Intelligent Systems Group, (2008)
Abstract. Major aspects of cognitive science are based on natural language processing utilizing automatic speech recognition (ASR) systems in scenarios of human-computer interaction. In order to...
Adapted Random Subspace Sampling for Automatic Classification of NMR Data (2008)
Kai Lienemann, Thomas Plötz, Gernot A. Fink
Abstract. We present an approach for the automatic classification of Nuclear Magnetic Resonance Spectroscopy data of biofluids with respect to drug induced organ toxicities. Classification is...
Jan Richarz, Thomas Plötz, Gernot A. Fink
Image structure and color are those two cues that are most frequently used in image interpretation and computer vision tasks. However, both have weaknesses if applied separately. Fusing the...
Modality Integration and Dialog Management for a Robotic Assistant (2008)
Ioannis Toptsis Axel, Axel Haasch, Sonja Hüwel, Jannik Fritsch, Gernot A. Fink
The communication with robotic assistants or companions is a challenging new domain for the use of dialog systems. In contrast to classical spoken language interfaces users interact with mobile...
ABSTRACT to appear. Providing the Basis for Human-Robot-Interaction: (2007)
Sebastian Lang, Marcus Kleinehagenbrock, Sascha Hohenner, Jannik Fritsch, Gernot A. Fink, Gerhard Sagerer
In order to enable the widespread use of robots in home and office environments, systems with natural interaction capabilities have to be developed. A prerequisite for natural interaction is the...
empty ; A = A = A ; empty (2007)
Christel Brindopke, Gernot A. Fink, Franz Kummert, Gerhard Sagerer
This paper presents an HMM-based recognition system for perceptive relevant pitch movements of spontaneous German speech. The pitch movements are defined according to the perceptively and...
A HYBRID SPEECH RECOGNIZER COMBINING HMMS AND POLYNOMIAL CLASSIFICATION (2007)
Franz Kummert, Gernot A. Fink, Gerhard Sagerer
In this paper, we present a hybrid speech recognizer combining Hidden Markov Models (HMMs) and a polynomial classifier. In our approach the emission probabilities are not modeled as a mixture of...
A FLEXIBLE FORMAL LANGUAGE FOR THE ORTHOGRAPHIC TRANSCRIPTION OF SPONTANEOUS SPOKEN DIALOGUES (2007)
Gernot A. Fink, Michaela Johanntokrax, Brigitte Schaffranietz
Orthographic transcriptions of speech are important in most fields of research concerned with spoken language. For spontaneous speech they have to be created manually, resulting potentially in...
MODELING OF TIME CONSTITUENTS FOR SPEECH UNDERSTANDING (2007)
Bernd Hildebr, Gernot A. Fink, Franz Kummert, Gerhard Sagerer
The analysis and interpretation of time constituents is important for most applications of speech understanding systems. Problems can be caused by the varying distribution of constituents. A basic...
UNDERSTANDING OF TIME CONSTITUENTS IN SPOKEN LANGUAGE DIALOGUES (2007)
Bernd Hildebr, Gernot A. Fink, Franz Kummert, Gerhard Sagerer
The analysis and interpretation of time constituents is a rather complex enterprise, since diverse time constituents are distributable in variable positions within an utterance. The first step in...
Gernot A. Fink, Nils Jungclaus, Helge Ritter, Gerhard Sagerer
Unlike in traditional approaches to parallel or distributed processing where normally well structured problems are implemented completely in some programming environment we are faced with the problem...
Influence of duration on static and dynamic properties of German vowels in spontaneous speech (2007)
Britta Wrede, Gernot A. Fink, Gerhard Sagerer
Changes in speech rate severely affect the performance of continuous speech recognition systems. In order to better understand the underlying effects of speech rate changes an analysis was carried...
An investigation of modelling aspects for rate-dependent speech recognition (2007)
Britta Wrede, Gernot A. Fink, Gerhard Sagerer
For the modelling of speech rate variation in speech recognition many approaches have been suggested. However, the training of speech-rate dependent models has by far received most of the attention....
Forward masking for increased robustness in automatic speech recognition (2007)
Sascha Wendt, Gernot A. Fink, Franz Kummert
In automatic speech recognition mel-frequency cepstral coefficients (MFCC) or linear predictive cepstral coefficients (LPCC) are features commonly used today. However, their calculation considers...
A Handwriting Recognition System Based on Visual Input (2007)
Markus Wienecke, Gernot A. Fink, Gerhard Sagerer
2001 IEEE. Personal use of this material is permitted.However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or...
Flexible Formal Language, Gernot A. Fink, Michaela Johanntokrax, Brigitte Schaffranietz
Orthographic transcriptions of speech are important in most fields of research concerned with spoken language. For spontaneous speech they have to be created manually, resulting potentially in...
Fink, Gernot A., Plötz, Thomas
The performance of writer-independent unconstrained handwriting recognition is severely affected by variations in writing style. In a segmentation-free approach based on Hidden-Markov models we,...
Fink, Gernot A., Plötz, Thomas
The performance of writer-independent unconstrained handwriting recognition is severely affected by variations in writing style. In a segmentation-free approach based on Hidden-Markov models we,...
Fink, Gernot A., Plötz, Thomas
The performance of writer-independent unconstrained handwriting recognition is severely affected by variations in writing style. In a segmentation-free approach based on Hidden-Markov models we,...
Fink, Gernot A., Plötz, Thomas
The performance of writer-independent unconstrained handwriting recognition is severely affected by variations in writing style. In a segmentation-free approach based on Hidden-Markov models we,...
Fink, Gernot A., Plötz, Thomas
The performance of writer-independent unconstrained handwriting recognition is severely affected by variations in writing style. In a segmentation-free approach based on Hidden-Markov models we,...
Robust Remote Homology Detection by Feature Based Profile Hidden Markov Models (2005)
Plötz, Thomas, Fink, Gernot A.
The detection of remote homologies is of major importance for molecular biology applications like drug discovery. The problem is still very challenging even for state-of-the-art probabilistic models...
Robust Remote Homology Detection by Feature Based Profile Hidden Markov Models (2005)
Plötz, Thomas, Fink, Gernot A.
The detection of remote homologies is of major importance for molecular biology applications like drug discovery. The problem is still very challenging even for state-of-the-art probabilistic models...
Robust Remote Homology Detection by Feature Based Profile Hidden Markov Models (2005)
Plötz, Thomas, Fink, Gernot A.
The detection of remote homologies is of major importance for molecular biology applications like drug discovery. The problem is still very challenging even for state-of-the-art probabilistic models...
Robust Remote Homology Detection by Feature Based Profile Hidden Markov Models (2005)
Plötz, Thomas, Fink, Gernot A.
The detection of remote homologies is of major importance for molecular biology applications like drug discovery. The problem is still very challenging even for state-of-the-art probabilistic models...
Towards Automatic Video-based Whiteboard Reading (2005)
Markus Wienecke Gernot, Gernot A. Fink, Gerhard Sagerer
As whiteboards have become a popular tool in meeting rooms, there has been a growing interest in making use of the whiteboard as a user interface for human computer interaction. Therefore, systems...
A Multi-modal Dialog System for a Mobile Robot (2004)
Ioannis Toptsis Shuyin, Ioannis Toptsis, Shuyin Li, Britta Wrede, Gernot A. Fink
A challenging domain for dialog systems is their use for the communication with robotic assistants. In contrast to the classical use of spoken language for information retrieval, on a mobile robot...
Mustererkennung mit Markov-Modellen : Theorie, Praxis, Anwendungsgebiete / (2003)
Zugl.: Bielefeld, Universiẗat, Habil.-Schr., 2003.
Towards Faster Profile HMM Evaluation (2003)
Thomas Plotz And, Thomas Plotz, Gernot A. Fink
es computing the classification scores of multiple models for the target sequences. Since the evaluation is usually performed sequentially, which means the scores for each model are calculated...
Data-driven Pronunciation Modeling for ASR using Acoustic Subword Units (2003)
Thurid Spiess, Britta Wrede, Gernot A. Fink, Franz Kummert
We describe a method to model pronunciation variation for ASR in a data-driven way, namely by use of automatically derived acoustic subword units. The inventory of units is designed so as to produce...
Sebastian Lang, Marcus Kleinehagenbrock, Sascha Hohenner, Jannik Fritsch, Gernot A. Fink, Gerhard Sagerer
In order to enable the widespread use of robots in home and office environments, systems with natural interaction capabilities have to be developed. A prerequisite for natural interaction is the...
Must Be Obtained, Markus Wienecke, Gernot A. Fink, Gerhard Sagerer
As whiteboards have become a popular tool in meeting rooms, there has been a growing interest in making use of the whiteboard as a user interface for human computer interaction. Therefore, systems...
Dynamic search-space pruning for time-constrained speech recognition (2002)
Sascha Wendt, Gernot A. Fink, Franz Kummert
In automatic speech recognition complex state spaces are searched during the recognition process. By limiting these search spaces the computation time can be reduced, but unfortunately the...
In this paper we describe system architectures for robust MLLR based environmental adaptation of continuous speech recognition systems. Inspired by an existing broadcast news transcription system [1]...
Experiments in unconstrained offline handwritten text recognition (2002)
Must Be Obtained, Markus Wienecke, Gernot A. Fink, Gerhard Sagerer
A system for off-line handwritten text recognition is presented. It is characterized by a segmentation-free approach, i.e. whole lines of text are processed by the recognition module. The methods...
Video-based on-line handwriting recognition (2001)
Gernot A. Fink, Markus Wienecke, Gerhard Sagerer
IEEE. Personal use of this material is permitted.However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or...
Video-based on-line handwriting recognition (2001)
Gernot A. Fink, Markus Wienecke, Gerhard Sagerer
2001 IEEE. Personal use of this material is permitted.However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or...
Using speech in visual object recognition (2000)
Sven Wachsmuth, Gernot A. Fink, Franz Kummert, Gerhard Sagerer
Springer-Verlag Heidelberg. Permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or...
Conversational speech recognition using acoustic and articulatory input (2000)
Katrin Kirchhoff, Gernot A. Fink, Gerhard Sagerer, Ag Angewandte Infoxnatik
The combination of multiple speech recognizers based on different speech signal representations is increasingly attracting interest in the speech community. In previous work we presented a hybrid...
Grapheme based speech recognition for large vocabularies (2000)
Christoph Schillo, Gernot A. Fink, Franz Kummert
Common speech recognition systems use phonetically motivated subword units. To utilize words in these systems, one has to translate the available graphemic word representation into a phonetic one. To...
Christel Brindopke, Gernot A. Fink, Franz Kummert
Three approaches to the speaker independent automatic recognition of melodic aspects of spontaneous German are presented. All systems are based on Hidden Markov Models. Their input is restricted to...
Integrated Recognition and Interpretation of Speech for a Construction Task Domain (1999)
Hans Brandt-Pook, Hans Br, Gernot A. Fink, Sven Wachsmuth, Gerhard Sagerer, ...
this paper a technique that tightly couples the speech recogniser and the speech understanding. We first give an overview of the system architecture and then we focus on the language modelling and...
Christel Brindöpke, Gernot A. Fink, Franz Kummert
Three approaches to the speaker independent automatic recognition of melodic aspects of spontaneous German are presented. All systems are based on Hidden Markov Models. Their input is restricted to...
Christel Brindöpke, Gernot A. Fink, Franz Kummert, Gerhard Sagerer
This paper presents an HMM-based recognition system for perceptive relevant pitch movements of spontaneous German speech. The pitch movements are defined according to the perceptively and...
Integration Of Parsing And Incremental Speech Recognition (1998)
Sven Wachsmuth, Gernot A. Fink, Gerhard Sagerer
In this paper we propose a new approach to integrating a parser into a statistical speech recognizer. The method is able to incrementally apply grammatical restrictions and robustly combine them with...
A distributed system for integrated speech and image understanding (1996)
Gernot A. Fink, Nils Jungclaus, Franz Kummert, Helge Ritter, Gerhard Sagerer
Most published work in the field of pattern analysis, in our opinion, underestimates the importance of system architecture or system development. When building large distributed systems both become a...
A Hybrid Approach to Identifying Objects from Verbal Descriptions (1996)
Gudrun Socher, Gernot A. Fink, Franz Kummert, Gerhard Sagerer
In this paper we present a hybrid approach for the identification of objects in a scene from spoken verbal descriptions. An integrated knowledge base realized by a semantic network is used to build...
A Distributed System For Integrated Speech And Image Understanding (1996)
Gernot A. Fink, Nils Jungclaus, Franz Kummert, Helge Ritter, Gerhard Sagerer
Most published work in the field of pattern analysis, in our opinion, underestimates the importance of system architecture or system development. When building large distributed systems both become a...
A Hybrid Approach to Identifying Objects from Verbal Descriptions (1996)
Gudrun Socher, Gernot A. Fink, Franz Kummert, Gerhard Sagerer
In this paper we present a hybrid approach for the identification of objects in a scene from spoken verbal descriptions. An integrated knowledge base realized by a semantic network is used to build...
Postfach 100131, 33501 Bielefeld, Germany (1996)
Email Gernot, Gernot A. Fink, Nils Jungclaus, Franz Kummert, Helge Ritter, Gerhard Sagerer
Most published work in the field of pattern analysis, in our opinion, underestimates the importance of system architecture or system development. When building large distributed systems both become a...
A Communication Framework for Heterogeneous Distributed Pattern Analysis (1995)
Gernot A. Fink, Nils Jungclaus, Helge Ritter, Gerhard Sagerer
Unlike in traditional approaches to parallel or distributed processing where normally well structured problems are implemented completely in some programming environment we are faced with the problem...
Generation Of Language Models Using The Results Of Image Analysis (1995)
Uta Naeve, Gudrun Socher, Gernot A. Fink, Franz Kummert, Gerhard Sagerer
We present a new approach towards using contextual information to enhance speech recognition and understanding. Dynamically inferred knowledge about the context is used in addition to the static...
Integration von Spracherkennung und Sprachverstehen / (1995)
Zugl.: Bielefeld, Universiẗat, Diss., 1995.
Robust interpretation of speech (1993)
Gernot A. Fink, Franz Kummert, Gerhard Sagerer, Bernd Seestaedt
In all fields of pattern recognition there may arise situations where severe distortions of the sensor data or errors of processing prevent a successful analysis. This is especially true in speech...
Speech Recognition using Semantic Hidden Markov Models (1993)
Gernot A. Fink, Franz Kummert, Gerhard Sagerer
Semantic Hidden Markov Networks (SHMNs) were first introduced in [2] as a new technique of interfacing between linguistic analysis and word recognition in speech understanding systems. The main...