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 124
- Downloads 0
Recent Approaches to Enhance the Efficiency of Ultra-Wide Band MAC Protocols
Ultra-wide band (UWB) is a promising radio technology to transmit huge data in short distances between different digital devices or between individual components of a personal computer. Due to the magnificent features of...
STUDY OF INDIAN BANKS WEBSITES FOR CYBER CRIME SAFETY MECHANSIM
The human society has undergone tremendous changes from time to time with rapid pace at social level from the beginning and technological level ever since the rise of technologies. This technology word changes the human...
TPACK Adaptation among Faculty Members of Education and ICT Departments in University of Sindh, Pakistan
Technological Pedagogical Content Knowledge (TPACK) framework has been to investigate the technological and instructive knowledge of teachers. Many researchers have found this framework a useful tool to explore teachers’...
A survey on top security threats in cloud computing
Cloud computing enables the sharing of resources such as storage, network, applications and software through internet. Cloud users can lease multiple resources according to their requirements, and pay only for the servic...
IMPROVING THE SECURITY OF THE MEDICAL IMAGES
Applying security to the transmitted medical images is important to protect the privacy of patients. Secure transmission requires cryptography, and watermarking to achieve confidentiality, and data integrity. Improving c...