Speech Recognition and Coding

Acoustic Modeling

1. Front Matter

   Pages 1-1

   PDF

2. Automatic Recognition of Noisy Speech

   • Jean-Paul Haton

   Pages 3-13

3. Adaptive Learning in Acoustic and Language Modeling

   • Chin-Hui Lee, Jean-Luc Gauvain

   Pages 14-31

4. Evaluation of ASR Systems, Algorithms and Databases

   • Gérard Chollet

   Pages 32-40

5. Statistical and Discriminative Methods for Speech Recognition

   • B. H. Juang, Wu Chou, C. H. Lee

   Pages 41-55

6. Automatic Speech Labeling Using Word Pronunciation Networks and Hidden Markov Models

   • B. Angelini, F. Brugnara, D. Falavigna, D. Giuliani, R. Gretter, M. Omologo

   Pages 56-59

7. Heuristic Search Methods for a Segment Based Continuous Speech Recognizer

   • Nick Cremelie, Jean-Pierre Martens

   Pages 60-63

8. Dimension and Structure of the Vowel Space

   • Mylène Pijpers, Michael D. Alder, Yianni Attikiouzel

   Pages 64-67

9. Continuous Speech HMM Training System: Applications to Speech Recognition and Phonetic Label Alignment

   • J. Ferreiros, R. de Córdoba, M. H. Savoji, J. M. Pardo

   Pages 68-71

10. HMM Based Acoustic-Phonetic Decoding with Constrained Transitions and Speaker Topology

    • C. Barras, M.-J. Caraty, C. Montacié

    Pages 72-75

11. Experiments on a Fast Mixture Density Likelihood Computation

    • Peter Beyerlein

    Pages 76-79

12. Explicit Modelling of Duration in HMM: an Efficient Algorithm

    • A. Bonafonte, X. Ros, J. B. Mariño

    Pages 80-83

13. Acoustic-Phonetic Decoding of Spanish Continuous Speech with Hidden Markov Models

    • I. Torres, F. Casacuberta, A. Varona

    Pages 84-87

14. HMM-Based Speech Recognition in Noisy Car Environment

    • J. Hernando, C. Nadeu, J. B. Mariño

    Pages 88-91

15. Extensions to the AESA for Finding k-Nearest-Neighbours

    • Pablo Aibar, Alfons Juan, Enrique Vidal

    Pages 92-95

16. An Efficient Pruning Algorithm for Continuous Speech Recognition

    • Pedro García, J. Carlos Segura, Antonio J. Rubio-Ayuso, Jesus Díaz

    Pages 96-99

17. On the Performance of SCHMM for Isolated Word Recognition and Rejection

    • Carlos Teixeira, Isabel Trancoso, Antonio Serralheiro

    Pages 100-103

18. A Speaker Independent Isolated Word Recognition System for Turkish

    • Ö. B. Tüzün, E. Erzin, M. Demirekler, A. T. Memişoğlu, M. S. Uğur, A. E. Çetin

    Pages 104-107

19. The Speech Recognition Research System of the TU Dresden

    • Christian-M Westendorf, Rüdiger Hoffmann

    Pages 108-111