Analysis of I-vector Length Normalization in Speaker Recognition Systems

被引：0

作者：

Garcia-Romero, Daniel ^{[1
]}

Espy-Wilson, Carol Y. ^{[1
]}

机构：

[1] Univ Maryland, Dept Elect & Comp Engn, College Pk, MD 20742 USA

来源：

12TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2011 (INTERSPEECH 2011), VOLS 1-5 | 2011年

关键词：

speaker recognition; i-vectors; length normalization;

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：

We present a method to boost the performance of probabilistic generative models that work with i-vector representations. The proposed approach deals with the non-Gaussian behavior of i-vectors by performing a simple length normalization. This non-linear transformation allows the use of probabilistic models with Gaussian assumptions that yield equivalent performance to that of more complicated systems based on Heavy-Tailed assumptions. Significant performance improvements are demonstrated on the telephone portion of NIST SEE 2010.

引用

页码：256 / 259

页数：4

共 50 条

[21] Emotional Speaker Recognition Based on i-vector Space Model
Mansour, Asma
Chenchah, Farah
Lachiri, Zied
[J]. 2016 4TH INTERNATIONAL CONFERENCE ON CONTROL ENGINEERING & INFORMATION TECHNOLOGY (CEIT), 2016,
[22] I-Vector Extraction Using Speaker Relevancy for Short Duration Speaker Recognition
Kang, Woo Hyun
Cho, Won Ik
Jang, Se Young
Lee, Hyeon Seung
Kim, Nam Soo
[J]. IT CONVERGENCE AND SECURITY 2017, VOL 1, 2018, 449 : 79 - 87
[23] Tied Variational Autoencoder Backends for i-Vector Speaker Recognition
Villalba, Jesus
Brummer, Niko
Dehak, Najim
[J]. 18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION, 2017, : 1004 - 1008
[24] Discriminatively learned network for i-vector based speaker recognition
Yao, Shengyu
Zhou, Ruohua
Zhang, Pengyuan
Yan, Yonghong
[J]. ELECTRONICS LETTERS, 2018, 54 (22) : 1302 - 1303
[25] Clustering-Based I-Vector Formulation for Speaker Recognition
Lee, Hung-Shin
Tsao, Yu
Wang, Hsin-Min
Jeng, Shyh-Kang
[J]. 15TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2014), VOLS 1-4, 2014, : 1101 - 1105
[26] Factorization of Discriminatively Trained i-vector Extractor for Speaker Recognition
Novotny, Ondrej
Plchot, Oldrich
Glembek, Ondrej
Burget, Lukas
[J]. INTERSPEECH 2019, 2019, : 4330 - 4334
[27] SUPERVISED DOMAIN ADAPTATION FOR I-VECTOR BASED SPEAKER RECOGNITION
Garcia-Romero, Daniel
McCree, Alan
[J]. 2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,
[28] I-VECTOR KULLBACK-LEIBLER DIVISIVE NORMALIZATION FOR PLDA SPEAKER VERIFICATION
Pan, Yilin
Zheng, Tieran
Chen, Chen
[J]. 2017 IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (GLOBALSIP 2017), 2017, : 56 - 60
[29] FMLLR Speaker Normalization With i-Vector: In Pseudo-FMLLR and Distillation Framework
Joy, Neethu Mariam
Kothinti, Sandeep Reddy
Umesh, Srinivasan
[J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2018, 26 (04) : 797 - 805
[30] ENTROPY ANALYSIS OF I-VECTOR FEATURE SPACES IN DURATION-SENSITIVE SPEAKER RECOGNITION
Nautsch, Andreas
Rathgeb, Christian
Saeidi, Rahim
Busch, Christoph
[J]. 2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP), 2015, : 4674 - 4678

← 1 2 3 4 5 →