Sparse coding over redundant dictionaries for fast adaptation of speech recognition system

详细信息    查看全文

• 作者：S. Shahnawazuddin ; ^{s.syed@iitg.ernet.in} ; Rohit Sinha ^{rsinha@iitg.ernet.in}
• 关键词：Fast adaptation ; Acoustic model interpolation ; Sparse coding ; Exemplar and learned speaker dictionary
• 刊名：Computer Speech & Language
• 出版年：2017
• 出版时间：May 2017
• 年：2017
• 卷：43
• 期：Complete
• 页码：1-17
• 全文大小：704 K
• 卷排序：43

文摘

A novel use of sparse coding is done for the on-line adaptation of HMM based ASR systems. The target is first sparse coded using OMP over exemplar/learned speaker dictionaries. Adapted model is obtained by the maximum likelihood scaling of the sparse coded target. Performance same as the existing techniques is obtained but with much lower complexity.