Transcribing broadcast news shows

Author

Gauvain, J.-L. ; Adda, G. ; Lamel, L. ; Adda-Decker, M.

Author_Institution

LIMSI, CNRS, Orsay, France

Volume

2

fYear

1997

fDate

21-24 Apr 1997

Firstpage

715

Abstract

While significant improvements have been made in large vocabulary continuous speech recognition of large read-speech corpora such as the ARPA Wall Street Journal-based CSR corpus (WSJ) for American English and the BREF corpus for French, these tasks remain relatively artificial. In this paper we report on our development work in moving from laboratory read speech data to real-world speech data in order to build a system for the new ARPA broadcast news transcription task. The LIMSI Nov96 speech recognizer makes use of continuous density HMMs with Gaussian mixtures for acoustic modeling and n-gram statistics estimated on newspaper texts. The acoustic models are trained on the WSJO/WSJ1, and adapted using MAP estimation with task-specific training data. The overall word error on the Nov96 partitioned evaluation test was 27.1%

Keywords

Gaussian processes; hidden Markov models; maximum likelihood estimation; radio broadcasting; speech recognition; television broadcasting; ARPA broadcast news transcription; Gaussian mixtures; LIMSI Nov96 speech recognizer; MAP estimation; Nov96 partitioned evaluation test; WSJO/WSJ1; acoustic modeling; broadcast news shows; continuous density HMMs; n-gram statistics; newspaper texts; real-world speech data; task-specific training data; word error; Broadcasting; Hidden Markov models; Laboratories; Loudspeakers; Speech enhancement; Speech recognition; Telephony; Text recognition; Training data; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1997. ICASSP-97., 1997 IEEE International Conference on

Conference_Location

Munich

ISSN

1520-6149

Print_ISBN

0-8186-7919-0

Type

conf

DOI

10.1109/ICASSP.1997.596002

Filename

596002