This session has been closed
Recent TTS (Text-To-Speech) technology is achieving very natural quality where we may interpret machine-synthesized speech as human’s one. However, the current technology is not necessarily successful to speak with emotion and intention, as usual humans do. In this talk, we introduce JEITA guideline for speaking style, IT-4012, which tries to match customer’s needs with future TTS solutions.
Speaker
Association for Named Entity
Representative
Mr. Junichi Hirasawa