Incremental Language Modeling for Automatic Transcription of Broadcast News(Speech and Hearing)
スポンサーリンク
概要
- 論文の詳細を見る
In this paper, we address the task of incremental language modeling for automatic transcription of broadcast news speech. Daily broadcast news naturally contains new words that are not in the lexicon of the speech recognition system but are important for downstream applications such as information retrieval or machine translation. To recognize those new words, the lexicon and the language model of the speech recognition system need to be updated periodically. We propose a method of estimating a list of words to be added to the lexicon based on some time-series text data. The experimental results on the RT04 Broadcast News data and other TV audio data showed that this method provided an impressive and stable reduction in both out-of-vocabulary rates and speech recognition word error rates.
- 社団法人電子情報通信学会の論文
- 2007-02-01
著者
-
Nguyen Long
Bbn Technologies
-
OHTSUKI Katsutoshi
NTT Cyber Space Laboratories, NTT Corporation
-
Ohtsuki Katsutoshi
Ntt Cyber Space Laboratories Ntt Corporation
関連論文
- Incremental Language Modeling for Automatic Transcription of Broadcast News(Speech and Hearing)
- Topic Extraction Based on Continuous Speech Recognition in Broadcast News Speech