Hybridized Feature Extraction and Acoustic Modelling Approach for Dysarthric Speech Recognition

Dysarthria is malfunctioning of motor speech caused by faintness in the human nervous system. It is characterized by the slurred speech along with physical impairment which restricts their communication and creates the lack of confidence and affects the lifestyle. This paper attempt to increase the efficiency of Automatic Speech Recognition (ASR) system for unimpaired speech signal. It describes state of art of research into improving ASR for speakers with dysarthria by means of incorporated knowledge of their speech production. Hybridized approach for feature extraction and acoustic modelling technique along with evolutionary algorithm is proposed for increasing the efficiency of the overall system. Here number of feature vectors are varied and tested the system performance. It is observed that system performance is boosted by genetic algorithm. System with 16 acoustic features optimized with genetic algorithm has obtained highest recognition rate of 98.28% with training time of 5:30:17.

[1]  Felipe Trujillo-Romero,et al.  Evolutionary approach for integration of multiple pronunciation patterns for enhancement of dysarthric speech recognition , 2014, Expert Syst. Appl..

[2]  Santiago Omar Caballero Morales.  Estimation of Phoneme-Specific HMM Topologies for the Automatic Recognition of Dysarthric Speech , 2013, Comput. Math. Methods Medicine.

[3]  Hynek Hermansky,et al.  Analysis of MLP-Based Hierarchical Phoneme Posterior Probability Estimator , 2011, IEEE Transactions on Audio, Speech, and Language Processing.

[4]  Seyed Reza Shahamiri,et al.  Artificial neural networks as speech recognisers for dysarthric speech: Identifying the best-performing set of MFCC parameters and studying a speaker-independent approach , 2014, Adv. Eng. Informatics.

[5]  Mondher Frikha,et al.  A Comparitive Survey of ANN and Hybrid HMM/ANN Architectures for Robust Speech Recognition , 2012 .

[6]  Martin Karafiát,et al.  Integrating Recent MLP Feature Extraction Techniques into TRAP Architecture , 2011, INTERSPEECH.

[7]  Mounir Boukadoum,et al.  Hidden Neural Network for Complex Pattern Recognition: A Comparison Study with Multi- Neural Network Based Approach , 2013 .

[8]  Mark Hasegawa-Johnson,et al.  State-Transition Interpolation and MAP Adaptation for HMM-based Dysarthric Speech Recognition , 2010, SLPAT@NAACL.

[9]  Mark Hasegawa-Johnson,et al.  Acoustic model adaptation using in-domain background models for dysarthric speech recognition , 2013, Comput. Speech Lang..