I-Vector Extraction Using Speaker Relevancy for Short Duration Speaker Recognition

被引：0
|
作者：
Kang, Woo Hyun
Cho, Won Ik
Jang, Se Young
Lee, Hyeon Seung
Kim, Nam Soo [1 ]
机构：
[1] Seoul Natl Univ, Dept Elect & Comp Engn, 1 Gwanak Ro, Seoul 08826, South Korea
来源：
IT CONVERGENCE AND SECURITY 2017, VOL 1 | 2018年 / 449卷
基金：
新加坡国家研究基金会;
关键词：
Speaker recognition; i-vector; DNN; NEURAL-NETWORKS;
D O I：
10.1007/978-981-10-6451-7_10
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
This paper presents a novel scheme for considering the frame-level speaker relevancy during i-vector extraction for speaker recognition. In the proposed system, the frame-level point-wise mutual information is utilized to directly modify the Baum-Welch statistics in order to extract a robust i-vector. Furthermore, a method for computing the frame-level speaker relevancy using deep neural network (DNN) analogous to the DNN used in robust automatic speech recognition (ASR) is proposed. The results show that the modified i-vectors obtained using the proposed methods outperformed the conventional i-vectors.
引用
收藏
页码：79 / 87
页数：9
相关论文
共 50 条
  • [1] i-vector Based Speaker Recognition on Short Utterances
    Kanagasundaram, Ahilan
    Vogt, Robbie
    Dean, David
    Sridharan, Sridha
    Mason, Michael
    [J]. 12TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2011 (INTERSPEECH 2011), VOLS 1-5, 2011, : 2352 - +
  • [2] Minimax i-vector extractor for short duration speaker verification
    Hautamaki, Ville
    Cheng, You-Chi
    Rajan, Padmanabhan
    Lee, Chin-Hui
    [J]. 14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5, 2013, : 3675 - 3679
  • [3] I-vector Extraction for Speaker Recognition Based on Dimensionality Reduction
    Ibrahim, Noor Salwani
    Ramli, Dzati Athiar
    [J]. KNOWLEDGE-BASED AND INTELLIGENT INFORMATION & ENGINEERING SYSTEMS (KES-2018), 2018, 126 : 1534 - 1540
  • [4] An Adaptive i-Vector Extraction for Speaker Verification with Short Utterance
    Poddar, Arnab
    Sahidullah, Md
    Saha, Goutam
    [J]. PATTERN RECOGNITION AND MACHINE INTELLIGENCE, PREMI 2017, 2017, 10597 : 326 - 332
  • [5] Nonparametrically trained PLDA for short duration i-vector speaker verification
    Khosravani, Abbas
    Homayounpour, Mohammad M.
    [J]. COMPUTER SPEECH AND LANGUAGE, 2018, 52 : 105 - 122
  • [6] DURATION MISMATCH COMPENSATION FOR I-VECTOR BASED SPEAKER RECOGNITION SYSTEMS
    Hasan, Taufiq
    Saeidi, Rahim
    Hansen, John H. L.
    van Leeuwen, David A.
    [J]. 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 7663 - 7667
  • [7] Simplification of I-Vector Extraction for Speaker Identification
    XU Longting
    YANG Zhen
    SUN Linhui
    [J]. Chinese Journal of Electronics, 2016, 25 (06) : 1121 - 1126
  • [8] Simplification of I-Vector Extraction for Speaker Identification
    Xu Longting
    Yang Zhen
    Sun Linhui
    [J]. CHINESE JOURNAL OF ELECTRONICS, 2016, 25 (06) : 1121 - 1126
  • [9] I-vector Based Speaker Gender Recognition
    Wang, Minghe
    Chen, Ying
    Tang, Zhenmin
    Zhang, Erhua
    [J]. 2015 IEEE ADVANCED INFORMATION TECHNOLOGY, ELECTRONIC AND AUTOMATION CONTROL CONFERENCE (IAEAC), 2015, : 729 - 732
  • [10] Improved i-vector extraction technique for speaker verification with short utterances
    Poddar A.
    Sahidullah M.
    Saha G.
    [J]. International Journal of Speech Technology, 2018, 21 (3) : 473 - 488
12345