DocumentCode :
1618966
Title :
Speech and audio processing for multimedia communications
Author :
Lee, Chin-Hui
Author_Institution :
Lucent Technols., Bell Labs., Murray Hill, NJ, USA
Volume :
2
fYear :
1997
Abstract :
Summary form only given. Multimedia communication involves processing, storage, transmission forwarding, and presentation of audiovisual information, and establishing natural interfaces between systems and their users. The computing, communication and integration infrastructures needed to support multimedia applications are also of great interest. Three of the key technologies in realizing multimedia systems are: coding of audiovisual signals, such as speech, audio, image and video; machine synthesis of these signals; and machine recognition and verification of the information embedded in these signals. The article focuses the discussion on speech and audio processing. It addresses the technology dimensions and challenges of speech and audio coding, text-to-speech synthesis, automatic speech recognition, and automatic speaker authentication. It illustrates some of the technology capabilities and limitations by a set of demonstration examples. It also discusses multimedia applications and shows examples of spoken language systems used to enhance multimedia communication between humans and machines
Keywords :
audio coding; multimedia communication; speaker recognition; speech coding; speech recognition; speech synthesis; audio coding; audio processing; audiovisual information; audiovisual signal coding; automatic speaker authentication; automatic speech recognition; machine recognition; machine synthesis; machine verification; multimedia communications; speech coding; speech processing; spoken language systems; text-to-speech synthesis; Automatic speech recognition; Image coding; Image recognition; Multimedia communication; Multimedia computing; Multimedia systems; Signal synthesis; Speech coding; Speech processing; Speech synthesis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
TENCON '97. IEEE Region 10 Annual Conference. Speech and Image Technologies for Computing and Telecommunications., Proceedings of IEEE
Conference_Location :
Brisbane, Qld.
Print_ISBN :
0-7803-4365-4
Type :
conf
DOI :
10.1109/TENCON.1997.648283
Filename :
648283
Link To Document :
بازگشت