Use of acoustic prior information for confidence measure in ASR (automatic speech recognition) applications

被引：0
|
作者：
Mengusoglu, E [1 ]
Ris, C
机构：
[1] Hacettepe Univ, Dept Comp Engn, Ankara, Turkey
[2] Fac Polytech Mons, TCTS Lab, B-7000 Mons, Belgium
来源：
ACOUSTICS RESEARCH LETTERS ONLINE-ARLO | 2005年 / 6卷 / 02期
关键词：
D O I：
10.1121/1.1843171
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
In this paper, a new acoustic confidence measure of automatic speech recognition hypothesis is proposed and it is compared to approaches proposed in the literature. This approach takes into account prior information on the acoustic model performance specific to each phoneme. The new method is tested on two types of recognition errors: the out-of-vocabulary words and the errors due to additive noise. An efficient way to interpret the raw confidence measure as a correctness prior probability is also proposed in the paper. (C) 2005 Acoustical Society of America.
引用
收藏
页码：92 / 98
页数：7
相关论文
共 50 条
  • [1] Cross-language use of acoustic information for automatic speech recognition
    Nieuwoudt, C
    Botha, EC
    [J]. SPEECH COMMUNICATION, 2002, 38 (1-2) : 101 - 113
  • [2] Feature extraction for automatic speech recognition (ASR)
    Swartz, B
    Magotra, N
    [J]. THIRTIETH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS, VOLS 1 AND 2, 1997, : 748 - 751
  • [3] Automatic Vocabulary Adaptation Based on Semantic Similarity and Speech Recognition Confidence Measure
    Yamahata, Shoko
    Yamaguchi, Yoshikazu
    Ogawa, Atsunori
    Masataki, Hirokazu
    Yoshioka, Osamu
    Takahashi, Satoshi
    [J]. 13TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2012 (INTERSPEECH 2012), VOLS 1-3, 2012, : 2307 - 2310
  • [4] Utterance Confidence Measure for End-to-End Speech Recognition with Applications to Distributed Speech Recognition Scenarios
    Kumar, Ankur
    Singh, Sachin
    Gowda, Dhananjaya
    Garg, Abhinav
    Singh, Shatrughan
    Kim, Chanwoo
    [J]. INTERSPEECH 2020, 2020, : 4357 - 4361
  • [5] CONFIDENCE MEASURE FOR AUTOMATIC FACE RECOGNITION
    Lenc, Ladislav
    Kral, Pavel
    [J]. KDIR 2011: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND INFORMATION RETRIEVAL, 2011, : 365 - 368
  • [6] Adversarial Attacks on Automatic Speech Recognition (ASR): A Survey
    Bhanushali, Amisha Rajnikant
    Mun, Hyunjun
    Yun, Joobeom
    [J]. IEEE ACCESS, 2024, 12 : 88279 - 88302
  • [7] Automatic speech recognition (ASR) and its use as a tool for assessment or therapy of voice, speech, and language disorders
    Kitzing, Peter
    Maier, Andreas
    Ahlander, Viveka Lyberg
    [J]. LOGOPEDICS PHONIATRICS VOCOLOGY, 2009, 34 (02) : 91 - 96
  • [8] Use of automatic speech recognition: Current and potential applications
    Noyes, J
    Starr, A
    [J]. COMPUTING & CONTROL ENGINEERING JOURNAL, 1996, 7 (05): : 203 - 208
  • [9] UTTERANCE CLASSIFICATION CONFIDENCE IN AUTOMATIC SPEECH RECOGNITION
    KIMBALL, R
    ROTHKOPF, MH
    [J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1976, 24 (02): : 188 - 189
  • [10] Acoustic Analysis for Automatic Speech Recognition
    O'Shaughnessy, Douglas
    [J]. PROCEEDINGS OF THE IEEE, 2013, 101 (05) : 1038 - 1053
12345