SOURCE-EXTENDED LANGUAGE MODEL FOR LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION

Tetsunori Kobayashi; Yosuke Wada; Norihiko Kobayashi

SOURCE-EXTENDED LANGUAGE MODEL FOR LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION

Tetsunori Kobayashi, Yosuke Wada, Norihiko Kobayashi

School of Fundamental Science and Engineering

Research output: Contribution to conference › Paper › peer-review

1 Citation (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 J_t1.9 to 26.4- The bigram-based recognition accuracy is improved from 79.8% to 85.3%.

Original language	English
Publication status	Published - 1998
Event	5th International Conference on Spoken Language Processing, ICSLP 1998 - Sydney, Australia Duration: 1998 Nov 30 → 1998 Dec 4

Conference

Conference	5th International Conference on Spoken Language Processing, ICSLP 1998
Country/Territory	Australia
City	Sydney
Period	98/11/30 → 98/12/4

ASJC Scopus subject areas

Language and Linguistics
Linguistics and Language

Cite this

@conference{e2fcda35d3524c4385649d96d48db265,

title = "SOURCE-EXTENDED LANGUAGE MODEL FOR LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION",

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%.",

author = "Tetsunori Kobayashi and Yosuke Wada and Norihiko Kobayashi",

note = "Funding Information: In this research, we used the corpus of 1994 Mainichi newspaper articles, and its differential corpus for morpheme analysis made by RWCP (RWC-DB-TEXT-95-1) and ASJ continuous speech corpus (JNAS). Publisher Copyright: {\textcopyright} 1998. 5th International Conference on Spoken Language Processing, ICSLP 1998. All rights reserved.; 5th International Conference on Spoken Language Processing, ICSLP 1998 ; Conference date: 30-11-1998 Through 04-12-1998",

year = "1998",

language = "English",

}

TY - CONF

T1 - SOURCE-EXTENDED LANGUAGE MODEL FOR LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION

AU - Kobayashi, Tetsunori

AU - Wada, Yosuke

AU - Kobayashi, Norihiko

N1 - Funding Information: In this research, we used the corpus of 1994 Mainichi newspaper articles, and its differential corpus for morpheme analysis made by RWCP (RWC-DB-TEXT-95-1) and ASJ continuous speech corpus (JNAS). Publisher Copyright: © 1998. 5th International Conference on Spoken Language Processing, ICSLP 1998. All rights reserved.

PY - 1998

Y1 - 1998

N2 - 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%.

AB - 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%.

UR - http://www.scopus.com/inward/record.url?scp=0005297498&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0005297498&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0005297498

T2 - 5th International Conference on Spoken Language Processing, ICSLP 1998

Y2 - 30 November 1998 through 4 December 1998

ER -

SOURCE-EXTENDED LANGUAGE MODEL FOR LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this