Speech synthesis and emotions : a compromise between flexibility and believability
ZOVATO, E., ROMPORTL, J. Speech synthesis and emotions : a compromise between flexibility and believability. In Fourth International Workshop on Human-Computer Conversation. [Sheffield]: [University of Sheffield], 2008. s. 1-5.
|Druh:||STAŤ VE SBORNÍKU|
|Anglický název:||Speech synthesis and emotions : a compromise between flexibility and believability|
|Název zdroje:||[University of Sheffield]|
|Autoři:||Enrico Zovato , Jan Romportl|
|Abstrakt CZ:||Článek se zabývá možnostmi emocionální syntézy v systémech převodu textu na řeč.|
|Abstrakt EN:||The synthesis of emotional speech is still an open question. The principal issue is how to introduce expressivity without compromising the naturalness of the synthetic speech produced by means of the state-of-the-art technology. In this paper two concatenative synthesis systems are described and some approaches to address this topic are proposed. One of the reported proposals is to consider the intrinsic expressivity of certain speech acts, i.e. exploit the correlation between affective states and communicative functions. This implies a different approach in the design of the databases for speech synthesis. In fact, beyond phonetic and prosodic criteria, linguistic and pragmatic aspects should also be considered|