Out-of-Vocabulary Rejection based on Selective Attention Model

被引：0
|
作者：
Ki-Young Park
Soo-Young Lee
机构：
[1] Korea Advanced Institute of Science and Technology,Brain Science Research Center; Department of Electrical Engineering
[2] Korea Advanced Institute of Science and Technology,Brain Science Research Center; Department of Electrical Engineering
来源：
Neural Processing Letters | 2000年 / 12卷
关键词：
error backpropagation; noisy speech; out-of-vocabulary rejection; robust speech recognition; selective attention;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Based on a psychological selective attention theory a new algorithm is developed to provide reliable out-of-vocabulary (OOV) rejection for speech recognition systems in noisy environments. The developed attention model is based on Broadbent's ‘early filtering’ theory, and the attention adaptation process utilizes a gradient-descent error minimization algorithm with error backpropagation rule. The developed model is applied to isolated-word recognition tasks, and much higher in-vocabulary recognition rates are achieved with the same out-of-vocabulary rejection rates.
引用
收藏
页码：41 / 48
页数：7
相关论文
共 50 条
  • [31] Class-Based N-Gram Language Model for New Words Using Out-of-Vocabulary to In-Vocabulary Similarity
    Naptali, Welly
    Tsuchiya, Masatoshi
    Nakagawa, Seiichi
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2012, E95D (09) : 2308 - 2317
  • [32] Handling Out-Of-Vocabulary Problem in Hangeul Word Embeddings
    Kwon, Ohjoon
    Kim, Dohyun
    Lee, Soo-Ryeon
    Choi, Junyoung
    Lee, SangKeun
    16TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (EACL 2021), 2021, : 3213 - 3221
  • [33] WASSUP? LOL : Characterizing Out-of-Vocabulary Words in Twitter
    Maity, Suman Kalyan
    Chaudhary, Anshit
    Kumar, Shraman
    Mukherjee, Animesh
    Sarda, Chaitanya
    Patil, Abhijeet
    Mondal, Akash
    PROCEEDINGS OF THE 19TH ACM CONFERENCE ON COMPUTER SUPPORTED COOPERATIVE WORK AND SOCIAL COMPUTING COMPANION, 2016, : 341 - 344
  • [34] Handling Out-of-Vocabulary Words in Lexicons to Polarity Classification
    Nascimento, Gabriel
    Duarte, Fellipe
    Guedes, Gustavo Paiva
    PROCEEDINGS OF THE 17TH BRAZILIAN SYMPOSIUM ON HUMAN FACTORS IN COMPUTING SYSTEMS (IHC 2018), 2015,
  • [35] PatchBERT: Just-in-Time, Out-of-Vocabulary Patching
    Moon, Sangwhan
    Okazaki, Naoaki
    PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP), 2020, : 7846 - 7852
  • [36] Out-Of-Vocabulary Words Recognition Based on Conditional Random Field in Electronic Commerce
    Yang, Yanfeng
    Yang, Yanqin
    Guan, Hu
    Xu, Wenchao
    NEURAL INFORMATION PROCESSING (ICONIP 2014), PT II, 2014, 8835 : 532 - 539
  • [37] Confidence measure based on forced-alignment for out-of-vocabulary term detection
    Han, J. (jqhan@hit.edu.com), 2013, Binary Information Press, P.O. Box 162, Bethel, CT 06801-0162, United States (09):
  • [38] Similarity Scoring for Recognizing Repeated Out-of-Vocabulary Words
    Hannemann, Mirko
    Kombrink, Stefan
    Karafiat, Martin
    Burget, Lukas
    11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 1-2, 2010, : 897 - 900
  • [39] Triplet Confidence for Robust Out-of-vocabulary Keyword Spotting
    Wang, Chengliang
    Hao, Yujie
    Wu, Xing
    Liao, Chao
    2022 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS 22), 2022, : 3130 - 3134
  • [40] Subword RNNLM Approximations for Out-Of-Vocabulary Keyword Search
    Singh, Mittul
    Virpioja, Sami
    Smit, Peter
    Kurimo, Mikko
    INTERSPEECH 2019, 2019, : 4235 - 4239
12345