (J-C. Junqua, J-P. Haton and Phil Green)

        ---

        ...... Dinner

        ---

        This site is maintained by Phil Green (p.green@dcs.shef.ac.uk)

        Last updated 30th January 1997