Training a language model using webdata for large vocabulary Japanese spontaneous speech recognition

被引：0

作者：

Masumura, Ryo ^{[1
]}

Hahm, Seongjun ^{[1
]}

Ito, Akinori ^{[1
]}

机构：

[1] Tohoku Univ, Grad Sch Engn, Sendai, Miyagi 980, Japan

来源：

12TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2011 (INTERSPEECH 2011), VOLS 1-5 | 2011年

关键词：

Spontaneous speech recognition; language model; World Wide Web; large vocabulary continuous speech recognition; Corpus of Spontaneous Japanese;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper describes a language modeling method using large-scale spoken language data retrieved from the Web for spontaneous speech recognition. We downloaded 15 million Web pages on a comprehensive range topics. Next, spoken language-like texts were selected from the downloaded Web data using the naive Bayes classifier, and typical linguistic phenomena such as fillers and pauses were added using simulation models. A language model trained by the generated data gave as high performance as the large-scale spontaneous speech corpus (Corpus of Spontaneous Japanese, CSJ). By combining the generated data and CSJ, we improved word accuracy.

引用

页码：1476 / 1479

页数：4

共 50 条

[31] Recognition of target domain Japanese speech using language model replacement
Mori, Daiki
Ohta, Kengo
Nishimura, Ryota
Ogawa, Atsunori
Kitaoka, Norihide
EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING, 2024, 2024 (01):
[32] LARGE VOCABULARY SPEECH RECOGNITION USING SUBWORD UNITS
LEE, CH
GAUVAIN, JL
PIERACCINI, R
RABINER, LR
SPEECH COMMUNICATION, 1993, 13 (3-4) : 263 - 279
[33] Continuous Mandarin speech recognition for Chinese language with large vocabulary based on segmental probability model
Shen, JL
IEE PROCEEDINGS-VISION IMAGE AND SIGNAL PROCESSING, 1998, 145 (05): : 309 - 315
[34] End-to-End Large Vocabulary Speech Recognition for the Serbian Language
Popovic, Branislav
Pakoci, Edvin
Pekar, Darko
SPEECH AND COMPUTER, SPECOM 2017, 2017, 10458 : 343 - 352
[35] Discriminative training of decoding graphs for large vocabulary continuous speech recognition
Kuo, Hong-Kwang Jeff
Kingsbury, Brian
Zweig, Geoffrey
2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL IV, PTS 1-3, 2007, : 45 - +
[36] Improved discriminative training techniques for large vocabulary continuous speech recognition
Povey, D
Woodland, PC
2001 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-VI, PROCEEDINGS: VOL I: SPEECH PROCESSING 1; VOL II: SPEECH PROCESSING 2 IND TECHNOL TRACK DESIGN & IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS NEURALNETWORKS FOR SIGNAL PROCESSING; VOL III: IMAGE & MULTIDIMENSIONAL SIGNAL PROCESSING MULTIMEDIA SIGNAL PROCESSING, 2001, : 45 - 48
[37] Lattice-based discriminative training for large vocabulary speech recognition
Valtchev, V
Odell, JJ
Woodland, PC
Young, SJ
1996 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, CONFERENCE PROCEEDINGS, VOLS 1-6, 1996, : 605 - 608
[38] Unsupervised training of acoustic models for large vocabulary continuous speech recognition
Wessel, F
Ney, H
ASRU 2001: IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING, CONFERENCE PROCEEDINGS, 2001, : 307 - 310
[39] SPEECH RECOGNITION OF FOREIGN OUT-OF-VOCABULARY WORDS USING A HIERARCHICAL LANGUAGE MODEL
Yamamoto, Hirofumi
Kikui, Genichiro
Nakamura, Satoshi
Sagisaka, Yoshinori
INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, : 1870 - +
[40] Hybrid language models for out of vocabulary word detection in large vocabulary conversational speech recognition
Yazgan, A
Saraclar, M
2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS: SPEECH PROCESSING, 2004, : 745 - 748

← 1 2 3 4 5 →