Ernst Günter Schukat-Talamazzini

Learn More
This paper presents automatic methods for the segmenta-tion and classication of dialog acts (DA). In Verbmobil it is often sucient to recognize the sequence of DAs occurring during a dialog between the two partners. Since a turn can consist of one or more successive D As we conduct the classication of DAs in a two step procedure: First each turn has to be(More)
A method for the oo-line recognition of cursive handwriting based on Hidden Markov Models (HMMs) is described. The features used in the HMMs are based on the arcs of skeleton graphs of the words to be recognized. An average correct recognition rate of over 98% on the word level has been achieved in experiments with cooperative writers using two dictionaries(More)
In this paper we present two new techniques for language modeling in speech recognition. The rst technique is based on ergodic discrete density Hidden Markov Models (HMM) which can be applied to bigrams based on word categories. This statistical approach of the so-called Markov bigrams enables an eecient unsupervised learning procedure for the bigram(More)
Prosodic boundary detection is important to disam-biguate parsing, especially in spontaneous speech, where elliptic sentences occur frequently. Word graphs are an eecient interface between word recognition and parser. Prosodic classiication of word chains has been published earlier. The adjustments necessary for applying these classiication techniques to(More)
This paper focuses on the evaluation of the German Sundial Demonstrator maintaining interactive conversations via microphone and telephone with users. The word recognizer was implemented by the University of Erlangen and currently obtains on our test set a word accuracy of over 92% in a speaker{independent task with perplexity 111. We also participated in(More)
This paper presents automatic methods for the classiication of dialog acts. In the verbmobil application (speech-to-speech translation of face-to-face dialogs) maximally 50 % of the utterances are analyzed in depth and for the rest, shallow processing takes place. The dialog component keeps track of the dialog with this shallow processing. For the(More)
In our paper, we address the problem of estimating stochastic language models based on n-gram statistics. We present a novel approach, rational interpolation, for the combination of a competing set of conditional n-gram word probability predictors, which consistently outper-forms the traditional linear interpolation scheme. The superiority of rational(More)