Maximum Likelihood Discriminant Feature for Text-Independent Speaker Verification

被引：0
|
作者：
Liu, Qingsong [1 ]
Dai, Beiqian [1 ]
机构：
[1] Univ Sci & Technol China, Dept Elect Sci & Technol, Hefei 230026, Peoples R China
来源：
PROCEEDINGS OF THE 2009 2ND INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, VOLS 1-9 | 2009年
关键词：
HLDA; Text Independent; Speaker Verification; RECOGNITION EVALUATION; SYSTEMS;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Feature extraction is an essential first step in speaker verification applications. In addition to static features extracted from each frame of speech data, it is beneficial to use dynamic features that use information from neighboring frames. In this paper a new feature estimation method based on maximum likelihood discriminant analysis is presented. We compare it to traditional MFCC features in a NIST 2006 SRE core task. Experiments show that the proposed scheme provides more discriminative feature vectors. The features obtained with the new estimation method show a 10% - 15% relative improvement in EER and MinDCF over traditional MFCC features.
引用
收藏
页码：3733 / 3736
页数：4
相关论文
共 50 条
  • [41] Mixup Learning Strategies for Text-independent Speaker Verification
    Zhu, Yingke
    Ko, Tom
    Mak, Brian
    INTERSPEECH 2019, 2019, : 4345 - 4349
  • [42] A CORRECTIVE LEARNING APPROACH FOR TEXT-INDEPENDENT SPEAKER VERIFICATION
    Wen, Yandong
    Zhou, Tianyan
    Singh, Rita
    Raj, Bhiksha
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 4894 - 4898
  • [43] Group-based speaker embeddings for text-independent speaker verification
    Jung, Youngmoon
    Eom, Youngsik
    Lee, Yeonghyeon
    Kim, Hoirin
    JOURNAL OF THE ACOUSTICAL SOCIETY OF KOREA, 2021, 40 (05): : 496 - 502
  • [44] Self-Attentive Speaker Embeddings for Text-Independent Speaker Verification
    Zhu, Yingke
    Ko, Tom
    Snyder, David
    Mak, Brian
    Povey, Daniel
    19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 3573 - 3577
  • [45] Speaker adaptive cohort selection for Tnorm in text-independent speaker verification
    Sturim, DE
    Reynolds, DA
    2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING, 2005, : 741 - 744
  • [46] Significance of Constraining Text in Limited Data Text-independent Speaker Verification
    Das, Rohan Kumar
    Jelil, Sarfaraz
    Prasanna, S. R. Mahadeva
    2016 INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING AND COMMUNICATIONS (SPCOM), 2016,
  • [47] Text-independent speaker identification utilizing likelihood normalization technique
    Toyohashi Univ of Technology, Toyohashi-shi, Japan
    IEICE Trans Inf Syst, 5 (585-593):
  • [48] Text-independent speaker identification utilizing likelihood normalization technique
    Markov, KP
    Nakagawa, S
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 1997, E80D (05) : 585 - 593
  • [49] GENERATIVE X-VECTORS FOR TEXT-INDEPENDENT SPEAKER VERIFICATION
    Xu, Longting
    Das, Rohan Kumar
    Yilmaz, Emre
    Yang, Jichen
    Li, Haizhou
    2018 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY (SLT 2018), 2018, : 1014 - 1020
  • [50] Discriminative transformation for sufficient adaptation in text-independent speaker verification
    Yang, Hao
    Dong, Yuan
    Zhao, Xianyu
    Zha, Jian
    Wang, Haila
    CHINESE SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, 2006, 4274 : 558 - +
12345