Anton Batliner, Richard Huber, Heinrich Niemann, Elmar Noth, Jorg Spilker, Kerstin Fischer
Abstract. 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...
Automatic Pixel Selection for Optimizing Facial Expression Recognition using Eigenfaces (2007)
Abstract. A new direction in improving modern dialogue systems is to make a human-machine dialogue more similar to a human-human dialogue. This can be done by adding more input modalities, e.g....
Comparison and Combination of Confidence Measures (2007)
Georg Stemmer, Stefan Steidl, Elmar Noth, Heinrich Niemann
Abstract. A set of features for word-level confidence estimation is developed. The features should be easy to implement and should require no additional knowledge beyond the information which is...
A Segment Based Approach for Prosodic Boundary Detection (2007)
Volker Warnke, Elmar Noth, Heinrich Niemann, Georg Stemmer
Abstract. Successful detection of the position of prosodic phrase boundaries is useful for the rescoring of the sentence hypotheses in a speech recognition system. In addition, knowledge about...
Towards a Dynamic Adjustment of the Language (2007)
Georg Stemmer, Viktor Zeissler, Elmar Noth, Heinrich Niemann
Abstract. Most speech recognition systems use a language weight to reduce the mismatch between the language model and the acoustic models. Usually a constant value of the language weight is chosen...
Anton Batliner, Anke Feldhaus, Stefan Geiler, Andreas Kieling, Ralf Kompe, Elmar Noth, ...
We describe a number of experiments that demonstrate the usefulness of prosodic information for a processing module which parses spoken utterances with a feature-based grammar employing empty...
Uwe Ohler, Stefan Harbeck, Heinrich Niemann, Elmar Noth, Martin G. Reese
Motivation: We describe a new content based approach for the detection of promoter regions of eukaryotic protein encoding genes. Our system is based on three interpolated Markov chains (IMCs) of...
Elmar Noth, Manuela Boros, Jurgen Haas, Volker Warnke, Florian Gallwitz
Linguistic processing in spoken dialogue systems has to be robust against a large number of phenomena such as recognizer errors, spontaneous speech phenomena and out-of-vocabulary (OOV) words. A...
Andreas Kieling, Ralf Kompe, Anton Batliner, Heinrich Niemann, Elmar Noth
In this paper a method for the automatic labeling of phrase accents is described, based on a large text corpus that has been generated automatically and read by 100 speakers. Perception experiments...
Real Users Behave Weird--- Experiences made collecting large (2007)
Wieland Eckert, Elmar Noth, Heinrich Niemann
We have built a demonstrator for spoken human--machine dialogs. The system is capable to answer inquiries about the InterCity train timetable of the Deutsche Bahn. It evolved from the work done in...
: (kuhn OR lazarids OR norman OR (2007)
Ariane Lazarides, Yves Norm, Julie Brousseau, Elmar Noth
This paper describes decision tree methodology and shows how it has been adapted to three different problems in speech recognition and understanding at CRIM and at FORWISS. The three problems are: 1....
Optimizing Eigenfaces by Face Masks for Facial Expression Recognition (2007)
Abstract. A new direction in improving modern dialogue systems is to make a human-machine dialogue more similar to a human-human dialogue. This can be done by adding more input modalities. One...
Speech Recognition with -Law Companded (2003)
Features On Reverberated, Tino Haderlein, Georg Stemmer, Elmar Noth
One of the goals of the EMBASSI project is the creation of a speech interface between a user and a TV set or VCR. The interface should allow spontaneous speech recorded by microphones far away from...
Prosodic Classification of Offtalk: First Experiments (2002)
Anton Batliner, Viktor Zeier, Elmar Noth, Heinrich Niemann
Abstract. SmartKom is a multi-modal dialogue system which combines speech with gesture and facial expression. In this paper, we want to deal with one of those phenomena which can be observed in such...
Mobsy: Integration of vision and dialogue in service robots (2001)
Matthias Zobel, Matthias Zobel, Joachim Denzler, Joachim Denzler, Benno Heigl, Benno Heigl, ...
Abstract. MOBSY is a fully integrated autonomous mobile service robot system. It acts as an automatic dialogue based receptionist for visitors of our institute. MOBSY incorporates many techniques...
How to Repair Speech Repairs in an End-to-End System (2001)
Jorg Spilker, Anton Batliner, Elmar Noth
If automatic speech processing wants to deal with spontaneous speech, it has to deal with disfluencies in general and speech repairs in particular as well. The paper describes the processing of...
Georg Stemmer, Elmar Noth, Heinrich Niemann
Abstract. Information about the dialogue-state can be integrated into language models to improve performance of the speech recognizer in a dialogue system. A dialogue state is defined in this paper...
Anton Batliner, Jan Buckow, Heinrich Niemann, Elmar Noth, Volker Warnke
Abstract. We describe the acoustic-prosodic and syntactic-prosodic annotation and classification of boundaries, accents and sentence mood integrated in the Verbmobil system for the three languages...
Prosodic Feature Evaluation: Brute Force or Well Designed (1999)
Anton Batliner, Jan Buckow, Richard Huber, Volker Warnke, Elmar Noth, Heinrich Niemann
In this paper we want to bridge the gap between phonetic /phonological theory on the one hand and automatic speech processing on the other hand. As material, we use a subset of the German VERBMOBIL...
Stefan Harbeck, Elmar Noth, Heinrich Niemann
Abstract. The multilingual speech recognizer implemented inside the SQEL Copernicus project is based on a combination of several monolingual recognizer within one recognizer using a special bigram...
A Concept for a Prosodically and Statistically Driven Chunky Semantic Parser (1998)
Jurgen Haas, Manuela Boros, Elmar Noth, Volker Warnke, Heinrich Niemann
Abstract. In spoken dialog systems typically just a small set of predefined information has to be provided to the system in order to accomplish its task. We present here a concept for a partial...
Semantigrams -- Polygrams Detecting Meaning (1997)
Jurgen Haas, Elmar Noth, Heinrich Niemann
Abstract. In this paper we present a statistical approach to shallow linguistic analysis of word chains modeled with probabilistic methods. We reduce the linguistic analysis to the problem of...
Semantic Processing Of Out-Of-Vocabulary Words In A Spoken Dialogue System (1997)
Manuela Boros, Maria Aretoulaki, Florian Gallwitz, Elmar Noth, Heinrich Niemann
One of the most important causes of failure in spoken dialogue systems is usually neglected: the problem of words that are not covered by the system's vocabulary (out-of-vocabulary or OOV...
Automatic classification of dialog acts with semantic classification trees and polygrams (1996)
Marion Mast, Heinrich Niemann, Elmar Noth, Ernst Gunter
Abstract. This paper presents automatic methods for the classification of dialog acts. In the verbmobil application (speech-to-speech translation of face-to-face dialogs) maximally 50 % of the...
Prosodic Modules for Speech Recognition and Understanding in VERBMOBIL (1996)
Wolfgang Hess Anton, Anton Batliner, Andreas Kiefiling, Ralf Kompe, Elmar Noth, Anja Petzold, ...
Within VERBMOBIL, a large project on spoken language research in Germany, two modules for detecting and recognizing prosodic events have been developed. One module operates on speech signal...
Prosodic Modules for Speech Recognition and Understanding in VERBMOBIL (1996)
Wolfgang Hess, Wolfgang Hess, Anton Batliner, Anton Batliner, Anton Batliner, Andreas Kiessling, ...
Within VERBMOBIL, a large project on spoken language research in Germany, two modules for detecting and recognizing prosodic events have been developed. One module operates on speech signal...
Integrating Syntactic and Prosodic Information for the Efficient Detection of Empty Categories
Anke Feldhaus, Stefan Geiler, Andreas Kieling, Ralf Kompe, Elmar Noth, Anton Batliner, ...
We describe a number of experiments that demonstrate the usefulness of prosodic information for a processing module which parses spoken utterances with a feature-based grammar employing empty...