This book presents details of a text-to-speech synthesis procedure using epoch synchronous overlap add (ESOLA), and provides a solution for development of a text-to-speech system using minimum data resources compared to existing solutions. It also examines most natural speech signals including random perturbation in synthesis. The book is intended for students, researchers and industrial practitioners in the field of text-to-speech synthesis.
This book presents details of a text-to-speech synthesis procedure using epoch synchronous overlap add (ESOLA), and provides a solution for development of a text-to-speech system using minimum data resources compared to existing solutions. It also examines most natural speech signals including random perturbation in synthesis. The book is intended for students, researchers and industrial practitioners in the field of text-to-speech synthesis.
Prof. Asoke Kumar Datta, an MSc. (Pure Math), was born in 1935 and worked in Indian Statistical Institute 1955-1994, retired as HOD Electronics and Communication Sciences Department, Visiting Professor of ISI till date; President, BOM-BOM, Kolkata; Senior Guest Researcher, Sir C V Raman Centre for Physics and Music, JU; Executive Member, Society for Natural Language Technology Research, Kolkata; Life Member, Acoustical Society of India; J C Bose Memorial Award, 1969, Sir C V Raman Award, 1982-83 &1998-99, S K Mitra Memorial Award, 1984, Sri C Achyut Menon Prize, 2001.
Inhaltsangabe
Introduction.- Epoch Synchronous Overlap Add (ESOLA) Algorithm.- State Phase Analysis: PDA/VDA Algorithm and Phoneme Classifier.- Phonological Rules.- Intonation.- Random Perturbations.- Application in singing synthesis.