Title :
Issues in the development of the next generation of concatenative speech synthesis systems
Author_Institution :
Sch. of Inf. Syst., East Anglia Univ., Norwich, UK
Abstract :
While commercial organisations are as interested in the ability of text-to-speech (TTS) systems to perform well at text normalisation and pronunciation as they are in the overall quality of the synthetic voice, there is still a general opinion that TTS systems are only usable for limited applications. The vast majority of applications still require more natural speech and a greater variety of styles and emotion. Work on mark-up has attempted to address the limitations of a plain text interface, but has done little to solve the basic problems of how to maintain a high quality synthetic voice and apply different speaking styles. As a consequence this paper is concerned with one narrow aspect of TTS synthesis, that is the improvement of voice quality through the progressive improvement of existing approaches to unit selection
Keywords :
speech synthesis; TTS systems; concatenative speech synthesis systems; high quality synthetic voice; natural speech; plain text interface; pronunciation; speaking styles; synthetic voice quality; text normalisation; text-to-speech systems; unit selection;
Conference_Titel :
State of the Art in Speech Synthesis (Ref. No. 2000/058), IEE Seminar on
Conference_Location :
London
DOI :
10.1049/ic:20000328