Differenced maximum mutual information criterion for robust unsupervised acoustic model adaptation
详细信息 查看全文
- 作者：Marc Delcroix ; marc.delcroix@lab.ntt.co.jp" class="auth_mail" title="E-mail the corresponding author ; Atsunori Ogawa ; Seong-Jun Hahm1 ; Tomohiro Nakatani ; Atsushi Nakamura2
- 关键词：Discriminative criterion ; Differenced maximum mutual information ; Speech recognition ; Acoustic model adaptation ; Unsupervised adaptation
- 刊名：Computer Speech & Language
- 出版年：2016
- 出版时间：March 2016
- 年：2016
- 卷：36
- 期：Complete
- 页码：24-41
- 全文大小：938 K
文摘
- •
The differenced-MMI (dMMI) is a discriminative criterion that generalizes MPE and BMMI.
- •
We discuss the behavior of dMMI when there are errors in the transcription labels.
- •
dMMI may be less sensitive to such errors than other criteria.
- •
We support our claim with unsupervised speaker adaptation experiments.
- •
dMMI based adaptation achieves significant gains over MLLR for 2 LVCSR tasks.