A real-time speech quality improvement system

Author

Zhao, Hua An

Author_Institution

Fac. of Eng., Kyushu Kyoritsu Univ., Kitakyushu, Japan

Volume

1

fYear

2003

fDate

16-19 Sept. 2003

Firstpage

491

Abstract

In this paper, we will present a speech quality improvement system (SQIS) which can be used in a real-time processing. This system is based on 1/f fluctuation theory. It is well known that the 1/f fluctuation is an irregular oscillation in the natural physical world and is of comfortable and agreeable sensation for human. Using this system, automatic generated speeches which lack natural rhythm can be modified to high quality speeches. This system has been tested by some simple Japanese utterances. The results show that this method will be a powerful tool for automatic production of high quality speech and for researches on automatic prosody generations.

Keywords

fluctuations; natural languages; real-time systems; speech processing; speech synthesis; Japanese utterances; automatic generated speeches; automatic prosody generations; fluctuation theory; human sensation; oscillation; real-time processing; speech quality improvement system; Cities and towns; Fluctuations; Frequency; Humans; Real time systems; Rhythm; Speech analysis; Speech processing; Speech synthesis; Synthesizers;

fLanguage

English

Publisher

ieee

Conference_Titel

Emerging Technologies and Factory Automation, 2003. Proceedings. ETFA '03. IEEE Conference

Print_ISBN

0-7803-7937-3

Type

conf

DOI

10.1109/ETFA.2003.1247747

Filename

1247747