Prosody, Models, and Spontaneous Speech

This paper presents a definition of prosody as the organization of linguistic units within an utterance and a coherent group of utterances, having manifestations both in segmental and suprasegmental features of speech, serving at the same time as a medium for conveying para- and nonlinguistic information. It then discusses the process of spontaneous speech production, emphasizing the role of quantitative generative models in both speech synthesis and speech recognition, examples are illustrated in Japanese. Finally, it discusses the continuum of spontaneity in speech, and briefly touches on the characteristics of speech that become dominant with increased spontaneity.