Introduction.- Generation of Speech Signal and its Characteristics.- Information of Adaptive Filters and Noises.- Information of Wavelet Transforms.- Speech Signal Enhancement using Adaptive Filters.- Speech Signal Enhancement using Adaptive Filters and Wavelet Transforms.- Future Research Direction.- Conclusion.
Dr. Komal R. Borisagar has obtained her Ph.D. in Speech Enhancement Techniques for Digital Hearing Aids in 2012. She has teaching experience of over 15 years. She is working as an Associate Professor at Electronics & Communication Department, Atmiya Institute of Technology and Science, Rajkot. She has published 2 books, 3 book chapters and more than 50 research papers to her credit in referred & indexed journals, conferences at international and in IEEE digital library. She has achieved best paper award five times for her research articles and presentation. Her areas of interest are wireless communication, speech processing, signal & system and image processing.
Dr. Rohit M. Thanki has obtained his Ph.D. in Multibiometric System Security using CS Theory and Watermarking from C. U. Shah University, Wadhwan city, Gujarat, India in 2017. His area of research is Digital Watermarking, Biometrics System, Security, Compressive Sensing, Pattern Recognition and Image Processing. He has published 7 books, 9 book chapters and more than 25 research papers to his credit in refereed & indexed journals, and conferences at international and national level. He has achieved best paper presentation awards 2 times for his research articles. His international recognition includes his professional memberships & services in refereed organizations, programme committees and reviewer for journals published by IEEE, Elsevier, Taylor & Francis, Springer, IGI-Global etc.
Dr. Bhavin S. Sedani is working as a professor in Electronics and Communication Department at L.D. College of Engineering, Ahmedabad. He has teaching experience of 16 years. He has presented more than 46 research papers in various international and national conferences. His 21 research papers are published in various international journals and IEEE Xplore. He has achieved best paper presentation awards 7 times for his research articles. He is awarded with pedagogical award for continuing efforts towards teaching learning methodology, research and innovation in 2017 by Gujarat Technological University, Young Researcher Award in 2018 by Integrated Intelligent Research, ISTE Professional Center, Anna University Campus, Chennai – India. His area of research is in wireless communication and speech processing.
This book provides various speech enhancement algorithms for digital hearing aids. It covers information on noise signals extracted from silences of speech signal. The description of the algorithm used for this purpose is also provided. Different types of adaptive filters such as Least Mean Squares (LMS), Normalized LMS (NLMS) and Recursive Lease Squares (RLS) are described for noise reduction in the speech signals. Different types of noises are taken to generate noisy speech signals, and therefore information on various noises signals is provided. The comparative performance of various adaptive filters for noise reduction in speech signals is also described. In addition, the book provides a speech enhancement technique using adaptive filtering and necessary frequency strength enhancement using wavelet transform as per the requirement of audiogram for digital hearing aids.
Presents speech enhancement techniques for improving performance of digital hearing aids;
Covers various types of adaptive filters and their advantages and limitations;
Provides a hybrid speech enhancement technique using wavelet transform and adaptive filters.