Unsupervised language model adaptation for broadcast news

Author

Chen, Lungzhou ; Gauvain, Jean-Luc ; Lamel, Lori ; Adda, Gilles

Author_Institution

Spoken Language Process. Group, LIMSI-CNRS, Orsay, France

Volume

1

fYear

2003

fDate

6-10 April 2003

Abstract

Unsupervised language model adaptation for speech recognition is challenging, particularly for complicated tasks such the transcription of broadcast news (BN) data. This paper presents an unsupervised adaptation method for language modeling based on information retrieval techniques. The method is designed for the broadcast news transcription task where the topics of the audio data cannot be predicted in advance. Experiments are carried out using the LIMSI American English BN transcription system and the NIST 1999 BN evaluation sets. The unsupervised adaptation method reduces the perplexity by 7% relative to the baseline LM and yields a 2% relative improvement for a 10xRT system.

Keywords

information retrieval; natural languages; speech recognition; LIMSI American English BN transcription system; broadcast news; information retrieval techniques; language modeling; perplexity; speech recognition; unsupervised language model adaptation; Adaptation model; Broadcasting; Data mining; Decoding; Design methodology; Natural languages; Speech recognition; TV; Text recognition; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on

ISSN

1520-6149

Print_ISBN

0-7803-7663-3

Type

conf

DOI

10.1109/ICASSP.2003.1198757

Filename

1198757