MetaCartSign in to MyCiteSeer

Include Citations | Advanced Search | Help

Include Citations | Advanced Search | Help

  1 Conversational Requirements for Verbmobil

Download:
Download as a PDF | Download as a PS
by G. Gorz, J. Spilker, V. Strom, H. Weber
http://www8.informatik.uni-erlangen.de/IMMD8/Research/vm_papers/bellagio97.ps.gz
Add To MetaCart

Abstract:

is a large German joint research project in the area spontaneous speech-to-speech translation sytems which is sponsored by the German Federal Ministery for Research and Education. In its first phase (1992--1996) ca. 30 research groups in universities, research institutes and industry were involved, and it entered its second phase in January 1997. The overall goal is develop a system which supports face-to-face negotiation dialogues about the scheduling of meetings as its first domain, which will be enlarged to more general scenarios during the second project phase. For the dialogue situation it is assumed that two speakers with different mother tongues (German and Japanese) have some common knowledge of English. Whenever a speaker's knowledge of English is not sufficient, the Verbmobil system will serve him as a speech translation device to which he can talk in his native language. So, Verbmobil is a system providing assistance in conversations as opposed to fully automatic conversational systems. Of course, it can be used to translate complete dialogue turns. Both types of conversational systems share a lot of common goals, in particular utterance understanding--- at least as much as is required to produce a satisfacory translation---, processing of spontaneous speech phenomena, speech generation, and robustness in general. A difference can be seen in

Citations

122 A cache-based natural language model for speech recognition – Kuhn, Mori - 1990
43 Improvements In Part-of-Speech Tagging With an Application To German – Schmid - 1995
22 Algorithms for Bigram and Trigram Word Clustering – Martin, Liermann, et al. - 1995
22 Detection of accents, phrase boundaries and sentence modality in German with Prosodic Features – Strom - 1995
21 An investigation of tightly coupled time synchronousspeech language interfacesusing a unification grammar – HAUENSTEIN, WEBER - 1994
14 LR-inkrementelles probabilistisches Chartparsing von Worthypothesenmengen mit Unifikationsgrammatiken: Eine enge Kopplung von Suche und Analyse – Weber - 1995
12 ICE -- INTARC Communication Environment User Guide and Reference Manual Version 1.4 – Amtrup - 1995
11 Time synchronous chart parsing of speech integrating unification grammars with statistics – Weber - 1994
10 Improving language models by clustering training sentences – Carter - 1994
10 From word hypotheses to logical form: An efficient interleaved approach – Kasper, Krieger, et al. - 1996
9 Strategies for focal accent detection in spontaneous speech – Petzold - 1995
6 An extended clustering algorithm for statistical language models – Ueberla - 1994
5 Communication in Large distributed AI Systems for Natural Language Processing – Amtrup, Benra - 1996
5 integration of Prosodic and Grammatical Information in the Analysis of Dialogs – Kasper, Krieger - 1996
5 Modularizing codescriptive grammars for efficient parsing – Kasper, Krieger - 1996
5 Parsing n best trees from a word lattice – Weber, Spilker, et al. - 1997
3 The Treatment of Compounds in a morphological component for speech recognition. Verbmobil Report (to appear – Althoff, Drexel, et al. - 1996
2 What's in the `pure' prosody – Strom - 1996
1 The parallel timesynchronous speech-to-speech system INTARC 2.0 – Amtrup, Drexel, et al.