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
收藏
页码：569 / 572
页数：4
相关论文
共 50 条
  • [41] Continuous Hindi Speech Recognition Using Gaussian Mixture HMM
    Kuamr, Ankit
    Dua, Mohit
    Choudhary, Tripti
    2014 IEEE STUDENTS' CONFERENCE ON ELECTRICAL, ELECTRONICS AND COMPUTER SCIENCE (SCEECS), 2014,
  • [42] Recognition of Emotions in German Speech Using Gaussian Mixture Models
    Vondra, Martin
    Vich, Robert
    MULTIMODAL SIGNAL: COGNITIVE AND ALGORITHMIC ISSUES, 2009, 5398 : 256 - 263
  • [43] Robust Speech Recognition over Mobile Networks Using Combined Weighted Viterbi Decoding and Subvector Based Error Concealment
    Tan, Zheng-Hua
    Dalsgaard, Paul
    Lindberg, Borge
    INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, : 1137 - 1140
  • [44] Stochastic modeling and quantization of harmonic phases in speech using wrapped gaussian mixture models
    Agiomyrgiannakis, Yannis
    Stylianou, Yannis
    2007 IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol IV, Pts 1-3, 2007, : 1121 - 1124
  • [45] ISOLATED-WORD SPEECH RECOGNITION USING MULTISECTION VECTOR QUANTIZATION CODEBOOKS
    BURTON, DK
    SHORE, JE
    BUCK, JT
    IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1985, 33 (04): : 837 - 849
  • [46] Noise Compensation for Speech Recognition Using Subspace Gaussian Mixture Models
    Bouallegue, Mohamed
    Rouvier, Mickael
    Matrouf, Driss
    Linares, Georges
    13TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2012 (INTERSPEECH 2012), VOLS 1-3, 2012, : 318 - 321
  • [47] Speech emotion recognition using Gaussian mixture vector autoregressive models
    El Ayadi, Moataz M. H.
    Kamel, Mohamed S.
    Karray, Fakhri
    2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL IV, PTS 1-3, 2007, : 957 - +
  • [48] i-vector Algorithm with Gaussian Mixture Model for Efficient Speech Emotion Recognition
    Gomes, Joan
    El-Sharkawy, Mohamed
    2015 INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND COMPUTATIONAL INTELLIGENCE (CSCI), 2015, : 476 - 480
  • [49] Robust speech recognition against misdetection using whole-word HMMs and relaxed algorithm for likelihood calculation
    Hayasaka, Noboru
    IEEJ Transactions on Electronics, Information and Systems, 2015, 135 (10) : 1236 - 1243
  • [50] On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training
    Zhang, Jisi
    Zorila, Catalin
    Doddipatla, Rama
    Barker, Jon
    INTERSPEECH 2022, 2022, : 1056 - 1060
12345