Discriminative training for speaker identification

被引：1

作者：

Hong, QY ^{[1
]}

Kwong, S ^{[1
]}

机构：

[1] City Univ Hong Kong, Dept Comp Sci, Hong Kong, Hong Kong, Peoples R China

来源：

ELECTRONICS LETTERS | 2004年 / 40卷 / 04期

关键词：

D O I：

10.1049/el:20040149

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：

Maximum model distance training is applied to speaker identification and a new selection strategy of competitive speakers is proposed. It utilises the training data more efficiently than the maximum-likelihood method. Experimental results have demonstrated that a good identification performance can be obtained even when the training data is limited.

引用

页码：280 / 281

页数：2

共 50 条

[41] Constructing the discriminative kernels using GMM for text-independent speaker identification [J].

Lei, ZC ;

Yang, YC ;

Wu, ZH .

ADVANCES IN BIOMETRIC PERSON AUTHENTICATION, PROCEEDINGS, 2005, 3781 :165-171

[42] SPARSITY BASED ROBUST SPEAKER IDENTIFICATION USING A DISCRIMINATIVE DICTIONARY LEARNING APPROACH [J].

Tzagkarakis, Christos ;

Mouchtaris, Athanasios .

2013 PROCEEDINGS OF THE 21ST EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2013,

[43] Speaker modeling technique based on regression class for speaker identification with sparse training [J].

Fu, ZH ;

Zhao, RC .

ADVANCES IN BIOMETRIC PERSON AUTHENTICATION, PROCEEDINGS, 2004, 3338 :610-616

[44] Discriminative analysis of lip motion features for speaker identification and speech-reading [J].

Cetinguel, H. Ertan ;

Yemez, Yuecel ;

Erzin, Engin ;

Tekalp, A. Murat .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2006, 15 (10) :2879-2891

[45] Two discriminative training schemes of GMM for language identification [J].

Qu, D ;

Wang, BX ;

Zhang, Q .

2004 7TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS 1-3, 2004, :630-633

[46] Acoustic Language Identification Using Fast Discriminative Training [J].

Castaldo, Fabio ;

Colibro, Daniele ;

Dalmasso, Emanuele ;

Laface, Pietro ;

Vair, Claudio .

INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, :389-+

[47] Robust discriminative training against data insufficiency in PLDA-based speaker verification [J].

Rohdin, Johan ;

Biswas, Sangeeta ;

Shinoda, Koichi .

COMPUTER SPEECH AND LANGUAGE, 2016, 35 :32-57

[48] Fusion Multistyle Training for Speaker Identification of Disguised Speech [J].

Prasad, Swati ;

Prasad, Ramjee .

WIRELESS PERSONAL COMMUNICATIONS, 2019, 104 (03) :895-905

[49] Research of speaker identification based on little training data [J].

Yang, YQ ;

Chen, W ;

Lu, YD ;

Gao, AG .

PROCEEDINGS OF THE 2004 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, 2004, :3755-3758

[50] Fusion Multistyle Training for Speaker Identification of Disguised Speech [J].

Swati Prasad ;

Ramjee Prasad .

Wireless Personal Communications, 2019, 104 :895-905

← 1 2 3 4 5 →