DocumentCode :
1852370
Title :
Prosodic Chinese Sign Language Synthesis Driven by Speech
Author :
Sen Wang ; LiChun Wang ; Dehui Kong
Author_Institution :
Beijing Key Lab. of Multimedia & Intell. Software Technol., BJUT, Beijing, China
fYear :
2013
fDate :
21-23 June 2013
Firstpage :
1951
Lastpage :
1954
Abstract :
Making virtual human´s actions more natural and more approaching to reality is helpful for enhancing intelligibility of synthesized Chinese sign language (CSL). Usually action with prosody looks more vivid and prosody means that same word has discriminating style according to different context. The problem here is how to find and indicate the context. As formal description for CSL, CSLML provides a set of top level tags for recording context. This paper provides a new method for finding prosody information of context, which is utilizing speech sounds. Hidden Markov model (HMM) is trained for finding different prosody patterns, such as word stressing, sentence modal, and emotions etc. And parameters of HMM are mapped to value of tags in CSLML. The prosody tags are then transferred to animation parameter to synthesize prosodic Chinese Signed Language expression. Experiments in this paper show that synthesized animation driven by prosody parameters extracted with HMM is more realistic.
Keywords :
computer animation; feature extraction; handicapped aids; hidden Markov models; sign language recognition; speech intelligibility; speech recognition; CSLML; HMM parameters; animation parameter; context prosody information finding; formal description; hidden Markov model; intelligibility; prosodic Chinese sign language synthesis; prosodic Chinese signed language expression; prosody parameters extraction; prosody patterns; recording context; speech sounds; synthesized animation; top level tags; virtual human; Assistive technology; Feature extraction; Gesture recognition; Hidden Markov models; Speech; Speech recognition; Stress; CSLML; Chinese signed language; HMM; prosody; speech;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computational and Information Sciences (ICCIS), 2013 Fifth International Conference on
Conference_Location :
Shiyang
Type :
conf
DOI :
10.1109/ICCIS.2013.510
Filename :
6643429
Link To Document :
بازگشت