论文信息 - Using context to specify intonation in speech synthesis

Using context to specify intonation in speech synthesis

A generator based on Combinatory Categorial Grammar using a simple and domain-independent discourse model can be used to direct synthesis of intonation contours for responses to data-base queries, conveying distinctions of contrast and emphasis determined by the discourse model and the state of the knowledge-base. Comments University of Pennsylvania Department of Computer and Information Science Technical Report No. MSCIS-93-102. This technical report is available at ScholarlyCommons: http://repository.upenn.edu/cis_reports/241 Using Context To Specify Intonation In Speech Synthesis MS-CIS-93-102 LINC LAB 263 Scott Prevost Mark Steedman University of Pennsylvania School of Engineering and Applied Science Computer and Information Science Department Philadelphia, PA 19104-6389

Mark Steedman | Scott Prevost

[1] J. Pierrehumbert. The phonology and phonetics of English intonation , 1987 .

[2] Mark Steedman. Structure and Intonation , 1991 .

[3] J. Terken. The Distribution of Pitch Accents in Instructions as a Function of Discourse Structure , 1984 .

[4] Julia Hirschberg,et al. Accent and Discourse Context: Assigning Pitch Accent in Synthetic Speech , 1990, AAAI.

[5] Mark Steedman,et al. Surface Structure, Intonation, and “Focus” , 1991 .

[6] Julia Hirschberg,et al. Assigning Intonational Features in Synthesized Spoken Directions , 1988, ACL.

[7] F. Fallside,et al. Speech synthesis from concept: A method for speech output from information systems , 1979 .

[8] J. Pierrehumbert,et al. Intonational structure in Japanese and English , 1986, Phonology.

[9] Steven Bird. Focus and Phrasing in Unification Categorial Grammar , 1991 .

[10] Bonnie L. Webber,et al. Flexible support for trauma management through goal-directed reasoning and planning , 1992, Artif. Intell. Medicine.

[11] Mark Steedman,et al. Generating Contextually Appropriate Intonation , 1993, EACL.