Method and device for synthesizing and distributing voice types for voice-enabled devices

作者: Albert Noyes

DOI:

关键词: MultimediaThe InternetSoftwareComputer science

摘要: The present invention discloses a method and device that gives users the ability to select manipulate specific celebrity voice types into “voice flavors”. Voice flavors can be used with voice-enabled appliances, devices computer programs, Internet satellite delivered news services, other software hardware applications in business and/or daily life.

参考文章(15)
Philip John Busardo, Allophonic text-to-speech generator ,(1998)
Jason Raymond Baumgartner, Nadeem Malik, Steven Leonard Roberts, Flemming Andersen, High performance voice transformation apparatus and method ,(1999)
Steve D. Pearson, Kazue Hata, Stephen Johnson, Ronald B. Richard, Brian A. Hanson, Judson Hofmann, Electronic news reception apparatus that selectively retains sections and searches by keyword or index for text to speech conversion ,(1997)
Ellen M. Eide, Robert E. Donovan, Methods for generating pitch and duration contours in a text to speech system ASAJ. ,vol. 109, pp. 1285- ,(1998)
Paula Tallal, Steven Lamont Miller, Michael M. Merzenich, William M. Jenkins, Bret E. Peterson, Method and apparatus for training of sensory and perceptual systems in lli subjects Journal of the Acoustical Society of America. ,vol. 108, pp. 1380- 1381 ,(1998)
Dale Boss, Retaining prosody during speech analysis for later playback Journal of the Acoustical Society of America. ,vol. 107, pp. 2949- ,(1996) , 10.1121/1.429355
Willis J. Luther, Graphics user interface for controlling text-to-speech conversion Journal of the Acoustical Society of America. ,vol. 100, pp. 3487- ,(1992) , 10.1121/1.417253