Speaker adaptation using probabilistic linear discriminant analysis for continuous speech recognition

被引：1
|
作者：
Jeong, Y. [1 ]
机构：
[1] Pusan Natl Univ, Sch Elect Engn, Pusan 609735, South Korea
来源：
ELECTRONICS LETTERS | 2013年 / 49卷 / 25期
关键词：
MAXIMUM-LIKELIHOOD;
D O I：
10.1049/el.2013.2223
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：
The application of probabilistic linear discriminant analysis (PLDA) to speaker adaptation for automatic speech recognition based on hidden Markov models is proposed. By expressing the set of acoustic models of each of the training speakers in a matrix and treating each column as a sample, the small sample problem that can be encountered in PLDA if only one sample is available for each training speaker is overcome. In the continuous speech recognition experiments, the performance of the PLDA based approach improves over the principal component analysis (PC) based approach and the two-dimensional PCA based approach for adaptation data longer than 12 s.
引用
收藏
页码：1641 / 1643
页数：2
相关论文
共 50 条
  • [1] Speaker Recognition Using Sparse Probabilistic Linear Discriminant Analysis
    Yang, Hai
    Xu, Yunfei
    Zhao, Qinwei
    Zhou, Ruohua
    Yan, Yonghong
    [J]. IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2013, E96A (10) : 1938 - 1945
  • [2] Speaker adaptation techniques for speech recognition using probabilistic models
    Shinoda, K
    [J]. ELECTRONICS AND COMMUNICATIONS IN JAPAN PART III-FUNDAMENTAL ELECTRONIC SCIENCE, 2005, 88 (12): : 25 - 42
  • [3] TOWARDS NOISE-ROBUST SPEAKER RECOGNITION USING PROBABILISTIC LINEAR DISCRIMINANT ANALYSIS
    Lei, Yun
    Burget, Lukas
    Ferrer, Luciana
    Graciarena, Martin
    Scheffer, Nicolas
    [J]. 2012 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2012, : 4253 - 4256
  • [4] Probabilistic Linear Discriminant Analysis with Bottleneck Features for Speech Recognition
    Lu, Liang
    Renals, Steve
    [J]. 15TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2014), VOLS 1-4, 2014, : 910 - 914
  • [5] Probabilistic Linear Discriminant Analysis for Robust Speaker Identification in Co-channel Speech
    Shokouhi, Navid
    Hansen, John H. L.
    [J]. 16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 3016 - 3020
  • [6] Feature-space Speaker Adaptation for Probabilistic Linear Discriminant Analysis Acoustic Models
    Lu, Liang
    Renals, Steve
    [J]. 16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 2862 - 2866
  • [7] SPEAKER ADAPTATION IN SPEECH RECOGNITION USING LINEAR-REGRESSION TECHNIQUES
    COX, S
    [J]. ELECTRONICS LETTERS, 1992, 28 (22) : 2093 - 2094
  • [8] Sparse Probabilistic Linear Discriminant Analysis for Speaker Verification
    Yang, Hai
    Liang, Chunyan
    Xu, Yunfei
    Yang, Lin
    Yan, Yonghong
    [J]. 13TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2012 (INTERSPEECH 2012), VOLS 1-3, 2012, : 2657 - 2660
  • [9] Curriculum Learning based Probabilistic Linear Discriminant Analysis for Noise Robust Speaker Recognition
    Ranjan, Shivesh
    Misra, Abhinav
    Hansen, John H. L.
    [J]. 18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION, 2017, : 3717 - 3721
  • [10] A speaker clustering algorithm for fast speaker adaptation in continuous speech recognition
    Rodríguez, LJ
    Torres, MI
    [J]. TEXT, SPEECH AND DIALOGUE, PROCEEDINGS, 2004, 3206 : 433 - 440
12345