Efficient speech recognition using subvector quantization and discrete-mixture HMMs

被引：9

作者：

Tsakalidis, S ^{[1
]}

Digalakis, V ^{[1
]}

Neumeyer, L ^{[1
]}

机构：

[1] Tech Univ Crete, Dept Elect & Comp Engn, Hania 73100, Greece

来源：

ICASSP '99: 1999 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS VOLS I-VI | 1999年

关键词：

D O I：

10.1109/ICASSP.1999.759730

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

This paper introduces a new form of observation distributions for hidden Markov models (HMMs), combining subvector quantization and mixtures of discrete distributions. We present efficient training and decoding algorithms for the discrete-mixture HMMs (DMHMMs). Our experimental results in the air-travel information domain show that the high-level of recognition accuracy of continuous mixture-density HMMs (CDHMMs) can be maintained at significantly faster decoding speeds. Moreover, we show that when the same number of mixture components is used in DMHMMs and CDHMMs, the new models exhibit superior recognition performance.

引用

页码：569 / 572

页数：4

共 50 条

[31] The Efficient Discrete Tchebichef Transform for Spectrum Analysis of Speech Recognition
Ernawan, Ferda
Abu, Nur Azman
Suryana, Nanna
INTERNATIONAL CONFERENCE ON GRAPHIC AND IMAGE PROCESSING (ICGIP 2012), 2013, 8768
[32] Self Learning Speech Recognition Model Using Vector Quantization
Saleem, M.
Rehman, Zia Ur
Zahoor, Usama
Mazhar, Amna
Anjum, M. R.
2016 SIXTH INTERNATIONAL CONFERENCE ON INNOVATIVE COMPUTING TECHNOLOGY (INTECH), 2016, : 199 - 203
[33] Efficient Use of DNN Bottleneck Features in Generalized Variable Parameter HMMs for Noise Robust Speech Recognition
Su, Rongfeng
Xie, Xurong
Liu, Xunying
Wang, Lan
16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 2474 - 2478
[34] INTEGER-ONLY ZERO-SHOT QUANTIZATION FOR EFFICIENT SPEECH RECOGNITION
Kim, Sehoon
Gholami, Amir
Yao, Zhewei
Lee, Nicholas
Wang, Patrick
Nrusimha, Aniruddha
Zhai, Bohan
Gao, Tianren
Mahoney, Michael W.
Keutzer, Kurt
2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 4288 - 4292
[35] Efficient codebook for arabic speech using optimized vector quantization
UAE Univ
Adv Modell Anal A, 1 (41-51):
[36] Product HMMs for audio-visual continuous speech recognition using facial animation parameters
Aleksic, PS
Katsaggelos, AK
2003 INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, VOL II, PROCEEDINGS, 2003, : 481 - 484
[37] Eigenvalues Driven Gaussian Selection in continuous speech recognition using HMMs with full covariance matrices
Marko Janev
Darko Pekar
Niksa Jakovljevic
Vlado Delic
Applied Intelligence, 2010, 33 : 107 - 116
[38] Eigenvalues Driven Gaussian Selection in continuous speech recognition using HMMs with full covariance matrices
Janev, Marko
Pekar, Darko
Jakovljevic, Niksa
Delic, Vlado
APPLIED INTELLIGENCE, 2010, 33 (02) : 107 - 116
[39] Performance Analysis of Speech Digit Recognition using Cepstrum and Vector Quantization
Rudresh, M. D.
Latha, A. S.
Suganya, J.
Nayana, C. G.
2017 INTERNATIONAL CONFERENCE ON ELECTRICAL, ELECTRONICS, COMMUNICATION, COMPUTER, AND OPTIMIZATION TECHNIQUES (ICEECCOT), 2017, : 632 - 637
[40] Speech Enhancement for Automatic Speech Recognition Using Complex Gaussian Mixture Priors for Noise and Speech
Astudillo, Ramon F.
Hoffmann, Eugen
Mandelartz, Philipp
Orglmeister, Reinhold
ADVANCES IN NONLINEAR SPEECH PROCESSING, 2010, 5933 : 60 - 67

← 1 2 3 4 5 →