Method and system for text-to-speech synthesis with personalized voice
作者： Ron Hoory , Itzhack Goldberg , Boaz Mizrachi , Zvi Kons
DOI:
关键词: Speech recognition 、 Expression (mathematics) 、 Computer science 、 Text to speech synthesis 、 Speaker diarisation
摘要: A method and system are provided for text-to-speech synthesis with personalized voice. The includes receiving an incidental audio input ( 403 ) of speech in the form communication from speaker 401 generating a voice dataset 404 ). text 411 at same device as synthesizing 312 to synthesized including using personalize sound like In addition, analyzing 316 expression adding 315 speech. may be part video 453 have associated visual 455 image speaker. include providing look expressions added
lens.org 参考文章(44)
Pradeep Mansey, Brent Davis, Peeyush Jaiswal, Chat and teleconferencing system with text to speech and speech to text translation ,(2004)
Daniel Yellin, Wave digital filter with low power consumption ,(2000)
John Locke, Voice enabled personalized documents ,(2003)
Donald Tang, Ligin Shen, Wei Zhang, Qin Shi, Method for generating pesonalized speech from text ,(2002)
Mikio Saito, Takao Yamagishi, Hideaki Sato, Chat system, communication device, control method thereof and computer-readable information storage medium ,(2005)
Christopher Pavlovski, Thomas Creamer, Peeyush Jaiswal, Voice-to-text reduction for real time IM/chat/SMS ,(2003)
David E. Reich, Method and system for generating natural sounding concatenative synthetic speech ,(2003)
Michael C. Huttinger, Cenk Demiroglu, Jonathan Kahn, Synchronized pattern recognition source data processed by manual or automatic means for creation of shared speaker-dependent speech user profile ,(2005)
Sheng Zhao, Min Chu, Yong Zhao, Providing personalized voice front for text-to-speech applications ,(2004)
Caroline G. Henton, Method and apparatus for automatic generation of vocal emotion in a synthetic text-to-speech system ,(1997)