TAILIEUCHUNG - Báo cáo khoa học: "Generating Contextually Appropriate Intonation"

One source of unnaturalness in the output of text-to-speech systems stems from the involvement of algorithmically generated default intonation contours, applied under minimal control from syntax and semantics. It is a tribute both to the resilience of human language understanding and to the ingenuity of the inventors of these algorithms that the results are as intelligible as they are. However, the result is very frequently unnatural, and may on occasion mislead the hearer. This paper extends earlier work on the relation between syntax and intonation in language understanding in Combinatory Categorial Grammar (CCG). . | Generating Contextually Appropriate Intonation Scott Prevost Mark steedman Computer and Information Science University of Pennsylvania 200 South 33rd Street Philadelphia PA 19104-6389 USA Internet Abstract One source of unnaturalness in the output of text-to-speech systems stems from the involvement of algorithmically generated default intonation contours applied under minimal control from syntax and semantics. It is a tribute both to the resilience of human language understanding and to the ingenuity of the inventors of these algorithms that the results are as intelligible as they are. However the result is very frequently unnatural and may on occasion mislead the hearer. This paper extends earlier work on the relation between syntax and intonation in language understanding in Combinatory Categorial Grammar CCG . A generator with a simple and domain-independent discourse model can be used to direct synthesis of intonation contours for responses to data-base queries to convey distinctions of contrast and emphasis determined by the discourse model. 1 The Problem Consider the exchange shown in example 1 . Capitals indicate stress and brackets informally indicate the intonational phrasing. The intonation contour is indicated underneath using Pierrehumbert s notation 8 1 see 13 for a brief summary . L H Keywords Speech-synthesis Generation. We thank Mark Beutnagel and AT T Bell Laboratories for allowing us access to the TTS speech synthesiser. The research was supported in part by NSF grant nos IRI90-18513 IRI90-16592 and IRI91-17110 DARPA grant no. N00014-90-J-1863 and ARO grant no. DAAL03-89-C0031. and H are different high pitch accents and LH and LL and its relative L are rising and low boundaries respectively. The other annotations indicate that the intonational tunes L H LH and H LL convey two distinct kinds of discourse information. First both pitch accents mark any word that they occur on or rather its .

• Báo cáo khoa học
• Generating Contextually
• Appropriate Intonation
• Scott Prevost & Mark Steedman Mark Jan Nederhof