Title
Acoustic Modeling With Bootstrap And Restructuring Based On Full Covariance
Abstract
Bootstrap and restructuring (BSRS) has been shown in our previous work to be superior over the conventional acoustic modeling approach when dealing with low-resourced languages. This paper presents a full covariance based BSRS scheme, which is an extension of our previous work on diagonal covariance based BSRS acoustic modeling. Since full covariance provides richer structural information of acoustic model compared to its diagonal counterpart, it is advantageous for both model clustering and refinement. Therefore, in this work, full covariance is employed in BSRS to keep the structural information until the last step before being converted to diagonal covariance for practical applications. We show that using full covariance further improves the performance over diagonal covariance in the BSRS acoustic modeling framework under the same model size without increasing computational cost in decoding.
Year
Venue
Keywords
2011
12TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2011 (INTERSPEECH 2011), VOLS 1-5
acoustic modeling, bootstrap, model restructuring, full covariance
Field
DocType
Citations 
Pattern recognition,Computer science,Speech recognition,Artificial intelligence,Bootstrapping (electronics),Covariance,Restructuring
Conference
2
PageRank 
References 
Authors
0.37
1
6
Name
Order
Citations
PageRank
Xiaodong Cui141040.82
Xin Chen21169.64
Jian Xue3787.07
Peder A. Olsen439837.80
John R. Hershey584465.57
Bowen Zhou62212246.21