Lively voice: a new model for speaking synthetic characters

نویسندگان

  • Alistair D. N. Edwards
  • Christopher Newell
چکیده

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.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Processing the prosody of oral presentations

Standard advice to people preparing to speak in public is to use a “lively” voice. A lively voice is described as one that varies in intonation, rhythm and loudness: qualities that can be analyzed using speech analysis software. This paper reports on a study analyzing pitch variation as a measure of speaker liveliness. A potential application of this approach for analysis would be for rehearsin...

متن کامل

Creating expressive synthetic voices by unsupervised clustering of audiobooks

In this work we design an approach for automatic feature selection and voice creation for expressive synthesis. Our approach is guided by two main goals: (1) increasing the flexibility of expressive voice creation and (2) overcoming the limitations of speaking styles in expressive synthesis. We define a novel set of features, combining traditionally used prosodic features with spectral features...

متن کامل

A Novel Source Analysis Method by Matching Spectral Characters of LF Model with STRAIGHT Spectrum

This paper presents a voice source analysis method by studying the spectral characters of LF model and their representation in output speech signal. The estimation of source features is defined as the set of LF parameter whose spectrum has the most similar characters in frequency domain, including glottal formant and spectral tilt, with the corresponding characters held by the STRAIGHT spectrum...

متن کامل

Visual Femininity and Masculinity in Synthetic Characters and Patterns of Affect

It has been shown that users of a digital system perceive a more ‘masculine-sounding’ female voice as more persuasive and intelligent than a corresponding but more ‘feminine-sounding’ female voice. Our study explores whether a parallel pattern of affectively colored evaluations can be elicited when femininity and masculinity are manipulated via visual cues instead of via voice. 80 participants ...

متن کامل

Text2Video: Text-Driven Facial Animation using MPEG-4

We present a complete system for the automatic creation of talking head video sequences from text messages. Our system converts the text into MPEG-4 Facial Animation Parameters and synthetic voice. A user selected 3D character will perform lip movements synchronized to the speech data. The 3D models created from a single image vary from realistic people to cartoon characters. A voice selection ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2006