Sparse Hidden Markov Models for Exemplar-based Speech Recognition Using Deep Neural Network Posterior Features
| Type of publication: | Idiap-RR |
| Citation: | Dighe_Idiap-RR-19-2016 |
| Number: | Idiap-RR-19-2016 |
| Year: | 2016 |
| Month: | 8 |
| Institution: | Idiap |
| Abstract: | Statistical speech recognition has been cast as a natural realization of the compressive sensing problem in this work. The compressed acoustic observations are sub-word posterior probabilities obtained from a deep neural network. Dictionary learning and sparse recovery are exploited for inference of the high-dimensional sparse word posterior probabilities. This formulation amounts to realization of a \textit{sparse} hidden Markov model where each state is characterized by a dictionary learned from training exemplars and the emission probabilities are obtained from sparse representations of test exemplars. This new dictionary-based speech processing paradigm alleviates the need for a huge collection of exemplars as required in the conventional exemplar-based methods. We study the performance of the proposed approach for continuous speech recognition using Phonebook and Numbers'95 database. |
| Keywords: | |
| Projects: |
Idiap PHASER 200021-153507 |
| Authors: | |
| Added by: | [ADM] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
