The Cambridge University spoken document retrieval system

被引：22
|
作者：
Johnson, SE [1 ]
Jourlin, P [1 ]
Moore, GL [1 ]
Jones, KS [1 ]
Woodland, PC [1 ]
机构：
[1] Univ Cambridge, Dept Engn, Cambridge CB2 1PZ, England
来源：
ICASSP '99: 1999 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS VOLS I-VI | 1999年
关键词：
D O I：
10.1109/ICASSP.1999.758059
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
This paper describes the spoken document retrieval system that we have been developing and assesses its performance using automatic transcriptions of about 50 hours of broadcast news data. The recognition engine is based on the HTK broadcast news transcription system and the retrieval engine is based on the techniques developed at City University. The retrieval performance over a wide range of speech transcription error rates is presented and a number of recognition error metrics that more accurately reflect the impact of transcription errors on retrieval accuracy are defined and computed. The results demonstrate the importance of high accuracy automatic transcription. The final system is currently being evaluated on the 1998 TREC-7 spoken document retrieval task.
引用
收藏
页码：49 / 52
页数：4
相关论文
共 50 条
  • [11] Spoken document representations for probabilistic retrieval
    Jourlin, P
    Johnson, SE
    Sparck-Jones, K
    Woodland, PC
    SPEECH COMMUNICATION, 2000, 32 (1-2) : 21 - 36
  • [12] The THISL spoken document retrieval project
    Renals, S
    IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA COMPUTING AND SYSTEMS, PROCEEDINGS VOL 2, 1999, : 1049 - 1051
  • [13] Information fusion for spoken document retrieval
    Ng, K
    2000 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS, VOLS I-VI, 2000, : 2405 - 2408
  • [14] Probabilistic aspects in spoken document retrieval
    Macherey, W
    Viechtbauer, HJ
    Ney, H
    EURASIP JOURNAL ON APPLIED SIGNAL PROCESSING, 2003, 2003 (02) : 115 - 127
  • [15] New Approaches to Spoken Document Retrieval
    Martin Wechsler
    Eugen Munteanu
    Peter Schäuble
    Information Retrieval, 2000, 3 : 173 - 188
  • [16] Probabilistic Aspects in Spoken Document Retrieval
    Wolfgang Macherey
    Hans Jörg Viechtbauer
    Hermann Ney
    EURASIP Journal on Advances in Signal Processing, 2003
  • [17] Probabilistic aspects in spoken document retrieval
    Macherey, W. (w.macherey@informatik.rwth-aachen.de), 1600, Hindawi Publishing Corporation (2003):
  • [18] Phonetic recognition for spoken document retrieval
    Ng, K
    Zue, VW
    PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-6, 1998, : 325 - 328
  • [19] New approaches to spoken document retrieval
    Wechsler, M
    Munteanu, E
    Schäuble, P
    INFORMATION RETRIEVAL, 2000, 3 (03): : 173 - 188
  • [20] AVIR: a spoken document retrieval system in e-learning environment
    Gagliardi, Isabella
    Padula, Marco
    Pagliarulo, Patrizia
    Aliprandi, Bruno
    INTERNET IMAGING VII, 2006, 6061
12345