Kernel-based speaker clustering for rapid speaker adaptation

被引：0

作者：

Hazrati, Dooz ^{[1
]}

Ahadi, S. M. ^{[1
]}

Sadjadi, Omid ^{[1
]}

机构：

[1] Tehran Polytech, EE Dept, Speech Proc Res Lab, Tehran, Iran

来源：

PROCEEDINGS OF THE FIFTH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY: NEW GENERATIONS | 2008年

关键词：

speaker adaptation; Kernel method; one-class SVM; speaker clustering;

D O I：

10.1109/ITNG.2008.176

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Speaker clustering is a widely used technique in speaker adaptation, especially since it can be easily combined with adaptation methods such as MAP or MLLR. In this paper we present and evaluate a new speaker adaptation method using a kernel-based speaker clustering algorithm inspired by the classical K-means and based on one-class support vector machines. We find that this adaptation method outperforms other conventional clustering techniques such as K-means and gender clustering with only small amounts of adaptation data (i.e. less than 10sec.).

引用

页码：1287 / 1289

页数：3

共 50 条

[1] GMM and kernel-based speaker recognition with the ISIP toolkit
Imbiriba, T
Klautau, A
Parihar, N
Raghavan, S
Picone, J
[J]. MACHINE LEARNING FOR SIGNAL PROCESSING XIV, 2004, : 371 - 380
[2] Kernel eigenvoice speaker adaptation
Mak, B
Kwok, JT
Ho, S
[J]. IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2005, 13 (05): : 984 - 992
[3] A novel method for rapid speaker adaptation based on support speaker weighting
Cai, T
Zhu, J
[J]. 2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING, 2005, : 993 - 996
[4] Speaker adaptation for telephony data using speaker clustering
Wu, C
Lubensky, D
Wang, ZH
[J]. 2000 5TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS I-III, 2000, : 768 - 771
[5] Speaker indexing and adaptation using speaker clustering based on statistical model selection
Nishida, M
Kawahara, T
[J]. 2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS: SPEECH PROCESSING, 2004, : 353 - 356
[6] SVM based speaker selection using GMM supervector for rapid speaker adaptation
Wang, Jian
Lei, Jianjun
Guo, Jun
Yang, Zhen
[J]. SIMULATED EVOLUTION AND LEARNING, PROCEEDINGS, 2006, 4247 : 617 - 624
[7] Speaker clustering and transformation for speaker adaptation in speech recognition systems
Padmanabhan, M
Bahl, LR
Nahamoo, D
Picheny, MA
[J]. IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1998, 6 (01): : 71 - 77
[8] UNSUPERVISED SPEAKER ADAPTATION BASED ON HIERARCHICAL SPECTRAL CLUSTERING
FURUI, S
[J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1989, 37 (12): : 1923 - 1930
[9] Addressing the Data-Imbalance Problem in Kernel-based Speaker Verification via Utterance Partitioning and Speaker Comparison
Rao, Wei
Mak, Man-Wai
[J]. 12TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2011 (INTERSPEECH 2011), VOLS 1-5, 2011, : 2728 - 2731
[10] Rapid Unsupervised Speaker Adaptation Using Single Utterance Based on MLLR and Speaker Selection
Gomez, Randy
Toda, Tomoki
Saruwatari, Hiroshi
Shikano, Kiyohiro
[J]. INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 1365 - 1368

← 1 2 3 4 5 →