5th International Conference on Spoken Language Processing
This paper proposes new prosodic feature control rules for constructing semantic prosody control. Research was conducted into mental state tendencies using tests that examined the perceptions of the subject's sensibility to the control of synthetic speech prosody. The results showed the relationships between prosodic control rules and non-verbal expressions. Duration control reflects information processing state in spoken dialogues. Sentence final pitch contour control reflects the reliability of the information. Pitch contour dynamic range control indicates the speaker's excitement. The pitch contour control from start to peak pitch contour indicates the speaker's requirement for attention. Furthermore, for the Multi-layered Speech/Sound Synthesis Control Language(MSCL) we construct prosodic feature control commands using prosodic control rules and semantic control commands using the relationships. MSCL realizes expressive synthetic speech.
Bibliographic reference. Mizuno, Osamu / Nakajima, Shin'ya (1998): "New prosodic control rules for expressive synthetic speech", In ICSLP-1998, paper 1014.