Foundations and TrendsŪ in Signal Processing
THE APPLICATION OF HIDDEN MARKOV MODELS IN SPEECH RECOGNITION
by Mark Gales & Steve Young (Cambridge University, UK)
Hidden Markov Models (HMMs) provide a simple and effective framework for modelling time-varying spectral vector sequences. As a consequence, almost all present day large vocabulary continuous speech recognition (LVCSR) systems are based on HMMs. Whereas the basic principles underlying HMM-based LVCSR are rather straightforward, the approximations and simplifying assumptions involved in a direct implementation of these principles would result in a system which has poor accuracy and unacceptable sensitivity to changes in operating environment. Thus, the practical application of HMMs in modern systems involves considerable sophistication.
The Application of Hidden Markov Models in Speech Recognition presents the core architecture of a HMM-based LVCSR system and proceeds to describe the various refinements which are needed to achieve state-of-the-art performance. These refinements include feature projection, improved covariance modelling, discriminative parameter estimation, adaptation and normalisation, noise compensation and multi-pass system combination. It concludes with a case study of LVCSR for Broadcast News and Conversation transcription in order to illustrate the techniques described.
The Application of Hidden Markov Models in Speech Recognition is an invaluable resource for anybody with an interest in speech recognition technology.
Published by Now Publishers and marketed by World Scientific
Contents:
- Introduction
- Architecture of a HMM-Based Recogniser
- HMM Structure
Refinements
- Parameter Estimation
- Adaptation and Normalisation
- Noise Robustness
- Multi-Pass Recognition Architectures
- Conclusions
- Acknowledgements
- Notations and Acronyms
- References
Readership: Postgraduates, researchers and professionals.
| 112pp |
Pub. date: Mar 2008 |
|