Distributed TDNN-Fuzzy Vector Quantization For HMM Speech Recognition

被引：1

作者：

Debyeche, Mohamed ^{[1
]}

Amrouche, Aderrahmane. ^{[1
]}

Haton, Jean Paul ^{[2
]}

机构：

[1] USTHB, Fac Elect & Comp, Algiers, Algeria

[2] CNRS, CRIN, INRIA Lorraine, Nancy, France

来源：

2009 INTERNATIONAL CONFERENCE ON MULTIMEDIA COMPUTING AND SYSTEMS (ICMCS 2009) | 2009年

关键词：

Speech recognition; Hidden Markov mode; TDNN; Vector quantization; Arabic language; MODELS;

D O I：

10.1109/MMCS.2009.5256727

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper investigates the use of a Time Delay Neural Network (TDNN) as fuzzy vector quantizer to improve the Distributed scheme of HMM speech recognition. We investigate how to optimize the use of the Vector Quantization (VQ) by combining complementary preprocessing techniques based on multi-streams acoustic analysis. Then, in order to eliminate the effect of quantization error incurred by the vector quantizer front-end process a Distributed TDNN Fuzzy Vector Quantizer (DTDNN-FVQ) scheme is proposed. The evaluation of the whole of these methods is performed by focusing on specific Arabic phonemes: emphatic and back consonants. Experimental results shows that the distributed approach proposed increases the global performance of the HMM speech recognition system.

引用

页码：72 / +

页数：2

共 50 条

[21] Design of a Quantization Algorithm of the Speech Feature Parameters for the Distributed Speech Recognition
Lee, Joonseok
Kang, Sangwon
Yoon, Byungsik
[J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF KOREA, 2005, 24 (04): : 217 - 223
[22] ROBUST ESTIMATION OF HMM PARAMETERS USING FUZZY VECTOR QUANTIZATION AND PARZENS WINDOW
DAI, JN
[J]. PATTERN RECOGNITION, 1995, 28 (01) : 53 - 57
[23] Hybrid NN/HMM acoustic modeling techniques for distributed speech recognition
Stadermann, Jan
Rigoll, Gerhard
[J]. SPEECH COMMUNICATION, 2006, 48 (08) : 1037 - 1046
[24] Self Learning Speech Recognition Model Using Vector Quantization
Saleem, M.
Rehman, Zia Ur
Zahoor, Usama
Mazhar, Amna
Anjum, M. R.
[J]. 2016 SIXTH INTERNATIONAL CONFERENCE ON INNOVATIVE COMPUTING TECHNOLOGY (INTECH), 2016, : 199 - 203
[25] MFCC and vector quantization for Arabic fricatives Speech/Speaker recognition
Chelali, Fatma Zohra
Djeradi, Amar
[J]. 2012 INTERNATIONAL CONFERENCE ON MULTIMEDIA COMPUTING AND SYSTEMS (ICMCS), 2012, : 284 - 289
[26] Robust recognition of cellular telephone speech by adaptive vector quantization
Sonmez, MK
Rajasekaran, R
Baras, JS
[J]. 1996 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, CONFERENCE PROCEEDINGS, VOLS 1-6, 1996, : 503 - 506
[27] Application of Vector Quantization in Emotion Recognition from Human Speech
Khanna, Preeti
Kumar, M. Sasi
[J]. INFORMATION INTELLIGENCE, SYSTEMS, TECHNOLOGY AND MANAGEMENT, 2011, 141 : 118 - +
[28] Histogram-based quantization for robust and/or distributed speech recognition
Wan, Chia-Yu
Lee, Lin-Shan
[J]. IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2008, 16 (04): : 859 - 873
[29] Context-dependent quantization for distributed and/or robust speech recognition
Wan, Chia-Yu
Chen, Yi
Lee, Lin-Shan
[J]. 2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12, 2008, : 4413 - 4416
[30] Deformable TDNN with adaptive receptive fields for speech recognition
An, Keyu
Zhang, Yi
Ou, Zhijian
[J]. INTERSPEECH 2021, 2021, : 2067 - 2071

← 1 2 3 4 5 →