Enhancement of Speech Signal Using Improved FA-ANFIS Classifier for Hearing AIDS Application

Authors

  • Dr. N. Shanmugapriya Assistant Professor & Head, Department of Computer Applications (PG), Dr. S.N.S. Rajalakshmi College of Arts & Science, Coimbatore. Author

DOI:

https://doi.org/10.61841/4jf4q274

Keywords:

Speech Signal Enhancement, Fast Independent Component Analysis (Fast ICA), Improved Discrete Wavelet Transform (IDWT), Firefly Algorithm, Improved FA-ANFIS

Abstract

Research is undergoing in hearing aids application in the sense of dealing with background noise in speech. It aims to understand the speech in the availability of background noise. It acts as challenging environment to enhance the speech understanding during presence of noise. Thus, hearing aid applications had been introduced to understand the speech even in the presence of noise in various environments for end users. It is one type of methodology adopted for improving the user to understand the information in signal. This speech enhancement application helps to improve availability of data. Additionally, it increases the speech signal intelligibility and quality of the application. This review introduced the mechanism for improving these above-mentioned characteristics in applications such as hearing aids. This could be followed out using enhancement methods namely, Fast Independent Component Analysis algorithm shortly Fast ICA. This helps to reduce the noise presence in speech-related signals. This process also involves IDWT techniques, where IDWT stands for Improved Discrete Wavelet Transform, to do feature selection. Features have been extracted from the speech signal that are denoised. AANOVA stands for Advanced Analysis of Variance and helps to identify the important feature from the features that are already selected in the previous process. Finally, the features that are extracted as important have been given for the optimization algorithm in order to get the features in an optimized manner. Now lastly collected features are then classified efficiently using ANFIS. ANFIS stands for Adaptive Neural Fuzzy Inference System, which is a classification approach. It is also called the Improved FAANFIS Method. The result obtained in the proposed approach proves that it would give out promisingly better speech intelligibility and good quality over speech signals in hearing aid commodities as compared to applications that already exist.

Downloads

Download data is not yet available.

References

[1] N.Shanmugapriya, E.Chandra, A Thorough Investigation on Speech Enhancement Techniques for Hearing

Aids, International Journal of Computer Applications (0975–8887) Vol 99–No.13, August 2014.

[2] Rashmirekha Ram, Mihir Narayan Mohanty, The Use of Deep Learning in Speech Enhancement, Proceedings

of the First International Conference on Information Technology and Knowledge Management, Vol. 14, 2017.

[3] John Woodruff, DeLiang Wang, Directionality-Based Speech Enhancement for Hearing Aids, IEEE, 2017.

[4] Amir Hussain, Jon Barker, Ricard Marxer, Ahsan Adeel, William Whitmer, Roger Watt and Peter Derleth,

Towards Multi-modal Hearing Aid Design and Evaluation in Realistic Audio-Visual Settings: Challenges and

Opportunities, Proc. of the 1st Int. Conference on Challenges in Hearing Assistive Technology (CHAT-17),

August 19, 2017.

[5] N. Shanmugapriya and E. Chandra, Evaluation Of Sound Classification Using Modified Classifier And Speech

Enhancement Using Ica Algorithm For Hearing Aid Application, ICTACT Journal On Communication

Technology, Vol 07, March 2016.

[6] ShifengOu, Chao Geng, Xianyun Wang, Ying Gao, A Two-Step Noise Estimation Algorithm for Noisy Speech

Enhancement, International Journal of Signal Processing, Image Processing and Pattern Recognition, Vol. 6,

No. 5, 2013.

[7] Somanath Pradhan, SankhaSubhra Bhattacharjee, Vinal Patel, Nithin V. George, Speech Enhancement In

Digital Hearing Aids: AnActive Noise Control Approach, 24th International Conference on Sound and

Vibration, July 2017.

[8] Marco Siniscalchi, Yu Tsao, Syu-Siang Wang, Wen-Hung Liao, Experimental Study on Extreme Learning

Machine Applications for Speech Enhancement, IEEE Access, October 2017.

[9] Devyani S. Kulkarni, Ratnadeep R. Deshmukh, Pukhraj P. Shrishrimal, A Review of Speech Signal

Enhancement Techniques, International Journal of Computer Applications (0975 – 8887) Vol 139 – No.14,

April 2016.

[10] E.Verteletskaya, K.Sakhnov, Voice Activity Detection for Speech Enhancement Applications,

ActaPolytechnica Vol. 50 No. 4, 2010.

[11] K.Mohanaprasad, P.Arulmozhivarman, Comparison of Fast ICA and Gradient Algorithms of Independent

Component Analysis for Separation of Speech Signals, International Journal of Engineering and Technology

(IJET).

[12] A. Bharathi, Dr.A.M.Natarajan, Cancer Classification of Bioinformatics data using ANOVA, International

Journal of Computer Theory and Engineering, Vol. 2, No. 3, June, 2010.

[13] Nguyen Cong Long, Phayung Meesad, Herwig Unger, A highly accurate firefly-based algorithm for heart

disease prediction, Expert Systems with Applications An International Conference, June 26, 2015.

[14] Sandhya Balakrishnan P K, Dr.L. Pavithira, Adaptive Neuro Fuzzy Inference System-based Optical Character

Recognition, 10th International Conference on Recent trends in Engineering Science and Management, August

2017.

Downloads

Published

31.05.2020

How to Cite

N. , S. (2020). Enhancement of Speech Signal Using Improved FA-ANFIS Classifier for Hearing AIDS Application. International Journal of Psychosocial Rehabilitation, 24(3), 2037-2047. https://doi.org/10.61841/4jf4q274