Referenced Items are not available for this document.
Maximum mutual information estimation of HMM parameters for continuous speech recognition using the
An application of discriminative training methods, maximum mutual information (MMI) training, to large-vocabulary continuous speech recognition is described. An algorithm is developed for efficient MMI estimation of HMM parameters, including exponential codebook coefficients, which cannot be estimated using maximum likelihood (ML) methods. Continuous speech recognition performance of the BYBLOS system on the DARPA 1000-word resource management speech corpus is presented
Published in:
Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on
Date of Conference: 3-6 Apr 1990
- Page(s):
- 701 - 704 vol.2
- Meeting Date :
- 03 Apr 1990-06 Apr 1990
- ISSN :
- 1520-6149
- INSPEC Accession Number:
- 3853972
- Conference Location :
- Albuquerque, NM
- Digital Object Identifier :
- 10.1109/ICASSP.1990.115863
About IEEE Xplore | Contact | Help | Terms of Use | Nondiscrimination Policy | Site Map | Privacy & Opting Out of Cookies
A not-for-profit organization, IEEE is the world's largest professional association for the advancement of technology.
© Copyright 2013 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.
