Uncertainty in Artificial Intelligence
First Name   Last Name   Password   Forgot Password   Log in!
    Proceedings   Proceeding details   Article details         Authors         Search    
Statistical Modeling in Continuous Speech Recognition (CSR)(Invited Talk)
Steve Young
Abstract:
Automatic continuous speech recognition (CSR) is sufficiently mature that a variety of real world applications are now possible including large vocabulary transcription and interactive spoken dialogues. This paper reviews the evolution of the statistical modelling techniques which underlie current-day systems, specifically hidden Markov models (HMMs) and N-grams. Starting from a description of the speech signal and its parameterisation, the various modelling assumptions and their consequences are discussed. It then describes various techniques by which the effects of these assumptions can be mitigated. Despite the progress that has been made, the limitations of current modelling techniques are still evident. The paper therefore concludes with a brief review of some of the more fundamental modelling work now in progress.
Keywords:
Pages: 562-571
PS Link:
PDF Link: /papers/01/p562-young.pdf
BibTex:
@INPROCEEDINGS{Young01,
AUTHOR = "Steve Young ",
TITLE = "Statistical Modeling in Continuous Speech Recognition (CSR)(Invited Talk)",
BOOKTITLE = "Proceedings of the Seventeenth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-01)",
PUBLISHER = "Morgan Kaufmann",
ADDRESS = "San Francisco, CA",
YEAR = "2001",
PAGES = "562--571"
}


hosted by DSL   •   site info   •   help