%Aigaion2 BibTeX export from Idiap Publications %Thursday 21 November 2024 12:01:49 PM @TECHREPORT{Dighe_Idiap-RR-19-2016, author = {Dighe, Pranay and Asaei, Afsaneh and Bourlard, Herv{\'{e}}}, projects = {Idiap, PHASER 200021-153507}, month = {8}, title = {Sparse Hidden Markov Models for Exemplar-based Speech Recognition Using Deep Neural Network Posterior Features}, type = {Idiap-RR}, number = {Idiap-RR-19-2016}, year = {2016}, 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.}, pdf = {https://publications.idiap.ch/attachments/reports/2015/Dighe_Idiap-RR-19-2016.pdf} }