tailieunhanh - Báo cáo khoa học: "Constituent-based Accent Prediction"

Near-perfect automatic accent assignment is attainable f o r citation-style speech, but better computational models are needed to predict accent in extended, spontaneous discourses. This paper presents an empirically motivated theory o f the discourse focusing nature o f accent in spontaneous speech. Hypotheses based on this theory lead to a new approach to accent prediction, in which patterns of deviation from citation form accentuation, defined at the constituent or noun phrase level, are atttomatically learned from an annotated corpus. . | Constituent-based Accent Prediction Christine H. Nakatani AT T Labs - Research 180 Park Avenue Florham Park NJ 07932-0971 USA email chn@ Abstract Near-perfect automatic accent assignment is attainable for citation-style speech but better computational models are needed to predict accent in extended spontaneous discourses. This paper presents an empirically motivated theory of the discourse focusing nature of accent in spontaneous speech. Hypotheses based on this theory lead to a new approach to accent prediction in which patterns of deviation from citation form accentuation defined at the constituent or noun phrase level are automatically learned from an annotated corpus. Machine learning experiments on 1031 noun phrases from eighteen spontaneous direction-giving monologues show that accent assignment can be significantly improved by up to 4 -6 relative to a hypothetical baseline system that would produce only citation-form accentuation giving error rate reductions of 11 -25 . 1 Introduction In speech synthesis systems near-perfect 98 accent assignment is automatically attainable for read-aloud citation-style speech Hirschberg 1993 . But for unrestricted extended spontaneous discourses highly natural accentuation is often achieved only by costly human post-editing. A better understanding of the effects of discourse context on accentual variation is needed not only to fully model this fundamental prosodic feature for text-to-speech TTS synthesis systems but also to further the integration of prosody into speech understanding and concept-to-speech CTS synthesis systems at the appropriate level of linguistic representation. This paper presents an empirically motivated theory of the discourse focusing function of accent. The theory describes for the first time the interacting contributions to accent prediction made by factors related to the local and global attentional status of discourse referents in a discourse model Grosz and Sidner 1986 . The .