Recent Advances in Speech Understanding and Dialog Systems

1. Front Matter

   Pages I-X

   PDF

2. Speech Coding and Segmentation

   1. Invited Papers

      1. Recent Advances in Speech Coding

         • D. Wolf, H. Reininger

         Pages 1-23

      2. Acoustic-Phonetic Decoding of Speech

         • Richard M. Schwartz, Y. Chow, M. Dunham, O. Kimball, M. Krasner, F. Kubala et al.

         Pages 25-49

      3. Knowledge-Based Approaches in Acoustic-Phonetic Decoding of Speech

         • Jean-Paul Haton

         Pages 51-69

      4. The Use of Prosodic Parameters in Automatic Speech Recognition

         • J. Vaissière

         Pages 71-99

   2. Contributed Papers

      1. Prosodic Features in German Speech: Stress Assignment by Man and Machine

         • E. Nöth, H. Niemann, S. Schmölz

         Pages 101-106

      2. Recognition of Speech using Temporal Decomposition

         • Gérard Chollet, Gunnar Ahlbom, Frédéric Bimbot

         Pages 107-110

      3. Long Term Analysis-Synthesis of Speech by Non-Stationary AR Methods

         • Susanna Ragazzini

         Pages 111-115

      4. Using Contextual Information in View of Formant Speech Analysis Improvement

         • O. Al-Dakkak, G. Murillo, G. Bailly, B. Guérin

         Pages 117-122

      5. A Speech Recognition Strategy Based on Making Acoustic Evidence and Phonetic Knowledge Explicit

         • P. D. Green, M. P. Cooke, H. H. Lafferty, A. J. H. Simons

         Pages 123-128

      6. On Finding Objects in Spectrograms: A Multiscale Relaxation Labelling Approach

         • M. P. Cooke, P. D. Green

         Pages 129-133

      7. Phonetic Segmentation Using Psychoacoustic Speech Parameters

         • J.-P. Martens

         Pages 135-139

      8. Morphological Representation of Speech Knowledge for Automatic Speech Recognition Systems

         • Mathew J. Palakal

         Pages 141-146

      9. Speaker-Independent Automatic Recognition of Plosive Sound in Letters and Digits

         • Régis Cardin

         Pages 147-151

      10. A Real-Time Auditory Model: Description and Applications in an ASR Acoustic-Phonetic Front End

          • Frank Gooding, Ian Shaw, Husein Mahdi

          Pages 153-157

      11. A New Phonematic Approach to Speech Recognition

          • A. J. Rubio-Ayuso, J. M. Herrera-Garrido

          Pages 159-163

      12. Primary Perceptual Units in Word Recognition

          • Walter F. Sendlmeier

          Pages 165-169

      13. Context-Dependent Phone Markov Models for Speech Recognition

          • Anne-Marie Derouault

          Pages 171-175

      14. Speech Recognition Based on Speech Units

          • G. Zanellato

          Pages 177-182

3. Word Recognition

   1. Invited Papers

      1. Mathematical Foundations of Hidden Markov Models

         • Lawrence R. Rabiner

         Pages 183-205

This volume contains invited and contributed papers presented at the NATO Advanced study Insti tute on "Recent Advances in Speech Understanding and Dialog systems" held in Bad Windsheim, Federal Republic of Germany, July 5 to July 18, 1987. It is divided into the three parts Speech coding and Segmentation, Word Recognition, and Linguistic Processing. Although this can only be a rough organization showing some overlap, the editors felt that it most naturally represents the bottom-up strategy of speech understanding and, therefore, should be useful for the reader. Part 1, SPEECH CODING AND SEGMENTATION, contains 4 invited and 14 contributed papers. The first invited paper summarizes basic properties of speech signals, reviews coding schemes, and describes a particular solution which guarantees high speech quality at low data rates. The second and third invited papers are concerned with acoustic-phonetic decoding. Techniques to integrate knowledge­ sources into speech recognition systems are presented and demonstrated by experimental systems. The fourth invited paper gives an overview of approaches for using prosodic knowledge in automatic speech recogni tion systems, and a method for assigning a stress score to every syllable in an utterance of German speech is reported in a contributed paper. A set of contributed papers treats the problem of automatic segmentation, and several authors successfully apply knowledge-based methods for interpreting speech signals and spectrograms. The last three papers investigate phonetic models, Markov models and fuzzy quantization techniques and provide a transi tion to Part 2 .

• cognition
• hidden Markov model
• knowledge
• knowledge base
• linguistics
• search algorithm
• speech recognition

• Universität Erlangen-Nürnberg, Erlangen, Germany

  H. Niemann, G. Sagerer

• ZT ZTI SYS 5, Siemens AG, München 83, Germany

  M. Lang

Policies and ethics