Sciweavers

Share
CORR
2016
Springer

Exploiting Low-dimensional Structures to Enhance DNN Based Acoustic Modeling in Speech Recognition

3 years 2 months ago
Exploiting Low-dimensional Structures to Enhance DNN Based Acoustic Modeling in Speech Recognition
We propose to model the acoustic space of deep neural network (DNN) class-conditional posterior probabilities as a union of lowdimensional subspaces. To that end, the training posteriors are used for dictionary learning and sparse coding. Sparse representation of the test posteriors using this dictionary enables projection to the space of training data. Relying on the fact that the intrinsic dimensions of the posterior subspaces are indeed very small and the matrix of all posteriors belonging to a class has a very low rank, we demonstrate how low-dimensional structures enable further enhancement of the posteriors and rectify the spurious errors due to mismatch conditions. The enhanced acoustic modeling method leads to improvements in continuous speech recognition task using hybrid DNN-HMM (hidden Markov Models) framework in both clean and noisy conditions.
Pranay Dighe, Gil Luyet, Afsaneh Asaei, Herv&eacut
Added 01 Apr 2016
Updated 01 Apr 2016
Type Journal
Year 2016
Where CORR
Authors Pranay Dighe, Gil Luyet, Afsaneh Asaei, Hervé Bourlard
Comments (0)
books