ITRI - 97 - 13 Context Modeling and the Generation of Spoken
نویسنده
چکیده
This paper presents the Dial-Your-Disc (dyd) system, an interactive system that supports browsing through a large database of musical information and generates a spoken monologue once a musical composition has been selected. The paper focuses on the generation of spoken monologues and, more speciically, on the various ways in which the generation of an utterance at a given point in the monologue requires modeling of the linguistic context of the utterance. Zusammenfassung In diesem Artikel wird das Dial-Your-Disc (dyd) System vorgestellt. Dieses interaktive System unterst} utzt den Benutzer beim Durchsuchen einer grossen Datenbank mit Informationen } uber Musikkompositionen. Nach Auswahl einer Komposition erzeugt das System einen gesprochenen Monolog. Dieser Artikel konzentriert sich auf die Erzeugung gesprochener Monologe. Insbeson-dere wird besprochen, in welcher Weise die Erzeugung einer } Ausserung je nach ihrer Position im Monolog es erfordert, den linguistischen Kontext der } Ausserung zu modellieren. R esum e Cet article pr esente le syst eme DYD (Dial-Your-Disc/Choisissez votre disque), qui comprend entre autres la fonction de recherche dans une grande base de donn ees, et celle de g en eration d'un monologue sous forme vocale, une fois que l'oeuvre musicale a et e s electionn ee. L'article pr esente en d etail la g en eration des monologues, avec un accent particulier sur la n ecessit e de recourir au contexte linguistique de l' enonc e pour eeectuer dii eremment la g en eration en fonction de la position courante dans le monologue.
منابع مشابه
Core Units of Spoken Grammar in Global ELT Textbooks
Materials evaluation studies have constantly demonstrated that there is no one fixed procedure for conducting textbook evaluation studies. Instead, the criteria must be selected according to the needs and objectives of the context in which evaluation takes place. The speaking skill as part of the communicative competence has been emphasized as an important objective in language teaching. The pr...
متن کاملContext Modeling for Language and Speech Generation
This paper discusses the various ways in which the generation of an utterance requires modeling of the linguistic context of the utterance. To illustrate the role of context modeling in monologue generation, the so-called Dial-Your-Disc (DYD) system is presented, which supports browsing through a large database of musical information and generates a spoken monologue once a musical composition h...
متن کاملITRI-03-13 CROCODIAL: Crosslingual Computer-mediated Dialogue
We describe a novel approach to crosslingual dialogue which allows for highly accurate communication of semantically complex content. The approach is introduced through an application in a B2B scenario. We are currently building a browser-based prototype for this scenario. The core technology underlying the approach is natural language generation. We also discuss how the proposed approach can c...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1995