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 low- dimensional 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 di- mensions 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 en- hancement 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 model) framework in both clean and noisy conditions, where upto 15.4% relative reduction in word error rate (WER) is achieved.


Publié dans:
2016 Ieee International Conference On Acoustics, Speech And Signal Processing Proceedings, 5690-5694
Présenté à:
Proceedings of 2016 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2016), Shanghai
Année
2016
Publisher:
New York, IEEE
ISSN:
1520-6149
ISBN:
978-1-4799-9988-0
Mots-clefs:
Laboratoires:




 Notice créée le 2016-04-19, modifiée le 2019-03-17

n/a:
Télécharger le document
PDF

Évaluer ce document:

Rate this document:
1
2
3
 
(Pas encore évalué)