An Automatic Dysarthric Speech Recognition Approach using Deep Neural Networks
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2017, Vol 8, Issue 12
Abstract
Transcribing dysarthric speech into text is still a challenging problem for the state-of-the-art techniques or commercially available speech recognition systems. Improving the accuracy of dysarthric speech recognition, this paper adopts Deep Belief Neural Networks (DBNs) to model the distribution of dysarthric speech signal. A continuous dysarthric speech recognition system is produced, in which the DBNs are used to predict the posterior probabilities of the states in Hidden Markov Models (HMM) and the Weighted Finite State Transducers framework was utilized to build the speech decoder. Experimental results show that the proposed method provides better prediction of the probability distribution of the spectral representation of dysarthric speech that outperforms the existing methods, e.g., GMM-HMM based dysarthric speech recogniztion approaches. To the best of our knowledge, this work is the first time to build a continuous speech recognition system for dysarthric speech with deep neural network technique, which is a promising approach for improving the communication between those individuals with speech impediments and normal speakers.
Authors and Affiliations
Jun Ren, Mingzhe Liu
Keywords
Related Articles
- EP ID EP251594
- DOI 10.14569/IJACSA.2017.081207
- Views 111
- Downloads 0
Formal Modeling and Verification of Smart Traffic Environment with Design Aided by UML
Issue challan in response to rules violation, LED (Light Emitting Diode) and Bridge components of this proposed Smart Traffic Monitoring and Guidance System are presented in this paper to monitor violation of rules, upda...
Iris Recognition Using Modified Fuzzy Hypersphere Neural Network with different Distance Measures
In this paper we describe Iris recognition using Modified Fuzzy Hypersphere Neural Network (MFHSNN) with its learning algorithm, which is an extension of Fuzzy Hypersphere Neural Network (FHSNN) proposed by Kulkarni et...
A Novel Approach to Detect Duplicate Code Blocks to Reduce Maintenance Effort
It was found in many cases that a code might be a clone for one programmer but not the same for another one. This problem occurs because of inaccurate documentation. According to research, the maintainers are not aware o...
A Survey of Big Data Analytics in Healthcare
Debate on big data analytics has earned a remarkable interest in industry as well as academia due to knowledge, information and wisdom extraction from big data. Big data and cloud computing are two most important trends...
Design and Development of AlgoWBIs
AlgoWBIs has been developed to support algorithm learning. The goal to develop this tool is to empower educators and learners with an interactive learning tool to improving algorithm’s skills. The paper focuses on how to...