A mismatch-aware stochastic matching algorithm for robust speech recognition

被引：0
|
作者：
Liao, YF [1 ]
Lin, JS [1 ]
Chen, JH [1 ]
机构：
[1] Natl Taipei Univ Technol, Dept Elect Engn, Taipei 106, Taiwan
来源：
2003 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL II, PROCEEDINGS: SPEECH II; INDUSTRY TECHNOLOGY TRACKS; DESIGN & IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS; NEURAL NETWORKS FOR SIGNAL PROCESSING | 2003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, we present a mismatch-aware stochastic matching (MASM) algorithm to alleviate the performance degradation under mismatched training and testing conditions. MASM first computes a reliability measure of applying a set of pre-trained speech models to a mismatch test utterance along the time axis or among different feature vector components. It then estimates and compensates the mismatch using the reliability measure to guide the speech segmentation. Experiments on a serious mismatched condition with training on PSTN-speech database and testing on mobile GSM-speech database showed that MASM outperformed the stochastic match (SM) method, especially, for short utterances.
引用
收藏
页码：101 / 104
页数：4
相关论文
共 50 条
  • [1] Stochastic Matching for Robust Speech Recognition
    Sankar, Ananth
    Lee, Chin-Hui
    IEEE SIGNAL PROCESSING LETTERS, 1994, 1 (08) : 124 - 125
  • [2] Hierarchical stochastic feature matching for robust speech recognition
    Jiang, H
    Soong, F
    Lee, CH
    2001 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-VI, PROCEEDINGS: VOL I: SPEECH PROCESSING 1; VOL II: SPEECH PROCESSING 2 IND TECHNOL TRACK DESIGN & IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS NEURALNETWORKS FOR SIGNAL PROCESSING; VOL III: IMAGE & MULTIDIMENSIONAL SIGNAL PROCESSING MULTIMEDIA SIGNAL PROCESSING - VOL IV: SIGNAL PROCESSING FOR COMMUNICATIONS; VOL V: SIGNAL PROCESSING EDUCATION SENSOR ARRAY & MULTICHANNEL SIGNAL PROCESSING AUDIO & ELECTROACOUSTICS; VOL VI: SIGNAL PROCESSING THEORY & METHODS STUDENT FORUM, 2001, : 217 - 220
  • [3] Maximum-likelihood approach to stochastic matching for robust speech recognition
    Sankar, A
    Lee, CH
    IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1996, 4 (03): : 190 - 202
  • [4] An SNR-incremental stochastic matching algorithm for noisy speech recognition
    Huang, CS
    Wang, HC
    Lee, CH
    IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2001, 9 (08): : 866 - 873
  • [5] Mismatch-aware Placement of Device Arrays using Genetic Optimization
    Nashaat, Islam
    Mohammed, Inas
    Dessouky, Mohamed
    Said, Hazem
    15TH INTERNATIONAL CONFERENCE ON SYNTHESIS, MODELING, ANALYSIS AND SIMULATION METHODS AND APPLICATIONS TO CIRCUIT DESIGN (SMACD 2018), 2018, : 177 - 180
  • [6] Stochastic features for noise robust speech recognition
    Iwahashi, N
    Pao, H
    Honda, H
    Minamino, K
    Omote, M
    PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-6, 1998, : 633 - 636
  • [7] Distance-Aware DNNs for Robust Speech Recognition
    Miao, Yajie
    Metze, Florian
    16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 761 - 765
  • [8] NOISE AWARE MANIFOLD LEARNING FOR ROBUST SPEECH RECOGNITION
    Tomar, Vikrant Singh
    Rose, Richard C.
    2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 7087 - 7091
  • [9] Nonlinear statistical matching for subband robust speech recognition
    Dept. of Radio Engineering, Southeast University, Nanjing 210096, China
    Dianzi Yu Xinxi Xuebao, 2006, 3 (480-484):
  • [10] An approach to robust speaker recognition using stochastic matching
    Ma, JY
    Gao, W
    2000 5TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS I-III, 2000, : 803 - 806
12345