SOURCE-EXTENDED LANGUAGE MODEL FOR LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION

Tetsunori Kobayashi, Yosuke Wada, Norihiko Kobayashi

Research output: Contribution to conferencePaperpeer-review

2 Citations (Scopus)

Abstract

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%.

Original languageEnglish
Publication statusPublished - 1998
Event5th International Conference on Spoken Language Processing, ICSLP 1998 - Sydney, Australia
Duration: 1998 Nov 301998 Dec 4

Conference

Conference5th International Conference on Spoken Language Processing, ICSLP 1998
Country/TerritoryAustralia
CitySydney
Period98/11/3098/12/4

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'SOURCE-EXTENDED LANGUAGE MODEL FOR LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION'. Together they form a unique fingerprint.

Cite this