QQ客服 官方微博 反馈留言

	Gesture Design of Hand-to-Speech Converter derived from Speech-to-Hand Converter based on Probabilistic Integration Model
	Aki Kunikoshi; Yu Qiao; Daisuke Saito; Nobuaki Minematsu; Keikichi Hirose
	2011
会议名称	12th Annual Conference of the International-Speech-Communication-Association 2011
会议地点	Florence, ITALY
英文摘要	When dysarthrics, individuals with speaking disabilities, try to communicate using speech, they often have no choice but to use speech synthesizers which require them to type word symbols or sound symbols. Input by this method often makes real-time communication troublesome and dysarthric users struggle tohave smooth flowing conversations. In this study, we are developing a novel speech synthesizer where speech is generated through hand motions rather than symbol input. In recent years, statistical voice conversion techniques have been proposed based on space mapping between given parallel utterances. By applying these methods, a hand space was mapped to a vowel space and a converter from hand motions to vowel transitions was developed. It reported that the proposed method is effective enough to generate the five Japanese vowels. In this paper, we discuss the expansion of this system to consonant generation. In order to create the gestures for consonants, a Speech-to-Hand conversion system is firstly developed using parallel data for vowels, in which consonants are not included. Then, we are able to automatically search for candidates for consonant gestures for a Hand-to-Speech system.
收录类别	EI
语种	英语
内容类型	会议论文
源URL	[http://ir.siat.ac.cn:8080/handle/172644/3264]
专题	深圳先进技术研究院_集成所
作者单位	2011
推荐引用方式 GB/T 7714	Aki Kunikoshi,Yu Qiao,Daisuke Saito,et al. Gesture Design of Hand-to-Speech Converter derived from Speech-to-Hand Converter based on Probabilistic Integration Model[C]. 见:12th Annual Conference of the International-Speech-Communication-Association 2011. Florence, ITALY.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。