The Spoken Language Translator
This book presents a detailed description of Spoken Language Translator (SLT), one of the first major projects in the area of automatic speech translation. The SLT system can translate between English, French, and Swedish in the domain of air travel planning, using a vocabulary of about 1500 words, and with an accuracy of about 75 per cent. The greater part of the book describes the language processing components, which are largely built on top of the SRI Core Language Engine, using a combination of general grammars and techniques that allow them to be rapidly customized to specific domains. Speech recognition is based on Hidden Markov Mode technology, and uses versions of the SRI DECIPHER system. This account of the Spoken Language Translator should be an essential resource both for those who wish to know what is achievable in spoken-language translation today, and for those who wish to understand how to achieve it.
- This is a major book about one of the first speech translation systems
- One of a very small number of books that give detailed descriptions of large implemented speech-understanding systems
- The book describes how many different techniques, both statistical and rule-based, were combined to create the SLT system
Reviews & endorsements
'… the book provides a fine overview of the main considerations in the development of a domain-specific speech translation system. The editors have ensured that the main issues are covered, and much effort has been made to ensure a balance in both form and contents from one chapter to another.' M. C. L'Homme, Computing Reviews
'… an essential resource both for those who wish to know what is achievable in spoken language translation today, and for those who wish to understand how to achieve it.' Zentralblatt für Mathematik
'… a very accessible account of a mainly rule-based system for translating spoken language. … the book is very well written and structured. There are many lessons here for subsequent generations of speech and language researchers. … it would be a good primer for anyone wishing to develop a serious speech or language processing system.' Journal of Natural Language Processing
Product details
August 2007Paperback
9780521038829
356 pages
228 × 151 × 20 mm
0.522kg
25 b/w illus. 33 tables
Available
Table of Contents
- Preface
- Acknowledgements
- 1. Introduction
- Part I. Language Processing and Corpora:
- 2. Translation using the core language engine
- 3. Grammar specialisation
- 4. Choosing among interpretations
- 5. The TreeBanker
- 6. Acquisition of lexical entries
- 7. Spelling and morphology
- 8. Corpora and data collection
- Part II. Linguistic Coverage:
- 9. English coverage
- 10. French coverage
- 11. Swedish coverage
- 12. Transfer coverage
- 13. Rational reuse of linguistic data
- Part III. Speech Processing:
- 14. Speech recognition
- 15. Acoustic modelling
- 16. Language modelling for multilingual speech translation
- 17. Porting a recogniser to a new language
- 18. Multiple dialects and languages
- 19. Common speech/language issues
- Part IV. Evaluation and Conclusions:
- 20. Evaluation
- 21. Conclusions
- Appendix A: the mathematics of discriminant scores
- Appendix B: notation for QLF-based processing
- References
- Index.