Jörg Spilker

The Recognition of Emotion

To detect emotional user behavior, particularly anger, can be very useful for successful automatic dialog processing. We present databases and prosodic classifiers implemented for the recognition of emotion in Verbmobil. Using a prosodic feature vector alone is, however, not sufficient for the modelling of emotional user behavior. Therefore, a module is described that combines several knowledge sources within an integrated classification of trouble in communication.

Processing self corrections in a speech to speech system

Speech repairs occur often in spontaneous spoken dialogues. The ability to detect and correct those repairs is necessary for any spoken language system. We present a framework to detect and correct speech repairs where all relevant levels of information, i. e., acoustics, lexis, syntax and semantics can be integrated. The basic idea is to reduce the search space for repairs as soon as possible by cascading filters that involve more and more features. At first an acoustic module generates hypotheses about the existence of a repair. Second a stochastic model suggests a correction for every hypothesis. Well scored corrections are inserted as new paths in the word lattice. Finally a lattice parser decides on accepting the repair.

Research on architectures for integrated speech/language systems in Verbmobil

The German joint research project Verbmobil (VM) aims at the development of a speech to speech translation system. This paper reports on research done in our group which belongs to Verbmobils subproject on system architectures (TP15). Our specific research areas are the construction of parsers for spontaneous speech, investigations in the parallelization of parsing and to contribute to the development of a flexible communication architecture with distributed control.

Combining Analyses from Various Parsers

This chapter describes measures implemented in the semantics module to ensure that best use is made of the available linguistic analyses.

Parsing N Best Trees from a Word Lattice

This article describes a probabilistic context free grammar approximation method for unification grammars. In order to produce good results, the method is combined with an N best parsing extension to chart parsing. The first part of the paper introduces the grammar approximation method, while the second part describes details of an efficient N-best packing and unpacking scheme for chart parsing.

Architectural Considerations for Conversational Systems

Verbmobil1 is a large German joint research project in the area spontaneous speech-to-speech translation systems which is sponsored by the German Federal Ministry 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.

Some recognition results for INTARC 2.0

This report presents some word recognition results on the speech-to-speech translation system INTARC 2.0. Our research goal was to build a system with a cognitive oriented architecture. The main topics are incremental, time-synchronous and interactive processing. All modules work on the same time segment processing the signal from left to right. Analyses - even partial ones - are passed as soon as possible. Figure 1 shows the overall structure of the system. Details of the architecture of parts of INTARC 2.0 can be found in [1]1 .