Edwards, A.D.N. and Newell, C. (2004) Lively voice: a new model for speaking synthetic characters. Sprache und Datenverarbeitung: International Journal for Language Data Processing, 28 (2). pp. 133-151. ISSN 0343-5205
Speech is one component of most synthetic characters. It is often assumed that the most important objective for such characters is that they should be ‘life-like’, ‘natural’ and ‘believable’. This paper suggests that this is inappropriate and that a better quality is one which we call ‘liveliness’. This concept and many of the ideas behind it derive from the theatre. One of the objectives of this work is to establish the same kind of relationship between the synthetic character and the user as exists between an actor and an audience, the audience is not fooled that the actor ’is’ the character, no more should the synthetic character be expected to be a real person. It is proposed to test these ideas in a performance bringing together an actor, an audience and a computer, all interacting and producing laughter in the audience.
|Keywords:||Performance ; Speech synthesis ; Naturalness ; Voice quality ; Synthetic voice ; Theatre ; Human-computer communication ; Computational linguistics ;|
|Institution:||The University of York|
|Academic Units:||The University of York > Computer Science (York)|
|Depositing User:||York RAE Import|
|Date Deposited:||15 Jun 2009 11:24|
|Last Modified:||15 Jun 2009 11:24|