Noise-robust speech recognition by discriminative adaptation in parallel model combination

被引：1
|
作者：
Chung, YJ [1 ]
机构：
[1] Keimyung Univ, Fac Elect & Comp Engn, Daegu 704701, South Korea
来源：
ELECTRONICS LETTERS | 2000年 / 36卷 / 04期
关键词：
D O I：
10.1049/el:20000277
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
A discriminative adaptation method for parallel model combination (PMC) is proposed. For the adaptation, a modified version of PMC is adopted and the association factor defined in this variant is discriminatively adapted based on the generalised probabilistic descent (GPD) method. The proposed method is shown to be very effective at improving the recognition performances under extreme noise conditions with a small amount of adaptation data.
引用
收藏
页码：370 / 371
页数：2
相关论文
共 50 条
  • [1] APPROXIMATED PARALLEL MODEL COMBINATION FOR EFFICIENT NOISE-ROBUST SPEECH RECOGNITION
    Sim, Khe Chai
    [J]. 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 7383 - 7387
  • [2] An engineering model of the masking for the noise-robust speech recognition
    Park, KY
    Lee, SY
    [J]. NEUROCOMPUTING, 2003, 52-4 : 615 - 620
  • [3] INTEGRATED DNN-BASED MODEL ADAPTATION TECHNIQUE FOR NOISE-ROBUST SPEECH RECOGNITION
    Lee, Kang Hyun
    Kang, Woo Hyun
    Kang, Tae Gyoon
    Kim, Nam Soo
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, : 5245 - 5249
  • [4] Noise-robust automatic speech recognition using a discriminative echo state network
    Skowronski, Mark D.
    Harris, John G.
    [J]. 2007 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1-11, 2007, : 1771 - 1774
  • [5] Comparing Jacorian adaptation with cepstral mean normalization and parallel model combination for noise robust speech recognition
    Pärssinen, K
    Salmela, P
    Harju, M
    Kiss, I
    [J]. 2002 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-IV, PROCEEDINGS, 2002, : 193 - 196
  • [6] Noise Robust Speech Recognition Based on Parallel Model Combination Adaptation Using Frequency-Variant
    Choi, Sook-Nam
    Chung, Hyun-Yeol
    [J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF KOREA, 2013, 32 (03): : 252 - 261
  • [7] Noise-Robust speech recognition of Conversational Telephone Speech
    Chen, Gang
    Tolba, Hesham
    O'Shaughnessy, Douglas
    [J]. INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, : 1101 - 1104
  • [8] Model adaptation employing DNN-based estimation of noise corruption function for noise-robust speech recognition
    Yoon, Ki-mu
    Kim, Wooil
    [J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF KOREA, 2019, 38 (01): : 47 - 50
  • [9] A combination of discriminative and Maximum Likelihood techniques for noise robust speech recognition
    Laurila, K
    Vasilache, M
    Viikki, O
    [J]. PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-6, 1998, : 85 - 88
  • [10] An overview of noise-robust automatic speech recognition
    Li, Jinyu
    Deng, Li
    Gong, Yifan
    Haeb-Umbach, Reinhold
    [J]. IEEE Transactions on Audio, Speech and Language Processing, 2014, 22 (04): : 745 - 777
12345