Hearing aid users are exposed to diversified vocal scenarios. The necessity for sound classification algorithms becomes a vital factor to yield good listening experience. In this work, an approach is proposed to improve the speech quality in the hearing aids based on Independent Component Analysis (ICA) algorithm with modified speech signal classification methods. The proposed algorithm has better results on speech intelligibility than other existing algorithm and this result has been proved by the intelligibility experiments. The ICA algorithm and modified Bayesian with Adaptive Neural Fuzzy Interference System (ANFIS) is to effectiveness of the strategies of speech quality, thus this classification increases noise resistance of the new speech processing algorithm that proposed in this present work. This proposed work indicates that the new Modified classifier can be feasible in hearing aid applications.
N. Shanmugapriya1, E. Chandra2
Dr. SNS Rajalakshmi College of Arts and Science, India1, Bharathiar University, India2
Independent Component Analysis (ICA), Speech Intelligibility, Bayesian Modified with Adaptive Neural Fuzzy Interference System (ANFIS) | Published By :
ICTACT
Published In :
ICTACT Journal on Communication Technology
( Volume: 7 , Issue: 1 )
Date of Publication :
March 2016
|