Sparse Hidden Markov Models for Automatic Speech Recognition
نویسندگان
چکیده
Stochastic speech recognition has been cast as a natural realization of the compressive sensing problem in this work. The compressed acoustic observations are subword 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 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.
منابع مشابه
Speaker Independent Speech Recognition Using Hidden Markov Models for Persian Isolated Words
متن کامل
Speaker Independent Speech Recognition Using Hidden Markov Models for Persian Isolated Words
متن کامل
Speech enhancement based on hidden Markov model using sparse code shrinkage
This paper presents a new hidden Markov model-based (HMM-based) speech enhancement framework based on the independent component analysis (ICA). We propose analytical procedures for training clean speech and noise models by the Baum re-estimation algorithm and present a Maximum a posterior (MAP) estimator based on Laplace-Gaussian (for clean speech and noise respectively) combination in the HMM ...
متن کاملHidden Markov Models for Automatic Speech Recognition : Theory and Application
Hidden Markov modelling is currently the most widely used and successful method for automatic recognition of spoken utterances. This paper reviews the mathematical theory of hidden Markov models and describes how they are applied to automatic speech recognition.
متن کاملGroup Sparse Hidden Markov Models for Speech Recognition
This paper presents the group sparse hidden Markov models (GS-HMMs) where a sequence of acoustic features is driven by Markov chain and each feature vector is represented by two groups of basis vectors. The group of common bases represents the features across states within a HMM. The group of individual bases compensates the intra-state residual information. Importantly, the sparse prior for se...
متن کامل