Björn Schuller, Martin Wöllmer, Tobias Moosmayr, Gerhard Rigoll
Performance of speech recognition systems strongly degrades in the presence of background noise, like the driving noise inside a car. In contrast to existing works, we aim to improve noise robustness...
Robust Appearance-based Sign Language Recognition Von der Fakultät für Mathematik, Informatik (2008)
Und Naturwissenschaften, Gerhard Rigoll, ...
online verfügbar. To my family In this work, we introduce a robust appearance-based sign language recognition system which is derived from a large vocabulary speech recognition system. The system...
Daniel Mllett, Christoph Neukirchen, Joe Rottl, Gerhard Rigoll
Decision tree-based state clustering has emerged in recent years as the most popular approach for clustering the states of context dependent hidden Markov model based speech recognizers. The...
LOW-LEVEL FUSION OF AUDIO AND VIDEO FEATURE FOR MULTI-MODAL EMOTION RECOGNITION (2008)
Matthias Wimmer, Björn Schuller, Dejan Arsic, Gerhard Rigoll, Bernd Radig
Abstract: Bimodal emotion recognition through audiovisual feature fusion has been shown superior over each individual modality in the past. Still, synchronization of the two streams is a challenge,...
Audio-Visual Processing in Meetings: Seven Questions and Some AMI Answers (2008)
Marc Al-hames, Thomas Hain, Jan Cernocky, Sascha Schreiber, Mannes Poel, Ronald Müller, ...
Abstract. The project Augmented Multi-party Interaction (AMI) is concerned with the development of meeting browsers and remote meeting assistants for instrumented meeting rooms – and the required...
Gregor Mcglaun, Frank Althoff, Manfred Lang, Gerhard Rigoll
This work describes two video-based approaches for detecting and classifying dynamic head-gestures. We compare a simple, fast, and efficient rule-based algorithm with a powerful, robust, and flexible...
Controlling the Complexity of HMM Systems by (2008)
Christoph Neukirchen, Gerhard Rigoll
This paper introduces a method for regularization of HMM systems that avoids parameter overfitting caused by insufficient training data. Regularization is done by augmenting the EM training method by...
Sensing Technologies and the Player-Middleware for Context-Awareness in Kitchen Environments (2008)
Matthias Kranz, Albrecht Schmidt, Benedikt Hörnler, Gerhard Rigoll
Abstract — In this paper we report on a use case of networked sensing technologies in the context of smart homes and specifically the kitchen as scenario for our research. We adapt, use and extend...
Video Indexing Using Face Detection and Face Recognition Methods (2008)
Stefan Eickeler, Stefan Müller, Gerhard Rigoll
This paper presents a video indexing approach, that combines face detection and face recognition. The frames of the video sequences are scanned for faces by a Neural Network based face detector and...
Audio-Visual Processing in Meetings: Seven Questions and Current AMI Answers (2008)
Marc Al-hames, Thomas Hain, Jan Cernocky, Sascha Schreiber, Mannes Poel, Ronald Müller, ...
Abstract. The project Augmented Multi-party Interaction (AMI) is concerned with the development of meeting browsers and remote meeting assistants for instrumented meeting rooms – and the required...
Combining Frame and Turn-Level Information for Robust Recognition of Emotions within Speech (2008)
Bogdan Vlasenko, Björn Schuller, Andreas Wendemuth, Gerhard Rigoll
Current approaches to the recognition of emotion within speech usually use statistic feature information obtained by application of functionals on turn- or chunk levels. Yet, it is well known that...
Bogdan Vlasenko, Björn Schuller, Andreas Wendemuth, Gerhard Rigoll
Abstract. Opposing the pre-dominant turn-wise statistics of acoustic Low-Level-Descriptors followed by static classification we re-investigate dynamic modeling directly on the frame-level in...
Audio-Visual Processing in Meetings: Seven Questions and Current AMI Answers (2008)
Marc Al-hames, Thomas Hain, Jan Cernocky, Sascha Schreiber, Mannes Poel, Ronald Müller, ...
Abstract. The project Augmented Multi-party Interaction (AMI) is concerned with the development of meeting browsers and remote meeting assistants for instrumented meeting rooms – and the required...
Tango or Waltz?: Putting Ballroom Dance Style into Tempo Detection (2008)
Björn Schuller, Florian Eyben, Gerhard Rigoll
Rhythmic information plays an important role in Music Information Retrieval. Example applications include automatically annotating large databases by genre, meter, ballroom dance style or tempo,...
Multiple Camera Person Tracking in Multiple Layers Combining 2D and 3D Information (2008)
Arsié, Dejan, Schuller, Björn, Rigoll, Gerhard
CCTV systems have been introduced in most public spaces in order to increase security. Video outputs are observed by human operators if possible but mostly used as a forensic tool. Therefore it seems...
Multiple Camera Person Tracking in Multiple Layers Combining 2D and 3D Information (2008)
Arsié, Dejan, Schuller, Björn, Rigoll, Gerhard
CCTV systems have been introduced in most public spaces in order to increase security. Video outputs are observed by human operators if possible but mostly used as a forensic tool. Therefore it seems...
Tango or Waltz?: Putting Ballroom Dance Style into Tempo Detection (2008)
Björn Schuller, Florian Eyben, Gerhard Rigoll
Rhythmic information plays an important role in Music Information Retrieval. Example applications include automatically annotating large databases by genre, meter, ballroom dance style or tempo,...
Jan Stadermann, Jörg Rottland, J Org Rottl, Gerhard Rigoll
This paper presents a new method for estimating the emission probabilities of general hybrid connectionist/HMM recognition systems. Contrary to the traditional hybrid approach, where a neural network...
Performance of the Duisburg Statistical Object Tracker on Test Data for PETS2000 (2007)
Gerhard Rigoll, Stefan Eickeler, Ilhan K. Yalcin
This paper presents the first results obtained from the statistical object tracker developed at Duisburg University for the test data sequence provided by the organizers of the PETS2000 workshop. Our...
Christoph Neukirchen, Gerhard Rigoll
Introduction While Neural Networks (NN) have been very successfully applied to static pattern recognition tasks like image classification, pure NN-speech recognition approaches often perform quite...
A new probabilistic neural network paradigm for dynamic pattern recognition problems is presented in this paper. The approach includes the following innovations: 1) It is based on a self-organizing...
Person-Independent Continuous Online Recognition of Gestures (2007)
Stefan Eickeler, Stefan Müller, Gerhard Rigoll
This paper presents a gesture recognition system based on Hidden Markov Models. It has several user friendly capabilities like person-independent and background independent recognition. It can...
Time Series Classification using Hidden Markov Models and Neural Networks (2007)
Christoph Neukirchen, Gerhard Rigoll
This paper gives a brief overview on statistical classification of time series using Hidden Markov Models. To overcome some limitations and assumptions made in the Hidden Markov Model framework two...
Daniel Willett, Gerhard Rigoll
. In this paper, we focus on a novel NN/HMM architecture for continuous speech recognition. The architecture incorporates a neural feature extraction to gain more discriminative feature vectors for...
Controlling the Complexity of HMM Systems by Regularization (2007)
Christoph Neukirchen, Gerhard Rigoll
This paper introduces a method for regularization of HMM systems that avoids parameter overfitting caused by insufficient training data. Regularization is done by augmenting the EM training method by...
Video Indexing Using Face Detection and Face Recognition Methods (2007)
Stefan Eickeler, Stefan Müller, Gerhard Rigoll
This paper presents a video indexing approach, that combines face detection and face recognition. The frames of the video sequences are scanned for faces by a Neural Network based face detector and...
Efficient Computation Of MMI Neural Networks For Large Vocabulary Speech Recognition Systems (2007)
Jörg Rottland, J Org Rottl, André Lüdecke, Gerhard Rigoll
This paper describes, how to train Maximum Mutual Information Neural Networks (MMINN) in an efficient way, with a new topology. Large vocabulary speech recognition systems, based on a Hybrid...
This paper proposes a new approach for a hybrid connectionistHMM speech recognition system. The system consists of a multi-feature HMM-based recognition module using three different neural networks...
Optimal combination of Neural Networks and discrete statistical pattern classifiers (2007)
Christoph Neukirchen, Gerhard Rigoll
. This paper deals with the problem of combination of Neural Networks (NN) and traditional statistical pattern classifiers. It is shown that a Neural Network can be used to replace the vector...
REDUCED LEXICON TREES FOR DECODING IN A MMI-CONNECTIONIST/HMM SPEECH RECOGNITION SYSTEM (2007)
Christoph Neukirchen, Daniel Willett, Gerhard Rigoll
The presented work deals with the experimental identification of parts in a tree based decoder lexicon, that are more important for decoding efficiency compared to less important lexicon parts. Three...
COMPARISON OF STANDARD AND HYBRID MODELING TECHNIQUES FOR DISTRIBUTED SPEECH RECOGNITION (2007)
Jan Stadermann, Gerhard Rigoll
Distributed speech recognition (DSR) is an interesting technology for mobile recognition tasks where the recognizer is split up into two parts and connected with a transmission channel. We compare...
A DISCRIMINATIVE TRAINING PROCEDURE BASED ON LANGUAGE MODEL AND DICTIONARY FOR LVCSR (2007)
Daniel Willett, Stefan Muller, Gerhard Rigoll
In today's HMM-based speech recognition systems, the parameters are most commonly estimated according to the Maximum Likelihood criterion. Because of limited training data, however,...
Facial Expression Recognition with Pseudo-3D Hidden Markov Models (2007)
Abstract. We introduce a novel approach to gesture recognition, based on Pseudo-3D Hidden Markov Models (P3DHMMs). This technique is capable of integrating spatially and temporally derived features...
Novel Hybrid NN/HMM Modelling Techniques for On-line Handwriting Recognition (2006)
Schenk, Joachim, Rigoll, Gerhard
In this work we propose two hybrid NN/HMM systems for handwriting recognition. The tied posterior model approximates the output probability density function of a Hidden Markov Model (HMM) with a...
Novel Hybrid NN/HMM Modelling Techniques for On-line Handwriting Recognition (2006)
Schenk, Joachim, Rigoll, Gerhard
In this work we propose two hybrid NN/HMM systems for handwriting recognition. The tied posterior model approximates the output probability density function of a Hidden Markov Model (HMM) with a...
Novel Hybrid NN/HMM Modelling Techniques for On-line Handwriting Recognition (2006)
Schenk, Joachim, Rigoll, Gerhard
In this work we propose two hybrid NN/HMM systems for handwriting recognition. The tied posterior model approximates the output probability density function of a Hidden Markov Model (HMM) with a...
Multimodal integration for meeting group action segmentation and recognition (2005)
Marc Al-hames, Alfred Dielmann, Daniel Gatica-perez, Stephan Reiter, Steve Renals, Gerhard Rigoll, ...
Abstract. We address the problem of segmentation and recognition of sequences of multimodal human interactions in meetings. These interactions can be seen as a rough structure of a meeting, and can...
SVC2004 : first international signature verification competition (2004)
Yeung, Dit-Yan, Chang, Hong, Xiong, Yimin, George, Susan, Kashi, Ramanujan, Matsumoto, Takashi, ...
Handwritten signature is the most widely accepted biometric for identity verification.To facilitate objective evaluation and comparison of algorithms in the field of automatic handwritten signature...
SVC2004: First international signature verification competition (2004)
Dit-yan Yeung, Hong Chang, Yimin Xiong, Susan George, Ramanujan Kashi, Takashi Matsumoto, ...
Abstract. Handwritten signature is the most widely accepted biometric for identity verification. To facilitate objective evaluation and comparison of algorithms in the field of automatic handwritten...
Confidence Measures for an Address Reading System (2003)
Anja Brakensiek, Jörg Rottland, Gerhard Rigoll
In this paper the performance of different confidence measures used for an address recognition system are evaluated. The recognition system for cursive handwritten German address words is based on...
Comparing an Innovative 3D and a Standard 2D User Interface for Automotive (2003)
Frank Althoff, Gregor Mcglaun, Manfred Lang, Gerhard Rigoll
In this work we present the results of a comparative user study of two radically different user interfaces for controlling infotainment applications in an automotive environment: a standard 2D...
Content-Based Indexing of Images and Video Using Face Detection and Recognition Methods (2001)
Stefan Eickeler, Frank Wallhoff, Uri Iurgel, Gerhard Rigoll
This paper presents an image and video indexing approach that combines face detection and face recognition methods. Images of a database or frames of a video sequence are scanned for faces by a...
Pseudo 2-dimensional Hidden Markov Models in Speech Recognition (2001)
Steffen Werner, Gerhard Rigoll
In this paper, the usage of pseudo 2-dimensional Hidden Markov Models for speech recognition is discussed. This image processing method should better model the timefrequency structure in speech...
This paper presents a brief description of the ALERT system, which is under development by a consortium working on a research project sponsored by the European Commission. The ALERT system uses...
A continuous density interpretation of discrete HMM systems and MMI-neural networks (2001)
Christoph Neukirchen, Jörg Rottl, Daniel Willett, Gerhard Rigoll, Senior Member
Abstract—The subject of this paper is the integration of the traditional vector quantizer (VQ) and discrete hidden Markov models (HMM) combination in the mixture emission density framework commonly...
Frank Wallhoff, Stefan M Uller, Gerhard Rigoll
Biometrical systems have been the focus of concentrated research efforts in recent years. These systems can be used to identify a person or to grant a person access to something, e.g. a room. Face...
Martha Larson, Daniel Willett, Joachim Köhler, Gerhard Rigoll
This paper proposes a novel combined compound splitting and phrase recombination method that optimizes the composition of the speech recognition lexicon for a given domain. Data-driven compound word...
Unlimited Vocabulary Script Recognition Using Character N-Grams (2000)
Anja Brakensiek, Daniel Willett, Gerhard Rigoll
. In this paper a robust script recognition system is described, which makes use of a language model, that consists of backo character n-grams. The system is based on Hidden Markov Models (HMMs)...
Improved Degraded Document Recognition with Hybrid Modeling Techniques and Character N-Grams (2000)
Anja Brakensiek, Daniel Willett, Gerhard Rigoll
In this paper a robust multifont character recognition system for degraded documents such as photocopy or fax is described. The system is based on Hidden Markov Models (HMMs) using discrete and...
Frame-Discriminative And Confidence-Driven Adaptation For LVCSR (2000)
Frank Wallhoff, Daniel Willett, Gerhard Rigoll
Maximum Likelihood Linear Regression (MLLR) has become the most popular approach for adapting speakerindependent Hidden Markov Models to a specic speaker's characteristics. However, it is well...
Ducoder - The Duisburg University Lvcsr Stackdecoder (2000)
Daniel Willett, Christoph Neukirchen, Gerhard Rigoll
With this paper, we present the DUcoder, the LVCSR decoder developed at Duisburg University. The decoder performs the Viterbi search for the most probable word sequence in recognition systems that...
Experiments In Topic Indexing Of Broadcast News Using Neural Networks (1999)
Christoph Neukirchen, Daniel Willett, Gerhard Rigoll
The paper deals with the problem of extracting topic information from news show stories by statistical methods. It is shown that the traditional topic-dependent n-gram language modeling approach can...
Jörg Rottland, J Org Rottl, Christoph Neukirchen, Daniel Willett, Gerhard Rigoll
This paper describes, how to perform speaker adaptation for a hybrid large vocabulary speech recognition system. The hybrid system is based on a Maximum Mutual Information Neural Network (MMINN),...
Daniel Willett, Christoph Neukirchen, Jörg Rottland, J Org Rottl, Gerhard Rigoll
Decision tree-based state clustering has emerged in recent years as the most popular approach for clustering the states of context dependent hidden Markov model based speech recognizers. The...
High Performance Face Recognition Using Pseudo 2-D Hidden Markov Models (1999)
Stefan Eickeler, Stefan Müller, Gerhard Rigoll
A face recognition system based on 2-D DCT features and pseudo-2D Hidden Markov Models is presented. The system achieves a recognition rate of 99.5 % on the Olivetti Research Laboratory (ORL) face...
Improved Stochastic Modeling of Shapes for Content-Based Image Retrieval (1999)
Recent advances in the stochastic modeling of shapes for content-based image database retrieval are presented in this paper. These advances include an integrated approach to shape and color-based...
Image Database Retrieval of Rotated Objects by User Sketch (1998)
Stefan Muller, Stefan Eickeler, Gerhard Rigoll
This paper describes our image retrieval system, which enables the user to search a grey-scale image database intuitively by presenting simple sketches. The database contains 120 different isolated...
Confidence measures for hmm-based speech recognition (1998)
Daniel Willett, Andreas Worm, Christoph Neukirchen, Gerhard Rigoll
In this paper, we describe our work on the field of confidence measures for HMM-based speech recognition. Confidence measures are a means of estimating the recognition reliability for single words of...
Gerhard Rigoll, Daniel Willett
This paper deals with a hybrid NN/HMM architecture for continuous speech recognition. We present a novel approach to set up a neural linear or nonlinear feature transformation that is used as a...
Daniel Willett, Arno Rorner, Arno Romer, Jorg Rottland, Gerhard Rigoll
In this paper, we present the basic design principles and architecture of a dialogue system for scheduling appointments. This mixed-initiative dialogue system integrates an automatic...
Andreas Kosmala, Gerhard Rigoll
The introduction of trigraphs offers a powerful method for the accuracy enhancement of handwriting modeling. A trigraph is a Hidden Markov Model (HMM) for a special character with defined adjacent...
Soft State-Tying For HMM-Based Speech Recognition (1998)
Christoph Neukirchen, Daniel Willett, Gerhard Rigoll
This paper introduces a method for regularization of HMM systems that avoids parameter overfitting causedby insufficient training data. Regularization is done by augmenting the EM training method by...
Efficient Search With Posterior Probability Estimates In Hmm-Based Speech Recognition (1998)
Daniel Willett, Christoph Neukirchen, Gerhard Rigoll
In this paper we present the methods we developed to estimate posterior probabilities for HMM states in continuous and discrete HMM-based speech recognition systems and several ways to speed up...
On-Line Handwritten Formula Recognition Using Statistical Methods (1998)
Andreas Kosmala, Gerhard Rigoll
This paper presents the design of a system for the processing and recognition of online handwritten mathematical formulas. The Hidden Markov Model (HMM) based system is trained and evaluated with a...
Hybrid Speech Recognition Systems: A Real Alternative To Traditional Approaches? (1998)
In this paper, an introduction to hybrid modeling techniques for speech recognition is presented. A hybrid speech recognition system consists of the combination of Hidden Markov Models (HMMs) with...
Hidden Markov Model Based Continuous Online Gesture Recognition (1998)
Stefan Eickeler, Andreas Kosmala, Gerhard Rigoll
This paper presents the extension of an existing visionbased gesture recognition system using Hidden Markov Models (HMMs). Several improvements have been carried out in order to increase the...
Invariant Recognition of Hand-Drawn Pictograms Using HMMs with a Rotating Feature Extraction (1998)
Stefan Müller, Gerhard Rigoll, Andreas Kosmala, Denis Mazurenok
In this paper, we present a new feature extraction technique and a novel Hidden Markov Model (HMM) based classifier for the rotation, translation and scale invariant recognition of handdrawn...
On-line handwritten formula recognition using statistical methods (1998)
Andreas Kosmala, Gerhard Rigoll
This paper presents an approach for the recognition of on-line handwritten mathematical expressions. The Hidden Markov Model (HMM) based system makes use of simultaneous segmentation and recognition...
High Performance Real-Time Gesture Recognition Using Hidden Markov Models (1997)
Gerhard Rigoll, Andreas Kosmala, Stefan Eickeler
Abstract. An advanced real-time system for gesture recognition is presented, which is able to recognize complex dynamic gestures, such as "hand waving", "spin",...
A New Approach to Content-based Video Indexing Using Hidden Markov Models (1997)
Stefan Eickeler, Andreas Kosmala, Gerhard Rigoll
Abstract. This paper presents one of the first investigations of the use of Hidden Markov Models (HMMs) for content-based video indexing. A real-time video indexing system for TV news is described,...
Improved On-Line Handwriting Recognition Using Context Dependent Hidden Markov Models (1997)
Andreas Kosmala, Jörg Rottland, Gerhard Rigoll
This paper presents the introduction of context dependent Hidden Markov Models for cursive, unconstrained handwriting recognition with large vocabularies. Since context dependent models were...
Christoph Neukirchen, Gerhard Rigoll
This paper deals with the construction and optimization of a hybrid speech recognition system that consists of a combination of a neural vector quantizer (VQ) and discrete HMMs. In our investigations...
An Investigation Of The Use Of Trigraphs For Large Vocabulary Cursive Handwriting Recognition (1997)
Andreas Kosmala, Jörg Rottland, Gerhard Rigoll
This paper presents an extensive investigation of the use of trigraphs for on-line cursive handwriting recognition based on Hidden Markov Models (HMMs). Trigraphs are context dependent HMMs...
Hybrid NN/HMM-Based Speech Recognition with a Discriminant Neural Feature Extraction (1997)
Daniel Willett, Gerhard Rigoll
In this paper, we present a novel hybrid architecture for continuous speech recognition systems. It consists of a continuous HMM system extended by an arbitrary neural network that is used as a...
A New Approach To Generalized Mixture Tying For Continuous HMM-Based Speech Recognition (1997)
Daniel Willett, Gerhard Rigoll
In this paper we present a new approach for a generalized tying of mixture components for continuous mixture-density HMM-based speech recognition systems. With an iterative pruning and splitting...
Large Vocabulary On-Line Handwriting Recognition with Context Dependent Hidden Markov Models (1997)
Andreas Kosmala, Jörg Rottland, Gerhard Rigoll
. This paper presents a systematic investigation of the benefits resulting from the introduction of context-dependent modeling techniques in HMM-based large vocabulary handwriting recognition...
Gerhard Rigoll, Andreas Kosmala
This paper describes new feature extraction methods which can be used very effectively in combination with statistical methods for image sequence recognition. Although these feature extraction...
An Investigation of the Use of Trigraphs for Large Vocabulary Cursive Handwriting Recognition (1997)
Andreas Kosmala, Jörg Rottl, Gerhard Rigoll
This paper presents an extensive investigation of the use of trigraphs for on-line cursive handwriting recognition based on Hidden Markov Models (HMMs). Trigraphs are context dependent HMMs...
Hybrid NN/HMM-Based Speech Recognition with a Discriminant Neural Feature Extraction (1997)
Daniel Willett, Gerhard Rigoll
In this paper, we present a novel hybrid architecture for continuous speech recognition systems. It consists of a continuous HMM system extended by an arbitrary neural network that is used as a...
A New Hybrid System Based On MMI-Neural Networks For The RM Speech Recognition Task (1996)
Gerhard Rigoll, Christoph Neukirchen, Jörg Rottland
We present a hybrid speech recognition system for speaker independent continuous speech recognition. The system combines a novel information theory based neural network (NN) paradigm and discrete...
Andreas Kosmala, Gerhard Rigoll, Stéphane Lavirotte, Loïc Pottier
This paper presents an approach for the recognition of on-line handwritten mathematical expressions. The Hidden Markov Model (HMM) based system makes use of simultaneous segmentation and recognition...
Improved Face Recognition Using Pseudo 2-D Hidden Markov Models
Stefan Eickeler, Stefan Müller, Gerhard Rigoll
. A face recognition system based on 2-D DCT features and pseudo-2D Hidden Markov Models is presented. The system achieves a recognition rate of 99.5 % on the Olivetti Research Laboratory (ORL) face...