A wave decoder for continuous speech recognition

被引:0
|
作者
Burhke, E
Chou, W
Zhou, QR
机构
来源
ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4 | 1996年
关键词
D O I
暂无
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
In this paper, a wave decoder based on the general re-entrant network for continuous speech recognition is described. The decoder design is based on the concept of self-adjusting decoding graph in which the decoding network is expanded and released frame-synchronously. The fast network expansion and release are made possible by utilizing a novel dynamic network scaffolding layer. The self-adjusting decoding graph is obtained by slicing the traditional decoding network horizontally for separation of different knowledge sources and vertically according to each time instant in search. A two layer hashing structure and an admissible are predication scheme are described. These methods significantly reduce the are mortality rate, a problem which plagues the efficiency of the dynamic decoder. Experimental results demonstrate that an order of magnitude reduction of decoding resources can be achieved based on the proposed approach.
引用
收藏
页码:2135 / 2138
页数:4
相关论文
共 50 条
  • [31] Segmental search for continuous speech recognition
    Laface, P
    Fissore, L
    Maro, A
    Ravera, F
    ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, 1996, : 2155 - 2158
  • [32] COMPUTER RECOGNITION OF VOWELS IN CONTINUOUS SPEECH
    PALIWAL, KK
    RAO, PVS
    INDIAN JOURNAL OF TECHNOLOGY, 1980, 18 (07): : 285 - 289
  • [33] Constraints on the recognition of words in continuous speech
    McQueen, JM
    INTERNATIONAL JOURNAL OF PSYCHOLOGY, 2000, 35 (3-4) : 39 - 39
  • [34] PRACTICAL AND CONTINUOUS SPEECH RECOGNITION.
    Ross, Steve
    MacAllister, Jeff
    Electronic Systems Technology and Design/Computer Design's, 1984, 23 (07): : 69 - 70
  • [35] CONTINUOUS SPEECH RECOGNITION FOR RADIOLOGY REPORTING
    SCHWARTZ, LH
    KIJEWSKI, PK
    ROOSSIN, PS
    HEELAN, RT
    CASTELLINO, RA
    RADIOLOGY, 1995, 197 : 533 - 533
  • [36] Signal enhancement for continuous speech recognition
    Athanaselis, T
    Fotinea, SE
    Bakamidis, S
    Dologlou, I
    Giannopoulos, G
    ARTIFICAIL NEURAL NETWORKS AND NEURAL INFORMATION PROCESSING - ICAN/ICONIP 2003, 2003, 2714 : 1117 - 1124
  • [37] 'Early recognition' of words in continuous speech
    Scharenborg, O
    ten Bosch, L
    Boves, L
    ASRU'03: 2003 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING ASRU '03, 2003, : 61 - 66
  • [38] Continuous speech recognition in radiology reporting
    Aggarwal, V
    Rudrapatna, V
    Rajappan, S
    Raval, B
    Tonnesen, AS
    Zhang, JJ
    JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION, 2000, : 946 - 946
  • [39] Continuous speech recognition with sparse coding
    Smit, W. J.
    Barnard, E.
    COMPUTER SPEECH AND LANGUAGE, 2009, 23 (02): : 200 - 219
  • [40] Continuous Chinese speech recognition and understanding
    Gu, JH
    Liu, JM
    Shen, XQ
    ICICS - PROCEEDINGS OF 1997 INTERNATIONAL CONFERENCE ON INFORMATION, COMMUNICATIONS AND SIGNAL PROCESSING, VOLS 1-3: THEME: TRENDS IN INFORMATION SYSTEMS ENGINEERING AND WIRELESS MULTIMEDIA COMMUNICATIONS, 1997, : 989 - 992