USING A* FOR THE PARALLELIZATION OF SPEECH RECOGNITION SYSTEMS

被引：0
作者：
Cardinal, Patrick [1 ]
Boulianne, Gilles [1 ]
Dumouchel, Pierre [1 ]
机构：
[1] Ctr Rech Informat Montreal, Montreal, PQ H3T 1P1, Canada
来源：
2012 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2012年
关键词：
Speech recognition; A*; parallelization;
D O I：
暂无
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
The speed of modern processors has remained constant over the last few years but the integration capacity continues to follow Moore's law and thus, to be scalable, applications must be parallelized. This paper presents results in using the A* search algorithm in a large vocabulary speech recognition parallel system. This algorithm allows better parallelization over the Viterbi algorithm. First experiments with a "unigram approximation" heuristic resulted in approximatively 8.7 times less states being explored compared to our classical Viterbi decoder. The multi-thread implementation of the A* decoder led to a speed-up factor of 3 over its sequential counterpart.
引用
收藏
页码：4433 / 4436
页数：4
相关论文
共 50 条
  • [31] Using speech rhythm knowledge to improve dysarthric speech recognition
    Selouani, S. -A.
    Dahmani, H.
    Amami, R.
    Hamam, H.
    INTERNATIONAL JOURNAL OF SPEECH TECHNOLOGY, 2012, 15 (01) : 57 - 64
  • [32] IMPROVING SPEECH RECOGNITION USING CONSISTENT PREDICTIONS ON SYNTHESIZED SPEECH
    Wang, Gary
    Rosenberg, Andrew
    Chen, Zhehuai
    Zhang, Yu
    Ramabhadran, Bhuvana
    Wu, Yonghui
    Moreno, Pedro
    2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 7029 - 7033
  • [33] Collecting Data for Automatic Speech Recognition Systems in Dialectal Arabic Using Games with a Purpose
    El-Sakhawy, Dayna
    Abdennadher, Slim
    Hamed, Injy
    MULTIMODAL ANALYSES ENABLING ARTIFICIAL AGENTS IN HUMAN-MACHINE INTERACTION, 2015, 8757 : 99 - 108
  • [34] Using speech rhythm knowledge to improve dysarthric speech recognition
    S.-A. Selouani
    H. Dahmani
    R. Amami
    H. Hamam
    International Journal of Speech Technology, 2012, 15 (1) : 57 - 64
  • [35] An Emotion Estimation from Human Speech Using Speech Recognition and Speech Synthesize
    Kurematsu, Masaki
    Ohashi, Marina
    Kinosita, Orimi
    Hakura, Jun
    Fujita, Hamido
    NEW TRENDS IN SOFTWARE METHODOLOGIES, TOOLS AND TECHNIQUES, 2008, 182 : 278 - 289
  • [36] Qur'an Recognition For The Purpose Of Memorisation Using Speech Recognition Technique
    Abro, Bushra
    Naqvi, Asma Batool
    Hussain, Ayyaz
    2012 15TH INTERNATIONAL MULTITOPIC CONFERENCE (INMIC), 2012, : 28 - 32
  • [37] Automatic Speech Recognition Used for Intelligibility Assessment of Text-to-Speech Systems
    Vich, Robert
    Nouza, Jan
    Vondra, Martin
    VERBAL AND NONVERBAL FEATURES OF HUMAN-HUMAN AND HUMAN-MACHINE INTERACTIONS, 2008, 5042 : 136 - +
  • [38] DROPOUT APPROACHES FOR LSTM BASED SPEECH RECOGNITION SYSTEMS
    Billa, Jayadev
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 5879 - 5883
  • [39] Development of Speech Recognition Systems in Emergency Call Centers
    Valizada, Alakbar
    Akhundova, Natavan
    Rustamov, Samir
    SYMMETRY-BASEL, 2021, 13 (04):
  • [40] The pros and cons of implementing PACS and speech recognition systems
    David B. Hayt
    Steven Alexander
    Journal of Digital Imaging, 2001, 14 : 149 - 157
12345