Speaker Adaptation Based on PARAFAC2 of Transformation Matrices for Continuous Speech Recognition

被引：0
|
作者：
Jeong, Yongwon [1 ]
Lim, Sangjun [1 ]
Kim, Young Kuk [2 ]
Kim, Hyung Soon [1 ]
机构：
[1] Pusan Natl Univ, Sch Elect Engn, Pusan 609735, South Korea
[2] AirPlug, CTO Grp, Seoul 135920, South Korea
来源：
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS | 2013年 / E96D卷 / 09期
关键词：
maximum likelihood linear regression; parallel factor analysis; PARAFAC2; speaker adaptation; speech recognition; HIDDEN MARKOV-MODELS; MAXIMUM-LIKELIHOOD; ALGORITHM;
D O I：
10.1587/transinf.E96.D.2152
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
We present an acoustic model adaptation method where the transformation matrix for a new speaker is given by the product of bases and a weight matrix. The bases are built from the parallel factor analysis 2 (PARAFAC2) of training speakers' transformation matrices. We perform continuous speech recognition experiments using the WSJ0 corpus.
引用
收藏
页码：2152 / 2155
页数：4
相关论文
共 50 条
  • [1] Rapid speaker adaptation for continuous speech recognition
    Lu, Ping
    Wu, Ji
    Wang, Zuoying
    Lu, Dajin
    Qinghua Daxue Xuebao/Journal of Tsinghua University, 2002, 42 (07): : 977 - 980
  • [2] Speaker clustering and transformation for speaker adaptation in speech recognition systems
    Padmanabhan, M
    Bahl, LR
    Nahamoo, D
    Picheny, MA
    IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1998, 6 (01): : 71 - 77
  • [3] A speaker clustering algorithm for fast speaker adaptation in continuous speech recognition
    Rodríguez, LJ
    Torres, MI
    TEXT, SPEECH AND DIALOGUE, PROCEEDINGS, 2004, 3206 : 433 - 440
  • [4] Speaker adaptation by modeling the speaker variation in a continuous speech recognition system
    Strom, N
    ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, 1996, : 989 - 992
  • [5] Speech Recognition Using Speaker Adaptation by System Parameter Transformation
    Hao, Ying
    Fang, Ditang
    IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1994, 2 (01): : 63 - 68
  • [6] Discriminative speaker adaptation in Persian continuous speech recognition systems
    Pirhosseinloo, Shadi
    Ganj, Farshad Almas
    4TH INTERNATIONAL CONFERENCE OF COGNITIVE SCIENCE, 2012, 32 : 296 - 301
  • [7] Continuous speech recognition using an on-line speaker adaptation method based on automatic speaker clustering
    Zhang, W
    Nakagawa, S
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2003, E86D (03) : 464 - 473
  • [8] Speaker clustering and transformation for speaker adaptation in large-vocabulary speech recognition systems
    Padmanabhan, M
    Bahl, LR
    Nahamoo, D
    Picheny, MA
    1996 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, CONFERENCE PROCEEDINGS, VOLS 1-6, 1996, : 701 - 704
  • [9] An Acoustic-Phonetic-Based Speaker Adaptation Technique for Improving Speaker-Independent Continuous Speech Recognition
    Zhao, Yunxin
    IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1994, 2 (03): : 380 - 394
  • [10] Speaker adaptation in the philips system for large vocabulary continuous speech recognition
    Thelen, E
    Aubert, X
    Beyerlein, P
    1997 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I - V: VOL I: PLENARY, EXPERT SUMMARIES, SPECIAL, AUDIO, UNDERWATER ACOUSTICS, VLSI; VOL II: SPEECH PROCESSING; VOL III: SPEECH PROCESSING, DIGITAL SIGNAL PROCESSING; VOL IV: MULTIDIMENSIONAL SIGNAL PROCESSING, NEURAL NETWORKS - VOL V: STATISTICAL SIGNAL AND ARRAY PROCESSING, APPLICATIONS, 1997, : 1035 - 1038
12345