Speech recognition in multiple languages and domains: the 2003 BBN/LIMSI EARS system

Author

Schwartz, R. ; Colthurst, T. ; Duta, N. ; Gish, H. ; Iyer, R. ; Kao, C.-L. ; Liu, D. ; Kimball, O. ; Ma, J. ; Makhoul, J. ; Matsoukas, S. ; Nguyen, L. ; Noamany, M. ; Prasad, R. ; Xiang, B. ; Xu, D.-X. ; Gauvain, J.-L. ; Lamel, L. ; Schwenk, H. ; Adda, G.

Author_Institution

BBN Technol., Cambridge, MA, USA

Volume

3

fYear

2004

fDate

17-21 May 2004

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

hidden Markov models; natural languages; speech recognition; Arabic language; EARS system; English language; HMM; Mandarin language; broadcast news; conversational telephone speech; effective affordable reusable speech-to-text; multiple domain speech recognition; multiple language speech recognition; recognition word error rate reduction; Broadcasting; Collaborative work; Ear; Hidden Markov models; Natural languages; Real time systems; Speech recognition; Telephony; Testing; Time factors;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on

ISSN

1520-6149

Print_ISBN

0-7803-8484-9

Type

conf

DOI

10.1109/ICASSP.2004.1326654

Filename

1326654