User-interactive knowledge-based speech enhancement

Author

Chiou, Fred Y. ; Barnwell, Thomas P., III

Author_Institution

Sch. of Electr. Eng., Georgia Inst. of Technol., Atlanta, GA, USA

Volume

3

fYear

1992

fDate

10-13 May 1992

Firstpage

1495

Abstract

Presents the details of a system which combines symbolic and numerical (signal processing) processing in a unified, interactive environment for the purpose of enhancing distorted speech and audio signals. The system is intended to allow the user to effectively and efficiently combine many different signal and symbolic processing techniques in order to interactively create an enhancement solution which is tailored to the specific distorted signal of interest. The primary goal is to allow the use of many different classes of available information (signal, noise, derived constituent structure, phonemic content, talker characteristics, segment boundaries, etc.) in the enhancement process, and to make the combination of the enhancement procedures easy for an experienced and expert user

Keywords

knowledge based systems; speech analysis and processing; IKBS; derived constituent structure; distorted audio signals; distorted speech; interactive environment; knowledge-based speech enhancement; numerical signal processing; phonemic content; segment boundaries; symbolic signal processing; talker characteristics; Digital signal processing; Distortion; Engines; Knowledge based systems; Signal generators; Signal processing; Signal processing algorithms; Speech enhancement; Speech processing; User interfaces;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1992. ISCAS '92. Proceedings., 1992 IEEE International Symposium on

Conference_Location

San Diego, CA

Print_ISBN

0-7803-0593-0

Type

conf

DOI

10.1109/ISCAS.1992.230217

Filename

230217