Speeding up dynamic search methods in speech recognition

被引：0
|
作者：
Gosztolya, G [1 ]
Kocsor, A [1 ]
机构：
[1] MTA SZTE Res Grp Artificial Intelligence, H-6720 Szeged, Hungary
来源：
INNOVATIONS IN APPLIED ARTIFICIAL INTELLIGENCE | 2005年 / 3533卷
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In speech recognition huge hypothesis spaces are generated. To overcome this problem dynamic programming can be used. In this paper we examine ways of speeding up this search process even more using heuristic search methods, multi-pass search and aggregation operators. The tests showed that these techniques can be applied together, and their combination could significantly speed up the recognition process. The run-times we obtained were 22 times faster than the basic dynamic search method, and 8 times faster than the multi-stack decoding method.
引用
收藏
页码：98 / 100
页数：3
相关论文
共 50 条
  • [1] Dynamic Gaussian selection technique for speeding up HMM-based continuous speech recognition
    Cai, Jun
    Bouselmi, Ghazi
    Fohr, Dominique
    Laprie, Yves
    2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12, 2008, : 4461 - 4464
  • [2] Speeding up neural network execution: An application to speech recognition
    Albesano, D
    Mana, F
    Gemello, R
    NEURAL NETWORKS FOR SIGNAL PROCESSING VI, 1996, : 579 - 588
  • [3] TRAINING AND SEARCH METHODS FOR SPEECH RECOGNITION
    JELINEK, F
    PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 1995, 92 (22) : 9964 - 9969
  • [4] Dynamic programming search for continuous speech recognition
    Ney, H
    Ortmanns, S
    IEEE SIGNAL PROCESSING MAGAZINE, 1999, 16 (05) : 64 - 83
  • [5] Speeding up the search for optimal partitions
    Elomaa, T
    Rousu, J
    PRINCIPLES OF DATA MINING AND KNOWLEDGE DISCOVERY, 1999, 1704 : 89 - 97
  • [6] Speeding up Similarity Search by Sketches
    Mic, Vladimir
    Novak, David
    Zezula, Pavel
    SIMILARITY SEARCH AND APPLICATIONS, SISAP 2016, 2016, 9939 : 250 - 258
  • [7] Speeding up Common Hyperparameter Optimization Methods by a Two-Phase-Search
    Wendt, Alexander
    Wuschnig, Marco
    Lechner, Martin
    IECON 2020: THE 46TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, 2020, : 517 - 522
  • [8] Speeding up Deep Neural Networks for Speech Recognition on ARM Cortex-A Series Processors
    Xing, Anhao
    Jin, Xin
    Li, Ta
    Wang, Xuyang
    Pan, Jielin
    Yan, Yonghong
    2014 10TH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION (ICNC), 2014, : 123 - 127
  • [9] Various robust search methods in a Hungarian speech recognition system
    Gosztolya, Gábor
    Kocsor, András
    Tóth, László
    Felföldi, László
    Acta Cybernetica, 2003, 16 (02): : 229 - 240
  • [10] Speeding up similarity search under dynamic time warping by pruning unpromising alignments
    Silva, Diego F.
    Giusti, Rafael
    Keogh, Eamonn
    Batista, Gustavo E. A. P. A.
    DATA MINING AND KNOWLEDGE DISCOVERY, 2018, 32 (04) : 988 - 1016
12345