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
  • [41] Methods for applying VAD in Kazakh speech recognition systems
    Kalimoldayev M.N.
    Alimhan K.
    Mamyrbayev O.J.
    International Journal of Speech Technology, 2014, 17 (2) : 199 - 204
  • [42] Automatic generation of subword units for speech recognition systems
    Singh, R
    Raj, B
    Stern, RM
    IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2002, 10 (02): : 89 - 99
  • [43] Boosting systems for large vocabulary continuous speech recognition
    Saon, George
    Soltau, Hagen
    SPEECH COMMUNICATION, 2012, 54 (02) : 212 - 218
  • [44] Summarization of Spontaneous Speech using Automatic Speech Recognition and a Speech Prosody based Tokenizer
    Szaszak, Gyorgy
    Tundik, Mate Akos
    Beke, Andras
    KDIR: PROCEEDINGS OF THE 8TH INTERNATIONAL JOINT CONFERENCE ON KNOWLEDGE DISCOVERY, KNOWLEDGE ENGINEERING AND KNOWLEDGE MANAGEMENT - VOL. 1, 2016, : 221 - 227
  • [45] The CUHK Dysarthric Speech Recognition Systems for English and Cantonese
    Hu, Shoukang
    Liu, Shansong
    Chang, Heng Fai
    Geng, Mengzhe
    Chen, Jiani
    Chung, Lau Wing
    Hei, To Ka
    Yu, Jianwei
    Wong, Ka Ho
    Liu, Xunying
    Meng, Helen
    INTERSPEECH 2019, 2019, : 3669 - 3670
  • [46] Speech Recognition and Listening Effort of Meaningful Sentences Using Synthetic Speech
    Ibelings, Saskia
    Brand, Thomas
    Holube, Inga
    TRENDS IN HEARING, 2022, 26
  • [47] Toward enhanced Arabic speech recognition using part of speech tagging
    AbuZeina, Dia
    Al-Khatib, Wasfi
    Elshafei, Moustafa
    Al-Muhtaseb, Husni
    INTERNATIONAL JOURNAL OF SPEECH TECHNOLOGY, 2011, 14 (04) : 419 - 426
  • [48] A Method of Speech Coding for Speech Recognition Using a Convolutional Neural Network
    Kubanek, Mariusz
    Bobulski, Janusz
    Kulawik, Joanna
    SYMMETRY-BASEL, 2019, 11 (09): : 1 - 12
  • [49] SPEECH ENHANCEMENT USING END-TO-END SPEECH RECOGNITION OBJECTIVES
    Subramanian, Aswin Shanmugam
    Wang, Xiaofei
    Baskar, Murali Karthick
    Watanabe, Shinji
    Taniguchi, Toru
    Tran, Dung
    Fujita, Yuya
    2019 IEEE WORKSHOP ON APPLICATIONS OF SIGNAL PROCESSING TO AUDIO AND ACOUSTICS (WASPAA), 2019, : 234 - 238
  • [50] Landmark Mining on a Smartwatch Using Speech Recognition
    Helgath, Jana
    Provinsky, Simon
    Schaschek, Timo
    PROCEEDINGS OF THE 14TH INTERNATIONAL CONFERENCE ON MOBILE AND UBIQUITOUS MULTIMEDIA (MUM 2015), 2015, : 379 - 383
12345