Please use this identifier to cite or link to this item:
|Title:||Comparison of discriminative input and output transformations for speaker adaptation in the hybrid NN/HMM systems||Authors:||Li, B.
|Issue Date:||2010||Citation:||Li, B.,Sim, K.C. (2010). Comparison of discriminative input and output transformations for speaker adaptation in the hybrid NN/HMM systems. Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010 : 526-529. ScholarBank@NUS Repository.||Abstract:||Speaker variability is one of the major error sources for ASR systems. Speaker adaptation estimates speaker specific models from the speaker independent ones to minimize the mismatch between the training and testing conditions arisen from speaker variabilities. One of the commonly adopted approaches is the transformation based method. In this paper, the discriminative input and output transforms for speaker adaptation in the hybrid NN/HMM systems are compared and further investigated with both structural and data-driven constraints. Experimental results show that the data-driven constrained discriminative transforms are much more robust for unsupervised adaptation. © 2010 ISCA.||Source Title:||Proceedings of the 11th Annual Conference of the International Speech Communication Association, INTERSPEECH 2010||URI:||http://scholarbank.nus.edu.sg/handle/10635/41498|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Dec 8, 2022
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.