Reinhold Häb-Umbach

发表

A summary of the REVERB challenge: state-of-the-art and remaining challenges in reverberant speech processing research

R. Maas, A. Sehr, Walter Kellermann, 2016, EURASIP Journal on Advances in Signal Processing.

Blind speech separation employing directional statistics in an Expectation Maximization framework

Reinhold Häb-Umbach, Dang Hai Tran Vu, Reinhold Häb-Umbach, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Blind Acoustic Beamforming Based on Generalized Eigenvalue Decomposition

Reinhold Häb-Umbach, Ernst Warsitz, Reinhold Häb-Umbach, 2007, IEEE Transactions on Audio, Speech, and Language Processing.

Specifying a tree structure for speech recognizers using correlation between regression classes

Reinhold Häb-Umbach, 2004 .

A comparative study of linear feature transformation techniques for automatic speech recognition

Detlev Langmann, Reinhold Häb-Umbach, Thomas Eisele, 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

Multi-class linear dimension reduction by generalized Fisher criteria

Reinhold Häb-Umbach, Marco Loog, M. Loog, 2000, INTERSPEECH.

Explanation as a Social Practice: Toward a Conceptual Framework for the Social Design of AI Systems

Stefan Kopp, Eyke Hüllermeier, Petra Wagner, 2021, IEEE Transactions on Cognitive and Developmental Systems.

The development of a command-based speech interface for a telephone answering machine

Stephan Gamm, Detlev Langmann, Reinhold Häb-Umbach, 1997, Speech Commun..

Design and use of speech recognition algorithms for a mobile radio telephone

Hermann Ney, Reinhold Häb-Umbach, Stefan Dobler, 1993, Speech Commun..

On the exploitation of hidden Markov models and linear dynamic models in a hybrid decoder architecture for continuous speech recognition

Reinhold Häb-Umbach, Volker Leutnant, Reinhold Häb-Umbach, 2010, INTERSPEECH.

A Novel Uncertainty Decoding Rule With Applications to Transmission Error Robust Speech Recognition

Reinhold Häb-Umbach, Valentin Ion, Reinhold Häb-Umbach, 2008, IEEE Transactions on Audio, Speech, and Language Processing.

Channel estimation by exploiting sublayer information in OFDM systems

Reinhold Häb-Umbach, Maik Bevermeier, Tobias Ebel, 2007, MCSS.

Continuous speech dictation - From theory to practice

Hermann Ney, Reinhold Häb-Umbach, H. Bartosik, 1995, Speech Commun..

Multiclass Linear Dimension Reduction by Weighted Pairwise Fisher Criteria

Robert P. W. Duin, Reinhold Häb-Umbach, Marco Loog, 2001, IEEE Trans. Pattern Anal. Mach. Intell..

Online speaker change detection by combining BIC with microphone array beamforming

Reinhold Häb-Umbach, Joerg Schmalenstroeer, Reinhold Häb-Umbach, 2006, INTERSPEECH.

Linear discriminant analysis for improved large vocabulary continuous speech recognition

H. Ney, R. Haeb-Umbach, Reinhold Häb-Umbach, 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Uncertainty decoding for distributed speech recognition over error-prone networks

Reinhold Häb-Umbach, Valentin Ion, Reinhold Häb-Umbach, 2006, Speech Commun..

LDA derived cepstral trajectory filters in adverse environmental conditions

Reinhold Häb-Umbach, Markus Lieb, Reinhold Häb-Umbach, 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

A generic neural acoustic beamforming architecture for robust multi-channel speech processing

Reinhold Häb-Umbach, Lukas Drude, Jahn Heymann, 2017, Comput. Speech Lang..

An Overview of Noise-Robust Automatic Speech Recognition

Yifan Gong, Jinyu Li, Reinhold Häb-Umbach, 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

A Study on Online Source Extraction in the Presence of Changing Speaker Positions

Reinhold Häb-Umbach, Jens Heitkaemper, Thomas Fehér, 2019, SLSP.

Neural network based spectral mask estimation for acoustic beamforming

Reinhold Häb-Umbach, Lukas Drude, Jahn Heymann, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A Model-Based Approach to Joint Compensation of Noise and Reverberation for Speech Recognition

Reinhold Häb-Umbach, Alexander Krueger, Reinhold Häb-Umbach, 2011, Robust Speech Recognition of Uncertain or Missing Data.

Directional Statistics and Filtering Using libDirectional pdf

Roland Siegwart, Uwe D. Hanebeck, Reinhold Häb-Umbach, 2017, Journal of Statistical Software.

Bayesian Feature Enhancement for Reverberation and Noise Robust Speech Recognition

Reinhold Häb-Umbach, Alexander Krueger, Volker Leutnant, 2013, IEEE Transactions on Audio, Speech, and Language Processing.

Bayesian Feature Enhancement for ASR of Noisy Reverberant Real-World Data

Reinhold Häb-Umbach, Oliver Walter, Alexander Krueger, 2012, INTERSPEECH.

Model-Based Feature Enhancement for Reverberant Speech Recognition

Reinhold Häb-Umbach, Alexander Krueger, Reinhold Häb-Umbach, 2010, IEEE Transactions on Audio, Speech, and Language Processing.

Joint Parameter Estimation and Tracking in a Multi-Stage Kalman Filter for Vehicle Positioning

Reinhold Häb-Umbach, Sven Peschke, Maik Bevermeier, 2009, VTC Spring 2009 - IEEE 69th Vehicular Technology Conference.

A GPS positioning approach exploiting GSM velocity estimates

Reinhold Häb-Umbach, Sven Peschke, Maik Bevermeier, 2009, 2009 6th Workshop on Positioning, Navigation and Communication.

Robust vehicle localization based on multi-level sensor fusion and online parameter estimation

Reinhold Häb-Umbach, Sven Peschke, Maik Bevermeier, 2009, 2009 6th Workshop on Positioning, Navigation and Communication.

Model based feature enhancement for automatic speech recognition in reverberant environments

Reinhold Häb-Umbach, Alexander Krueger, Reinhold Häb-Umbach, 2009, INTERSPEECH.

Beamnet: End-to-end training of a beamformer-supported multi-channel ASR system

Reinhold Häb-Umbach, Christoph Böddeker, Patrick Hanebrink, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

All-neural Online Source Separation, Counting, and Diarization for Meeting Analysis

Tomohiro Nakatani, Shoko Araki, Marc Delcroix, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Typicality and emotion in the voice of children with autism spectrum condition: evidence across three languages

Erik Marchi, Björn W. Schuller, Reinhold Häb-Umbach, 2015, INTERSPEECH.

Acoustic filter-and-sum beamforming by adaptive principal component analysis

Reinhold Häb-Umbach, Ernst Warsitz, Reinhold Häb-Umbach, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

Guided Source Separation Meets a Strong ASR Backend: Hitachi/Paderborn University Joint Investigation for Dinner Party ASR pdf

Naoyuki Kanda, Reinhold Häb-Umbach, Shota Horiguchi, 2019, INTERSPEECH.

Unsupervised Training of a Deep Clustering Model for Multichannel Blind Source Separation

Reinhold Häb-Umbach, Lukas Drude, Daniel Hasenklever, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Hidden Markov Model Variational Autoencoder for Acoustic Unit Discovery

Reinhold Häb-Umbach, Janek Ebbers, Patrick Hanebrink, 2017, INTERSPEECH.

Hidden Markov Model Variational Autoencoder for Acoustic Unit Discovery

Bhiksha Raj, Reinhold Häb-Umbach, Janek Ebbers, 2017, INTERSPEECH.

Contrastive Predictive Coding Supported Factorized Variational Autoencoder For Unsupervised Learning Of Disentangled Speech Representations

Reinhold Häb-Umbach, Janek Ebbers, Michael Kuhlmann, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A study on transfer learning for acoustic event detection in a real life scenario

Reinhold Häb-Umbach, Prerna Arora, Reinhold Häb-Umbach, 2017, 2017 IEEE 19th International Workshop on Multimedia Signal Processing (MMSP).

A summary of the REVERB challenge: state-of-the-art and remaining challenges in reverberant speech processing research

R. Maas, A. Sehr, Walter Kellermann, 2016, EURASIP J. Adv. Signal Process..

Self-Trained Audio Tagging and Sound Event Detection in Domestic Environments

Reinhold Häb-Umbach, Janek Ebbers, Reinhold Häb-Umbach, 2021, DCASE.

Unsupervised training of neural mask-based beamforming pdf

Reinhold Häb-Umbach, Lukas Drude, Jahn Heymann, 2019, INTERSPEECH.

Application of clustering techniques to mixture density modelling for continuous-speech recognition

R. Haeb-Umbach, C. Dugast, P. Beyerlein, 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

Joint Optimization of Neural Network-based WPE Dereverberation and Acoustic Model for Robust Online ASR

Tomohiro Nakatani, Reinhold Häb-Umbach, Keisuke Kinoshita, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Integrating Neural Network Based Beamforming and Weighted Prediction Error Dereverberation

Tomohiro Nakatani, Marc Delcroix, Reinhold Häb-Umbach, 2018, INTERSPEECH.

Autonomous Learning of Representations

Barbara Hammer, Reinhold Häb-Umbach, Bassam Mokbel, 2015, KI - Künstliche Intelligenz.

Leveraging Text Data for Word Segmentation for Underresourced Languages

Reinhold Häb-Umbach, Oliver Walter, Thomas Glarner, 2017, INTERSPEECH.

BLSTM supported GEV beamformer front-end for the 3RD CHiME challenge

Reinhold Häb-Umbach, Lukas Drude, Jahn Heymann, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

Fusing audio and video information for online speaker diarization

Reinhold Häb-Umbach, Joerg Schmalenstroeer, Volker Leutnant, 2009, INTERSPEECH.

The philips/RWTH system for transcription of broadcast news

Andreas Wendemuth, Dietrich Klakow, Reinhold Häb-Umbach, 1999, EUROSPEECH.

An investigation of cepstral parameterisations for large vocabulary speech recognition

Reinhold Häb-Umbach, Marco Loog, M. Loog, 1999, EUROSPEECH.

European speech databases for telephone applications

Richard Winski, Khalid Choukri, Reinhold Häb-Umbach, 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

A combined hardware-software approach for acoustic sensor network synchronization

Reinhold Häb-Umbach, Joerg Schmalenstroeer, Patrick Jebramcik, 2015, Signal Process..

A study of broadcast news audio stream segmentation and segment clustering

Reinhold Häb-Umbach, Peter Beyerlein, Xavier L. Aubert, 1999, EUROSPEECH.

Multi-stage coherence drift based sampling rate synchronization for acoustic beamforming

Reinhold Häb-Umbach, Joerg Schmalenstroeer, Christoph Böddeker, 2017, 2017 IEEE 19th International Workshop on Multimedia Signal Processing (MMSP).

Deep Attractor Networks for Speaker Re-Identification and Blind Source Separation

Reinhold Häb-Umbach, Thilo von Neumann, Lukas Drude, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A priori SNR Estimation Using a Generalized Decision Directed Approach

Reinhold Häb-Umbach, Aleksej Chinaev, Reinhold Häb-Umbach, 2016, INTERSPEECH.

A Priori SNR Estimation Using Weibull Mixture Model

Reinhold Häb-Umbach, Aleksej Chinaev, Jens Heitkaemper, 2016, ITG Symposium on Speech Communication.

A hidden Markov model for indoor user tracking based on WiFi fingerprinting and step detection

Reinhold Häb-Umbach, Manh Kha Hoang, Joerg Schmalenstroeer, 2013, 21st European Signal Processing Conference (EUSIPCO 2013).

Exploring Practical Aspects of Neural Mask-Based Beamforming for Far-Field Speech Recognition

Takuya Yoshioka, Reinhold Häb-Umbach, Christoph Böddeker, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Unsupervised word segmentation from noisy input

Bhiksha Raj, Reinhold Häb-Umbach, Oliver Walter, 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

An evaluation of unsupervised acoustic model training for a dysarthric speech interface

Hugo Van hamme, Reinhold Häb-Umbach, Bart Ons, 2014, INTERSPEECH.

On the Computation of Complex-valued Gradients with Application to Statistically Optimum Beamforming pdf

Reinhold Häb-Umbach, Christoph Böddeker, Patrick Hanebrink, 2017, ArXiv.

On the Appropriateness of Complex-Valued Neural Networks for Speech Enhancement

Bhiksha Raj, Reinhold Häb-Umbach, Lukas Drude, 2016, INTERSPEECH.

The REVERB Challenge: A Benchmark Task for Reverberation-Robust ASR Techniques

Emanuel A. P. Habets, Takuya Yoshioka, Bhiksha Raj, 2017, New Era for Robust Speech Recognition, Exploiting Deep Learning.

Unsupervised Training of a Deep Clustering Model for Multichannel Blind Source Separation

Reinhold Häb-Umbach, Lukas Drude, Daniel Hasenklever, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speech Enhancement With a GSC-Like Structure Employing Eigenvector-Based Transfer Function Ratios Estimation

Reinhold Häb-Umbach, Ernst Warsitz, Alexander Krueger, 2011, IEEE Transactions on Audio, Speech, and Language Processing.

Blind adaptive principal eigenvector beamforming for acoustical source separation

Reinhold Häb-Umbach, Ernst Warsitz, Dang Hai Tran Vu, 2007, INTERSPEECH.

Blind speech separation based on complex spherical k-mode clustering

Reinhold Häb-Umbach, Christoph Böddeker, Lukas Drude, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

DOA-estimation based on a complex Watson kernel method

Reinhold Häb-Umbach, Florian Jacob, Lukas Drude, 2015, 2015 23rd European Signal Processing Conference (EUSIPCO).

DOA-based microphone array postion self-calibration using circular statistics

Reinhold Häb-Umbach, Joerg Schmalenstroeer, Florian Jacob, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Adaptive systems for unsupervised speaker tracking and speech recognition

Wolfgang Minker, Reinhold Häb-Umbach, Franz Gerl, 2011, Evol. Syst..

Signal representations for hidden Markov model based online handwriting recognition

Reinhold Häb-Umbach, Hans J. G. A. Dolfing, Reinhold Häb-Umbach, 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Improved source modeling and predictive classification for channel robust speech recognition

Reinhold Häb-Umbach, Valentin Ion, 2006, INTERSPEECH.

Acoustic Microphone Geometry Calibration: An overview and experimental evaluation of state-of-the-art algorithms

Reinhold Häb-Umbach, Axel Plinge, Gernot A. Fink, 2016, IEEE Signal Processing Magazine.

Unsupervised Geometry Calibration of Acoustic Sensor Networks Using Source Correspondences

Reinhold Häb-Umbach, Gernot A. Fink, Marius H. Hennecke, 2011, INTERSPEECH.

A novel target separation algorithm applied to the two-dimensional spectrum for FMCW automotive radar systems

Reinhold Häb-Umbach, Christopher Grimm, Tai Fei, 2017, 2017 IEEE International Conference on Microwaves, Antennas, Communications and Electronic Systems (COMCAS).

Parameter Estimation of a State-Space Model of Noise for Robust Speech Recognition

Reinhold Häb-Umbach, Stefan Windmann, Reinhold Häb-Umbach, 2009, IEEE Transactions on Audio, Speech, and Language Processing.

A hierarchical system for word discovery exploiting DTW-based initialization

Bhiksha Raj, Reinhold Häb-Umbach, Timo Korthals, 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

Online Diarization of Streaming Audio-Visual Data for Smart Environments

Reinhold Häb-Umbach, Joerg Schmalenstroeer, Reinhold Häb-Umbach, 2010, IEEE Journal of Selected Topics in Signal Processing.

Unsupervised adaptation of a denoising autoencoder by Bayesian Feature Enhancement for reverberant asr under mismatch conditions

Reinhold Häb-Umbach, Ralf Schlüter, Pavel Golik, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Large vocabulary continuous speech recognition of Broadcast News - The Philips/RWTH approach

Hermann Ney, Andreas Wendemuth, Dietrich Klakow, 2002, Speech Commun..

Improvements in beam search for 10000-word continuous-speech recognition

Hermann Ney, Reinhold Häb-Umbach, H. Ney, 1994, IEEE Trans. Speech Audio Process..

The Philips research system for large-vocabulary continuous-speech recognition

Hermann Ney, Reinhold Häb-Umbach, H. Bartosik, 1993, EUROSPEECH.

Continuous mixture densities and linear discriminant analysis for improved context-dependent acoustic models

Hermann Ney, Reinhold Häb-Umbach, Xavier L. Aubert, 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Improvements in connected digit recognition using linear discriminant analysis and mixture densities

Dieter Geller, Hermann Ney, Reinhold Häb-Umbach, 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

A look-ahead search technique for large vocabulary continuous speech recognition

Hermann Ney, Reinhold Häb-Umbach, H. Ney, 1991, EUROSPEECH.

Contrastive Predictive Coding Supported Factorized Variational Autoencoder For Unsupervised Learning Of Disentangled Speech Representations

Reinhold Häb-Umbach, Michael Kuhlmann, Tobias Cord-Landwehr, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Voice Conversion Based Speaker Normalization for Acoustic Unit Discovery pdf

Reinhold Häb-Umbach, Janek Ebbers, Thomas Glarner, 2021, ArXiv.