EUROSPEECH 2003 - INTERSPEECH 2003
8th European Conference on Speech Communication and Technology

Geneva, Switzerland
September 1-4, 2003

        

Prosodic Analysis and Modeling of the NAGAUTA Singing to Synthesize its Prosodic Patterns from the Standard Notation

Nobuaki Minematsu, Bungo Matsuoka, Keikichi Hirose

University of Tokyo, Japan

NAGAUTA is a classical style of the Japanese singing. It has very original and unique prosodic patterns in its singing, where an abrupt and sharp change of F_0 is always observed at a transition from a note to another. This F_0 change is often found even where the transition is not accompanied by a change of tone. In this paper, we propose a model to synthesize this unique F_0 pattern from the standard notation. Further, this paper shows an interesting phenomenon about power movements at the F_0 changes. Acoustic analysis of NAGAUTA singing samples reveals that sharp increases of F_0 and sharp decreases of power are observed synchronously. Although no discussion on physical mechanisms of this phenomenon is done in this paper, another model to generate this unique power pattern is also proposed. Evaluation experiments are done through listening and their results indicate high validity of the two proposed models.

Full Paper

Bibliographic reference.  Minematsu, Nobuaki / Matsuoka, Bungo / Hirose, Keikichi (2003): "Prosodic analysis and modeling of the NAGAUTA singing to synthesize its prosodic patterns from the standard notation", In EUROSPEECH-2003, 385-388.