EUVIMEDEUVIMED entdecken
Crossref

The Application of Hidden Markov Models in Speech Recognition

Mark Gales, Steve Young

Foundations and Trends® in Signal Processing · 21.02.2008 · 1 (3) · 195-304

DOI: 10.1561/2000000004 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Foundations and Trends® in Signal Processing, online erschienen am 21.02.2008. Verfasst von Mark Gales und 1 weiteren Autor:innen. Die Arbeit wurde bisher 486-mal zitiert (Crossref) und nennt 201 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 aim of this review is first to present the core architecture of a HMM-based LVCSR system and then 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. The review concludes with a case study of LVCSR for Broadcast News and Conversation transcription in order to illustrate the techniques described.

Zitieren

APA

Gales, M., & Young, S. (2008). The Application of Hidden Markov Models in Speech Recognition. Foundations and Trends® in Signal Processing, 1(3), 195-304. https://doi.org/10.1561/2000000004

Vancouver

Gales M, Young S. The Application of Hidden Markov Models in Speech Recognition. Foundations and Trends® in Signal Processing. 2008;1(3):195-304. doi:10.1561/2000000004

BibTeX
@article{Gales2008,
  author = {Gales, Mark and Young, Steve},
  title = {The Application of Hidden Markov Models in Speech Recognition},
  journal = {Foundations and Trends® in Signal Processing},
  year = {2008},
  volume = {1},
  number = {3},
  pages = {195--304},
  doi = {10.1561/2000000004}
}
Kostenlos starten →