Full-text

URL: http://www.pyoudeyer.com/prosodyProd.ps

Cached: PDF-31K    PS-61K    PS.gz-24K

SAVE AS an easy-to-recall long filename:

Filename format: author--year--title   PDF-31K    PS-24K    :: About GZip'd PS

Filename format: author--year--title--journal|proceedings|...--pages   PDF-31K    PS-24K

Related links

CiteSeer: http://citeseer.ist.psu.edu/543564.html

Web search: Google Web Search   ::   Google Scholar

Within this site: References (11)

Paper at a Glance

The Synthesis of Cartoon Emotional Speech
Pierre­yves Oudeyer
Sony Computer Science Lab, Paris, France
py@csl.sony.fr

Abstract Recent years have been marked by the increasing develop­ ment of personal robots such as small pets or humanoids, of­ ten having young and cartoon like personalities. A key feature they currently lack is the ability to speak in a emotional life­like manner. We present here a technology that makes this possible by using concatenative speech synthesis.
1. Introduction Recent years have been marked by the increasing development of personal robots, either used as new educational technologies or for pure entertainment. Typically, these robots look like fa­ miliar pets such as dogs or cats (e.g. the Sony AIBO robot), or sometimes take the shape of young children such as the hu­ manoids SDR3­X (Sony). Among the capabilities that these personal robots need is the ability to express their own emotions. Indeed, not only emotions are crucial to human reasoning, but they are central to social regulation. Emotional communication is at the same time primitive enough and efficient enough so that we use it a lot when we interact with pets, in particular when we tame them. This is also certainly what allows children to bootstrap language learning and should be inspiring to teach robots natu­ ral language. In this paper, we present the result of our research for means to express emotions vocally for a baby­like robot. Unlike most of existing work, we are dealing with cartoon­like meaningless speech, which has different needs and different constraints than trying to produce naturally sounding adult­like normal emo­ tional speech. For example we would like the emotions to be recognized by people of different cultural or linguistic back­ ground. Our work has similarities with the one of ([2]), but we use concatenative speech synthesis and our algorithm is simpler and completely specified. The work presented here is based on the use of freely available softwares ...

@inproceedings{oudeyerprosody2002b,
  author={P-Y. Oudeyer},
  title={The Synthesis of Cartoon Emotional Speech},
  year={2002},
  pages={551-554},
  editor={Bel B. and Marlien I.},
  booktitle={Proceedings of the 1st International Conference on Speech Prosody},
  url={http://www.isrl.uiuc.edu/~amag/langev/paper/oudeyerprosody2002b.html}
}

HOME   ::  Conference List   ::   Conference Paper	Comments to: junwang4 you-know-at gmail.com	Last update: 2/6/08