Claudio Becchetti and Lucio Prina Ricotti, Fondazione Ugo Bordoni, Rome, Italy
0471 97730 6
March 1999
Hardback/CD
432pp
Automatic Speech Recognition (ASR) is the enabling technology for hands-free dictation and voice-triggered computer menus.
It is becoming increasingly prevalent in environments such as private telephone exchanges and real-time information
services.
Providing a crucial source of information on the principles of ASR systems, this detailed and timely volume examines both
the theory and implementation issues behind multi-speaker continuous speech recognition. Focusing on the algorithms
employed in commercial and laboratory systems, this treatment enables readers to devise practical solutions for ASR system
problems.
It also presents a complete overview of C++ programming techniques used to develop ASR applications, thus offering skills
that will prove extremely useful in any large C++ based software project. Possible extensions of the well-established ASR
technology are highlighted, based on 'Hidden Markov Models' applied to fields such as modelling and prediction of
econometric series.
Accompanying CD-ROM includes the entire C++ source code
(Linux, MS-Windows) of a laboratory speech recognition system
Includes detailed theoretical, mathematical and technical explanations of ASR
Presents a practical account of the functioning of ASR
Contents:
Statistical Speech Recognition
Speech Database
Speech Signal Analysis
HMMs and Initialization
HMM Training
Language Models
Recognition
Evaluation and Parameter Setting
Econometric Appendix: The Behaviour of Financial Time Series