Shallow ProcessingDeep Processing Synthesis SynthesisTransfer Prosodic - Generation Recording Dialogue Processing EnglishEnglish Generation German German
نویسنده
چکیده
In this paper we show how the notion of context has been reened in order to fullll the requirements posed by a natural language processing system. We describe the context model of the speech translation system verbmobil which has been derived from constraints given by various subcomponents of the system. In verbmo-bil context is stored in the dialogue memory which is incrementally constructed by the dialogue processing component. We describe our model of context and give examples for its representation. We also relate our model to state of the art approaches in theoretical and computational linguistics.
منابع مشابه
Deep Processing Shallow Processing Generation German Synthesis
verbmobil, a speech to speech translation system, poses new and challenging tasks for a dialogue component. We present a part of the dialogue component of verbmobil: a robust plan recognizer that processes all of the over 200 dialogues of the verb-mobil corpus. The recognizer currently handles unexpected sequences of input, and will in the future deal with multiple input, hypotheses, and incomp...
متن کاملUsing an HPSG grammar for the generation of prosodic structures
In this paper, we report on an experiment showing how the introduction of prosodic information from detailed syntactic structures into synthetic speech leads to better disambiguation of structurally ambiguous sentences. Using modifier attachment (MA) ambiguities and subject/object fronting (OF) in German as test cases, we show that prosody which is automatically generated from deep syntactic in...
متن کاملMultilingual Generation for Translation in Speech-to-Speech Dialogues and its Realization in Verbmobil
This paper presents the generation module of the speech-to-speech dialogue translation system Verbmobil. Spontaneous speech, large multilingual vocabulary, difficulty of the translation task, robustness and real-time constraints make the design of such a module very challenging. In order to overcome these difficulties, we have developed a system based on a general kernel and the declarativity o...
متن کاملLinguistic-prosodic processing for text-to-speech synthesis in italian
The linguistic-prosodic processing applied to text-to-speech synthesis in Italian is described. It proceeds in 5 steps: tokenisation and normalisation of abbreviations, numbers, etc.; part-of-speech tagging, based on function words, terminations and contextual heuristics; shallow parsing, based on a chunk grammar; grapheme-to-phoneme conversion, lexical stress assignment and syllabification by ...
متن کاملResearch Issues for the Next Generation
In this paper we present extensions to the spoken dialogue system EVAR which are crucial issues for the next generation dialogue systems. EVAR was developed at the University of Erlangen. In 1994, it became accessible over telephone line and could answer inquiries in the German language about German InterCity train connections. It has since been continuously improved and extended, including som...
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