N-best vector quantization for isolated word speech recognition

被引：0

作者：

Nose, Masaya ^{[1
]}

Maki, Shuichi ^{[1
]}

Yartiane, Noburnoto ^{[1
]}

Morikawa, Yoshitaka ^{[1
]}

机构：

[1] Okayama Univ, Grad Sch Nat Sci & Technol, Okayama, Japan

来源：

PROCEEDINGS OF SICE ANNUAL CONFERENCE, VOLS 1-8 | 2007年

关键词：

isolated word speech recognition; VQ; vector quantization; discrete HMM; acoustic model improvement; Baum-Welch algorithm; speaker-independent speech recognition;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Speech recognition is performed by utilizing acoustic and linguistic model. The contribution of this paper is improvement of acoustic model. Acoustic model is constructed by hidden Markov model (HMM). HMM has two representations, that are discrete HMM and continuous HMM. The former uses vector quantization (VQ), whereas the latter uses functions such as (mixture) Gaussian distribution. In Viterbi algorithm, VQ has advantage that it only operates by addition. However VQ also has a problem of distortion. This paper attempts to improve recognition precision in discrete HMM with modified VQ that gives multiple outputs for an input.

引用

页码：2053 / +

页数：2

共 50 条

[1] A word graph based N-Best search in continuous speech recognition
Tran, BH
Seide, F
Steinbiss, V
[J]. ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, 1996, : 2127 - 2130
[2] Dynamic segmental vector quantization in isolated-word speech recognition
Nhat, VDM
Lee, S
[J]. PROCEEDINGS OF THE FOURTH IEEE INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND INFORMATION TECHNOLOGY, 2004, : 204 - 208
[3] Improvement in N-best search for continuous speech recognition
Illina, I
Gong, YF
[J]. ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, 1996, : 2147 - 2150
[4] ISOLATED-WORD SPEECH RECOGNITION USING MULTISECTION VECTOR QUANTIZATION CODEBOOKS
BURTON, DK
SHORE, JE
BUCK, JT
[J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1985, 33 (04): : 837 - 849
[5] Results of the N-Best 2008 Dutch Speech Recognition Evaluation
van Leeuwen, David A.
Kessens, Judith
Sanders, Eric
van den Heuvel, Henk
[J]. INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, 2009, : 2531 - +
[6] Speaker-dependent Isolated-Word Speech Recognition System Based on Vector Quantization
Zhao, Yinyin
Zhu, Lei
[J]. 2017 INTERNATIONAL CONFERENCE ON COMPUTER NETWORK, ELECTRONIC AND AUTOMATION (ICCNEA), 2017, : 133 - 137
[7] The ESAT 2008 System for N-Best Dutch Speech Recognition Benchmark
Demuynck, Kris
Puurula, Antti
Van Compernolle, Dirk
Wambacq, Patrick
[J]. 2009 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION & UNDERSTANDING (ASRU 2009), 2009, : 339 - 344
[8] An N-Best Candidates-Based Discriminative Training for Speech Recognition Applications
Chen, Jung-Kuei
Soong, Frank K.
[J]. IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1994, 2 (01): : 206 - 216
[9] Automatic acoustic segmentation in N-best list rescoring for lecture speech recognition
Shen, Peng
Lu, Xugang
Kawai, Hisashi
[J]. 2016 10TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING (ISCSLP), 2016,
[10] Correcting, Rescoring and Matching: An N-best List Selection Framework for Speech Recognition
Kuo, Chin-Hung
Chen, Kuan-Yu
[J]. PROCEEDINGS OF 2022 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2022, : 729 - 734

← 1 2 3 4 5 →