Robust Techniques for Speech Recognition

ISBN-13: 9786202054157 / Angielski / Miękka / 176 str.

Vimala Chinnaraj; Radha Venkatachalam

Opis

Empowered by revolutionary models and techniques, developments in the field of Automatic Speech Recognition (ASR) have emerged as a pragmatic and useful technology for various applications. However, building up an ultimate ASR system involves many challenges and constraints on user and environment. These significant difficulties need to be addressed for making the ASR robust and wider. Consequently, the main goal of the book is to enhance the robustness of speech recognition by introducing an efficient speech front-end processing techniques using modified GFCC features and machine learning algorithms. The main objective of this book is to provide a hypothetically stable and sensibly comprehensive depiction of the essential learning and ideas of speech recognition by machine. There are several key factors discussed in the book including the fundamentals of speech signals, comprehensive overview of digital speech processing and the components of speech recognition. The major portion of the book concentrates on building up a typical and robust framework for both noise free and noisy environments, or else of developing separate algorithms for various environments.

O autorze

Chinnaraj, VimalaDr. Vimala C. received her Ph.D. Degree in Computer Science in 2015. She has worked in the UGC Major Research project in the field of Automatic Speech Recognition. Her major area of research interests includes Automatic Speech Recognition, Text-To-Speech Synthesis and Speech Signal Enhancement Techniques. She has published 20 research papers.