This paper describes the modeling scheme of emotions appearing in a speech production by using neural network and the synthesizing technique of emotional condition from neutral speech. To model emotion conditions in speech production, Emotion Space is introduced. It has already been proposed in facial expression modeling. Emotion Space can represent emotion condition appearing in speech production in a two dimensional space and realize both mapping and inverse mapping between the emotion condition and the speech production. We developed Emotional Speech Synthesizer to synthesize emotional speech. The Emotional Speech Synthesizer has an ability to synthesize an emotional speech by modifying a neutral speech in its timing, pitch and intensity. This paper also describes the subjective evaluation result of synthesized speech from the Emotion Space.
|出版物ステータス||Published - 1996 12 1|
|イベント||Proceedings of the 1996 5th IEEE International Workshop on Robot and Human Communication, RO-MAN - Tsukuba, Jpn|
継続期間: 1996 11 11 → 1996 11 14
|Other||Proceedings of the 1996 5th IEEE International Workshop on Robot and Human Communication, RO-MAN|
|期間||96/11/11 → 96/11/14|
ASJC Scopus subject areas
- Hardware and Architecture