Speech recognition in multiple languages and domains: the 2003 BBN/LIMSI EARS system
Authors:
- 28 September 2004
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3 (15206149)
Abstract
We report on the results of the first evaluations for the BBN/LIMSI system under the new DARPA EARS program. The evaluations were carried out for conversational telephone speech (CTS) and broadcast news (BN) for three languages: English, Mandarin, and Arabic. In addition to providing system descriptions and evaluation results, the paper highlights methods that worked well across the two domains and those few that worked well on one domain but not the other. For the BN evaluations, which had to be run under 10 times real-time, we demonstrated that a joint BBN/LIMSI system with a time constraint achieved better results than either system alone.Keywords
This publication has 16 references indexed in Scilit:
- A compact model for speaker-adaptive training2002
- Improvements in linear transform based speaker adaptation2002
- Progress in transcription of Broadcast News using ByblosSpeech Communication, 2002
- The LIMSI Broadcast News transcription systemSpeech Communication, 2002
- Lightly supervised and unsupervised acoustic model trainingComputer Speech & Language, 2002
- Large scale discriminative training of hidden Markov models for speech recognitionComputer Speech & Language, 2002
- Heteroscedastic discriminant analysis and reduced rank HMMs for improved speech recognitionSpeech Communication, 1998
- Maximum likelihood linear transformations for HMM-based speech recognitionComputer Speech & Language, 1998
- Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov modelsComputer Speech & Language, 1995
- Perceptual linear predictive (PLP) analysis of speechThe Journal of the Acoustical Society of America, 1990