Domain compensation based on phonetically discriminative features for speaker verification
详细信息 查看全文
- 作者：Yanhua Long ; yanhua@shnu.edu.cn" class="auth_mail" title="E-mail the corresponding author ; Hong Ye ; Jifeng Ni
- 关键词：Discriminative features ; I-vector ; Domain compensation ; Deep neural network ; Speaker verification
- 刊名：Computer Speech & Language
- 出版年：2017
- 出版时间：January 2017
- 年：2017
- 卷：41
- 期：Complete
- 页码：161-179
- 全文大小：1491 K
文摘
- •
A new domain compensation framework is proposed for speaker verification.
- •
This framework can be applied in both unsupervised and supervised manner.
- •
Deep neural networks are used to generate domain dependent discriminative features.
- •
Domain mismatches are compensated in the vector-based speaker-modeling step.
- •
Performances on NIST SRE2010 task are competitive to the state-of-the-art techniques.