Robustness in Automatic Speech Recognition

1. Front Matter

   Pages i-xxx

   PDF

2. Speech Communication by Humans and Machines

   1. Front Matter

      Pages 1-1

      PDF

   2. Nature and Perception of Speech Sounds

      • Jean-Claude Junqua, Jean-Paul Haton

      Pages 3-35

   3. Background on Speech Analysis

      • Jean-Claude Junqua, Jean-Paul Haton

      Pages 37-71

   4. Fundamentals of Automatic Speech Recognition

      • Jean-Claude Junqua, Jean-Paul Haton

      Pages 73-124

3. Robustness in ASR: Problems and Issues

   1. Front Matter

      Pages 125-125

      PDF

   2. Speaker Variability and Specificity

      • Jean-Claude Junqua, Jean-Paul Haton

      Pages 127-153

   3. Dealing with Noisy Speech and Channel Distortions

      • Jean-Claude Junqua, Jean-Paul Haton

      Pages 155-189

4. Possible Solutions and Some Perspectives

   1. Front Matter

      Pages 191-191

      PDF

   2. The Current Technology and Its Limits: An Overview

      • Jean-Claude Junqua, Jean-Paul Haton

      Pages 193-206

   3. Towards Robust Speech Analysis

      • Jean-Claude Junqua, Jean-Paul Haton

      Pages 207-231

   4. On the Use of a Robust Speech Representation

      • Jean-Claude Junqua, Jean-Paul Haton

      Pages 233-272

   5. ASR of Noisy, Stressed, and Channel Distorted Speech

      • Jean-Claude Junqua, Jean-Paul Haton

      Pages 273-323

   6. Word-Spotting and Rejection

      • Jean-Claude Junqua, Jean-Paul Haton

      Pages 325-345

   7. Spontaneous Speech

      • Jean-Claude Junqua, Jean-Paul Haton

      Pages 347-369

   8. On the use of Knowledge in ASR

      • Jean-Claude Junqua, Jean-Paul Haton

      Pages 371-392

   9. Application Domain, Human Factors, and Dialogue

      • Jean-Claude Junqua, Jean-Paul Haton

      Pages 393-428

5. Back Matter

   Pages 429-440

   PDF

Foreword Looking back the past 30 years. we have seen steady progress made in the area of speech science and technology. I still remember the excitement in the late seventies when Texas Instruments came up with a toy named "Speak-and-Spell" which was based on a VLSI chip containing the state-of-the-art linear prediction synthesizer. This caused a speech technology fever among the electronics industry. Particularly. applications of automatic speech recognition were rigorously attempt­ ed by many companies. some of which were start-ups founded just for this purpose. Unfortunately. it did not take long before they realized that automatic speech rec­ ognition technology was not mature enough to satisfy the need of customers. The fever gradually faded away. In the meantime. constant efforts have been made by many researchers and engi­ neers to improve the automatic speech recognition technology. Hardware capabilities have advanced impressively since that time. In the past few years. we have been witnessing and experiencing the advent of the "Information Revolution." What might be called the second surge of interest to com­ mercialize speech technology as a natural interface for man-machine communication began in much better shape than the first one. With computers much more powerful and faster. many applications look realistic this time. However. there are still tremendous practical issues to be overcome in order for speech to be truly the most natural interface between humans and machines.

• communication
• human factors
• production
• speech processing
• speech recognition

• Speech Technology Laboratory, USA

  Jean-Claude Junqua

• CRIN - INRIA, France

  Jean-Paul Haton

Policies and ethics