SOURCE-EXTENDED LANGUAGE MODEL FOR LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION

Tetsunori Kobayashi, Yosuke Wada, Norihiko Kobayashi

研究成果: Paper査読

2 被引用数 (Scopus)

抄録

Information source extension is utilized to improve the language model for large vocabulary continuous speech recognition (LVCSR). McMillan's theory, source extension make the model entropy close to the real source entropy, implies that the better language model can be obtained by source extension (making new unit through word concatenations and using the new unit for the language modeling). In this paper, we examined the effectiveness of this source extension. Here, we tested two methods of source extension: frequency-based extension and entropy-based extension. We tested the effect in terms of perplexity and recognition accuracy using Mainichi newspaper articles and IN AS speech corpus. As the results, the bi-gram perplexity is improved from 98.6 to 70.8 and tri-gram perplexity is improved from Jt1.9 to 26.4- The bigram-based recognition accuracy is improved from 79.8% to 85.3%.

本文言語English
出版ステータスPublished - 1998
イベント5th International Conference on Spoken Language Processing, ICSLP 1998 - Sydney, Australia
継続期間: 1998 11月 301998 12月 4

Conference

Conference5th International Conference on Spoken Language Processing, ICSLP 1998
国/地域Australia
CitySydney
Period98/11/3098/12/4

ASJC Scopus subject areas

  • 言語および言語学
  • 言語学および言語

フィンガープリント

「SOURCE-EXTENDED LANGUAGE MODEL FOR LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル