Development of a Vietnamese Large Vocabulary Continuous Speech Recognition System under Noisy Conditions

被引：4

作者：

Quoc Bao Nguyen ^{[1
]}

Van Tuan Mai ^{[1
]}

Quang Trung Le ^{[1
]}

Ba Quyen Dam ^{[1
]}

Van Hai Do ^{[2
,3
]}

机构：

[1] Viettel Grp, Cyberspace Ctr, Hanoi, Vietnam

[2] Thuyloi Univ, Hanoi, Vietnam

[3] Viettel Grp, Hanoi, Vietnam

来源：

PROCEEDINGS OF THE NINTH INTERNATIONAL SYMPOSIUM ON INFORMATION AND COMMUNICATION TECHNOLOGY (SOICT 2018) | 2018年

关键词：

Vietnamese speech recognition; speech corpus; noisy condition; model adaptation; system combination;

D O I：

10.1145/3287921.3287938

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

In this paper, we first present our effort to collect a 500-hour corpus for Vietnamese read speech. After that, various techniques such as data augmentation, recurrent neural network language model rescoring, language model adaptation, bottleneck feature, system combination are applied to build the speech recognition system. Our final system achieves a low word error rate at 6.9% on the noisy test set.

引用

页码：222 / 226

页数：5

共 50 条

[41] Large-Vocabulary Continuous Speech Recognition of Lhasa Tibetan
Li, Guanyu
Yu, Hongzhi
[J]. COMPUTER AND INFORMATION TECHNOLOGY, 2014, 519-520 : 802 - 806
[42] An overview of decoding techniques for large vocabulary continuous speech recognition
Aubert, XL
[J]. COMPUTER SPEECH AND LANGUAGE, 2002, 16 (01): : 89 - 114
[43] Connectionist language modeling for large vocabulary continuous speech recognition
Schwenk, H
Gauvain, JL
[J]. 2002 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-IV, PROCEEDINGS, 2002, : 765 - 768
[44] Speaker verification through large vocabulary continuous speech recognition
Newman, M
Gillick, L
Ito, Y
McAllaster, D
Peskin, B
[J]. ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, 1996, : 2419 - 2422
[45] Phone deactivation pruning in large vocabulary continuous speech recognition
Renals, S
[J]. IEEE SIGNAL PROCESSING LETTERS, 1996, 3 (01) : 4 - 6
[46] Speaker selection training for large vocabulary continuous speech recognition
Huang, C
Chen, T
Chang, E
[J]. 2002 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-IV, PROCEEDINGS, 2002, : 609 - 612
[47] A Detailed Survey on Large Vocabulary Continuous Speech Recognition Techniques
Vanajakshi, P.
Mathivanan, M.
[J]. 2017 INTERNATIONAL CONFERENCE ON COMPUTER COMMUNICATION AND INFORMATICS (ICCCI), 2017,
[48] Syllable-based large vocabulary continuous speech recognition
Ganapathiraju, A
Hamaker, J
Picone, J
Ordowski, M
Doddington, GR
[J]. IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2001, 9 (04): : 358 - 366
[49] IMPROVEMENTS ON BOTTLENECK FEATURE FOR LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION
Tuerxun, Maimaitiaili
Zhang, Shiliang
Bao, Yebo
Dai, Lirong
[J]. 2014 12TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING (ICSP), 2014, : 516 - 520
[50] Integrating Stress Information in Large Vocabulary Continuous Speech Recognition
Ludusan, Bogdan
Ziegler, Stefan
Gravier, Guillaume
[J]. 13TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2012 (INTERSPEECH 2012), VOLS 1-3, 2012, : 2641 - 2644

← 1 2 3 4 5 →