Connectionist Speech Recognition

Lieferzeit: Lieferbar innerhalb 14 Tagen

213,99 

A Hybrid Approach, The Springer International Series in Engineering and Computer Science 247

ISBN: 0792393961
ISBN 13: 9780792393962
Autor: Bourlard, Hervé A/Morgan, Nelson
Verlag: Springer Verlag GmbH
Umfang: xxix, 313 S.
Erscheinungsdatum: 31.10.1993
Produktform: Gebunden/Hardback
Einband: GEB

Describes the theory and implementation of a method to incorporate neural network approaches into state-of-the-art continuous speech recognition systems based on hidden Markov models (HMMs) to improve their performance. This book illustrates both the advantages and limitations of neural networks in the framework of a statistical systems.

Artikelnummer: 1564490 Kategorie:

Beschreibung

InhaltsangabeList of Figures. List of Tables. Notation. Foreword. Preface. I: Background. 1. Introduction. 2. Statistical Pattern Classification. 3. Hidden Markov Models. 4. Multilayer Perceptions. II: Hybrid HMM/MLP Systems. 5. Speech Recognition using ANNs. 6. Statistical Inference in MLPs. 7. The Hybrid HMM/MLP Approach. 8. Experimental Systems. 9. Context-Dependent MPLs. 10. System Tradeoffs. 11. Training Hardware and Software. III: Additional Topics. 12. Cross-Validation in MLP Training. 13. HMM/MLP and Predictive Models. 14. Feature Extraction by MLP. IV: Finale. 15. Final System Overview. 16. Conclusions. Bibliography. Index. Acronyms.

Inhaltsverzeichnis

List of Figures. List of Tables. Notation. Foreword. Preface. I: Background. 1. Introduction. 2. Statistical Pattern Classification. 3. Hidden Markov Models. 4. Multilayer Perceptions. II: Hybrid HMM/MLP Systems. 5. Speech Recognition using ANNs. 6. Statistical Inference in MLPs. 7. The Hybrid HMM/MLP Approach. 8. Experimental Systems. 9. Context-Dependent MPLs. 10. System Tradeoffs. 11. Training Hardware and Software. III: Additional Topics. 12. Cross-Validation in MLP Training. 13. HMM/MLP and Predictive Models. 14. Feature Extraction by MLP. IV: Finale. 15. Final System Overview. 16. Conclusions. Bibliography. Index. Acronyms.

Das könnte Ihnen auch gefallen …