Speaker Adaptation in Sparse Subspace of Acoustic Models

被引：0

作者：

Jeong, Yongwon ^{[1
]}

机构：

[1] Pusan Natl Univ, Sch Elect Engn, Pusan 609735, South Korea

来源：

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS | 2013年 / E96D卷 / 06期

关键词：

eigenvoice speaker adaptation; robust speech recognition; sparse principal component analysis; speaker adaptation; speech recognition; RECOGNITION;

D O I：

10.1587/transinf.E96.D.1402

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

I propose an acoustic model adaptation method using bases constructed through the sparse principal component analysis (SPCA) of acoustic models trained in a clean environment. I perform experiments on adaptation to a new speaker and noise. The SPCA-based method outperforms the PCA-based method in the presence of babble noise.

引用

页码：1402 / 1405

页数：4

共 50 条

[1] TWO-STAGE SPEAKER ADAPTATION IN SUBSPACE GAUSSIAN MIXTURE MODELS
Ghalehjegh, Sina Hamidi
Rose, Richard C.
2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,
[2] An investigation into subspace rapid speaker adaptation
Zhang, M
Xu, J
2004 International Symposium on Chinese Spoken Language Processing, Proceedings, 2004, : 273 - 276
[3] Speaker Identification Based on Sparse Subspace Model
Xu, Longting
Yang, Zhen
2013 19TH ASIA-PACIFIC CONFERENCE ON COMMUNICATIONS (APCC): SMART COMMUNICATIONS TO ENHANCE THE QUALITY OF LIFE, 2013, : 37 - 41
[4] Batch Normalization based Unsupervised Speaker Adaptation for Acoustic Models
Yi, Jiangyan
Tao, Jianhua
2019 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2019, : 176 - 180
[5] Adaptation of Acoustic Models in Joint Speaker and Noise Space Using Bilinear Models
Jeong, Yongwon
Kim, Hyung Soon
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2014, E97D (08): : 2195 - 2199
[6] An investigation into subspace rapid speaker adaptation for verification
Lucey, S
Chen, TH
2003 INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, VOL I, PROCEEDINGS, 2003, : 69 - 72
[7] Speaker adaptation of acoustic models using correlations of training transfer vectors
Takahashi, Satoshi, 1600, (Scripta Technica Inc, New York, NY, United States):
[8] Subspace LHUC for Fast Adaptation of Deep Neural Network Acoustic Models
Samarakoon, Lahiru
Sim, Khe Chai
17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 2016, : 1593 - 1597
[9] UNSUPERVISED SPEAKER ADAPTATION OF BATCH NORMALIZED ACOUSTIC MODELS FOR ROBUST ASR
Wang, Zhong-Qiu
Wang, DeLiang
2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, : 4890 - 4894
[10] Total variability subspace adaptation based speaker recognition
Li, Zhi-Yi, 1836, Science Press (40):

← 1 2 3 4 5 →