RESTRICTED BOLTZMANN MACHINE SUPERVECTORS FOR SPEAKER RECOGNITION

被引：0
|
作者：
Ghahabi, Omid [1 ]
Hernando, Javier [1 ]
机构：
[1] Univ Politecn Cataluna, BarcelonaTech, TALP Res Ctr, Dept Signal Theory & Commun, Barcelona, Spain
来源：
2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP) | 2015年
关键词：
Speaker Recognition; Supervector; Restricted Boltzmann Machine;
D O I：
暂无
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
The use of Restricted Boltzmann Machines (RBM) is proposed in this paper as a non-linear transformation of GMM supervectors for speaker recognition. It will be shown that the RBM transformation will increase the discrimination power of raw GMM supervectors for speaker recognition. The experimental results on the core test condition of the NIST SRE 2006 corpus show that the proposed RBM supervectors will achieve a comparable performance to i-vectors. Furthermore, the combination of RBM supevectors and i-vectors in the score level improves the performance of the i-vector approach by more than 10% in terms of EER.
引用
收藏
页码：4804 / 4808
页数：5
相关论文
共 50 条
  • [1] Restricted Boltzmann machines for vector representation of speech in speaker recognition
    Ghahabi, Omid
    Hernando, Javier
    COMPUTER SPEECH AND LANGUAGE, 2018, 47 : 16 - 29
  • [2] Speaker Dependent Emotion Recognition Using Prosodic Supervectors
    Lopez-Moreno, Ignacio
    Ortego-Resa, Carlos
    Gonzalez-Rodriguez, Joaquin
    Ramos, Daniel
    INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, 2009, : 1939 - 1942
  • [3] Word-Conditioned HMM Supervectors for Speaker Recognition
    Lei, Howard
    Mirghafori, Nikki
    INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 425 - +
  • [4] GPU Accelerated GMM Supervectors for Speaker and Language Recognition
    Wang Fuqiu
    Zhang, Wei-Qiang
    Jia, Liu
    PROCEEDINGS OF 2012 IEEE 11TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING (ICSP) VOLS 1-3, 2012, : 536 - +
  • [5] Voice conversion using speaker-dependent conditional restricted Boltzmann machine
    Nakashika, Toru
    Takiguchi, Tetsuya
    Ariki, Yasuo
    EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING, 2015,
  • [6] Voice conversion using speaker-dependent conditional restricted Boltzmann machine
    Toru Nakashika
    Tetsuya Takiguchi
    Yasuo Ariki
    EURASIP Journal on Audio, Speech, and Music Processing, 2015
  • [7] Cooperative object segmentation and recognition via restricted Boltzmann machine
    Huang, Wei
    Yu, Huimin
    ELECTRONICS LETTERS, 2020, 56 (08) : 378 - 379
  • [8] Application of a New Restricted Boltzmann Machine to Radar Target Recognition
    Xia, J. Y.
    Li, X.
    Liu, Y. X.
    2016 PROGRESS IN ELECTROMAGNETICS RESEARCH SYMPOSIUM (PIERS), 2016, : 2195 - 2201
  • [9] An Efficient Iris Recognition Method Based on Restricted Boltzmann Machine
    Huo, Guang
    Liu, Yuanning
    Zhu, Xiaodong
    Wu, Jianfeng
    BIOMETRIC RECOGNITION, CCBR 2015, 2015, 9428 : 349 - 356
  • [10] Architecture and Implementation of a Restricted Boltzmann Machine for Handwritten Digits Recognition
    Toulgaridis, Nikolaos
    Bougioukou, Eleni
    Antonakopoulos, Theodore
    2017 6TH INTERNATIONAL CONFERENCE ON MODERN CIRCUITS AND SYSTEMS TECHNOLOGIES (MOCAST), 2017,
12345