Parallel phoneme recognition algorithm based on continuous Hidden Markov Model

被引：0
|
作者：
Chung, Sang-Hwa [1 ]
Park, Min-Uk [1 ]
Kim, Hyung-Soon [1 ]
机构：
[1] Pusan Natl Univ, Pusan, Korea, Republic of
来源：
Proceedings of the International Parallel Processing Symposium, IPPS | 1999年
关键词：
Markov processes - MIM devices - Parallel algorithms - Probability - Real time systems - Speech recognition;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
This paper presents a parallel phoneme recognition algorithm based on the continuous Hidden Markov Model (HMM). The parallel phoneme recognition algorithm distributes 3-state HMMs of context dependent phonemes to the multiprocessors, computes output probabilities in parallel, and enhances the Viterbi beam search with a message passing mechanism. The algorithm is implemented in a multi-transputer system using distributed-memory MIMD multiprocessors. Experimental results show the feasibility of the parallel phoneme recognition algorithm in constructing a real-time parallel speech recognition system based on time-consuming continuous HMM.
引用
下载
收藏
页码：453 / 457
相关论文
共 50 条
  • [21] A PARALLEL IMPLEMENTATION OF A HIDDEN MARKOV MODEL WITH DURATION MODELING FOR SPEECH RECOGNITION
    MITCHELL, CD
    HARPER, MP
    JAMIESON, LH
    HELZERMAN, RA
    DIGITAL SIGNAL PROCESSING, 1995, 5 (01) : 43 - 57
  • [22] Fast Algorithm for Isolated Words Recognition Based on Hidden Markov Model Stationary Distribution
    Paramonov, Pavel
    2017 IEEE 4TH INTERNATIONAL CONFERENCE ON SOFT COMPUTING & MACHINE INTELLIGENCE (ISCMI), 2017, : 128 - 132
  • [23] A Study on Recognition Algorithm of Ultrasonic Sensing Gesture Based on Improved Hidden Markov Model
    Liu, Dianting
    Zhang, Chenguang
    Huang, Kangzheng
    Wu, Danling
    Zhao, Gege
    2020 CHINESE AUTOMATION CONGRESS (CAC 2020), 2020, : 2376 - 2380
  • [24] ENHANCED TIME DURATION CONSTRAINTS IN HIDDEN MARKOV MODELING FOR PHONEME RECOGNITION
    ARIKI, Y
    JACK, MA
    ELECTRONICS LETTERS, 1989, 25 (13) : 824 - 825
  • [25] Hidden Conditional Neural Fields for Continuous Phoneme Speech Recognition
    Fujii, Yasuhisa
    Yamamoto, Kazumasa
    Nakagawa, Seiichi
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2012, E95D (08): : 2094 - 2104
  • [26] Driver Intention Recognition Method Using Continuous Hidden Markov Model
    Hou, Haijing
    Jin, Lisheng
    Niu, Qingning
    Sun, Yuqin
    Lu, Meng
    INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS, 2011, 4 (03) : 386 - 393
  • [27] A Novel Character Recognition Algorithm Based on Hidden Markov Models
    Wang, Yu
    Wei, Xueye
    Han, Lei
    Wu, Xiaojin
    ARTIFICIAL INTELLIGENCE AND COMPUTATIONAL INTELLIGENCE, PROCEEDINGS, 2009, 5855 : 298 - 305
  • [28] Accelerating Speech Recognition Algorithm with Synergic Hidden Markov Model and Genetic Algorithm based on Cellular Automata
    Mosleh, Mohammad
    Setayeshi, Saeed
    Kheyrandish, Mohammad
    PROCEEDINGS OF THE 2009 INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING SYSTEMS, 2009, : 3 - +
  • [29] Tone recognition of Vietnamese continuous speech using hidden Markov model
    Quang, Nguyen Hong
    Pascal, Nocera
    Eric, Castelli
    Van Loan, Trinh
    2008 SECOND INTERNATIONAL CONFERENCE ON COMMUNICATIONS AND ELECTRONICS, 2008, : 233 - +
  • [30] Trajectory Recognition Based on Asynchronous Hidden Markov Model
    Qin, Peng
    Chen, Ying
    FOUNDATIONS OF INTELLIGENT SYSTEMS (ISKE 2013), 2014, 277 : 497 - 507
12345