Lukas Drude

49 papers A 8C 2Misc 14Journal 16Unranked 8
YearRankTypeTitle / Venue / Authors
2024 Misc conf
Promptformer: Prompted Conformer Transducer for ASR.
ICASSP
Sergio Duarte Torres, Arunasish Sen, Aman Rana, Lukas Drude, Alejandro Gómez Alanís, Andreas Schwarz, Leif Rädel, Volker Leutnant
2024 J jnl
Promptformer: Prompted Conformer Transducer for ASR.
CoRR
Sergio Duarte Torres, Arunasish Sen, Aman Rana, Lukas Drude, Alejandro Gómez Alanís, Andreas Schwarz, Leif Rädel, Volker Leutnant
2023 A conf
Multi-View Frequency-Attention Alternative to CNN Frontends for Automatic Speech Recognition.
INTERSPEECH
Belen Alastruey, Lukas Drude, Jahn Heymann, Simon Wiesler
2023 J jnl
Multi-View Frequency-Attention Alternative to CNN Frontends for Automatic Speech Recognition.
CoRR
Belen Alastruey, Lukas Drude, Jahn Heymann, Simon Wiesler
2022 — conf
Contextual-Utterance Training for Automatic Speech Recognition.
IberSPEECH
Alejandro Gómez Alanís, Lukas Drude, Andreas Schwarz, Rupak Vignesh Swaminathan, Simon Wiesler
2022 J jnl
Contextual-Utterance Training for Automatic Speech Recognition.
CoRR
Alejandro Gómez Alanís, Lukas Drude, Andreas Schwarz, Rupak Vignesh Swaminathan, Simon Wiesler
2021 J jnl
Far-Field Automatic Speech Recognition.
Proc. IEEE
Reinhold Haeb-Umbach, Jahn Heymann, Lukas Drude, Shinji Watanabe, Marc Delcroix, Tomohiro Nakatani
2021 A conf
Multi-Channel Opus Compression for Far-Field Automatic Speech Recognition with a Fixed Bitrate Budget.
Interspeech
Lukas Drude, Jahn Heymann, Andreas Schwarz, Jean-Marc Valin
2021 J jnl
Multi-channel Opus compression for far-field automatic speech recognition with a fixed bitrate budget.
CoRR
Lukas Drude, Jahn Heymann, Andreas Schwarz, Jean-Marc Valin
2020 Misc conf
Demystifying TasNet: A Dissecting Approach.
ICASSP
Jens Heitkaemper, Darius Jakobeit, Christoph Böddeker, Lukas Drude, Reinhold Haeb-Umbach
2020 Misc conf
End-to-End Training of Time Domain Audio Separation and Recognition.
ICASSP
Thilo von Neumann, Keisuke Kinoshita, Lukas Drude, Christoph Böddeker, Marc Delcroix, Tomohiro Nakatani, Reinhold Haeb-Umbach
2020 — —
Integration of neural networks and probabilistic spatial models for acoustic blind source separation.
Lukas Drude
2020 A conf
Multi-Talker ASR for an Unknown Number of Sources: Joint Training of Source Counting, Separation and ASR.
INTERSPEECH
Thilo von Neumann, Christoph Böddeker, Lukas Drude, Keisuke Kinoshita, Marc Delcroix, Tomohiro Nakatani, Reinhold Haeb-Umbach
2020 J jnl
Multi-talker ASR for an unknown number of sources: Joint training of source counting, separation and ASR.
CoRR
Thilo von Neumann, Christoph Böddeker, Lukas Drude, Keisuke Kinoshita, Marc Delcroix, Tomohiro Nakatani, Reinhold Haeb-Umbach
2019 J jnl
Demystifying TasNet: A Dissecting Approach.
CoRR
Jens Heitkaemper, Darius Jakobeit, Christoph Böddeker, Lukas Drude, Reinhold Haeb-Umbach
2019 J jnl
End-to-end training of time domain audio separation and recognition.
CoRR
Thilo von Neumann, Keisuke Kinoshita, Lukas Drude, Christoph Böddeker, Marc Delcroix, Tomohiro Nakatani, Reinhold Haeb-Umbach
2019 J jnl
Integration of Neural Networks and Probabilistic Spatial Models for Acoustic Blind Source Separation.
IEEE J. Sel. Top. Signal Process.
Lukas Drude, Reinhold Haeb-Umbach
2019 Misc conf
Joint Optimization of Neural Network-based WPE Dereverberation and Acoustic Model for Robust Online ASR.
ICASSP
Jahn Heymann, Lukas Drude, Reinhold Haeb-Umbach, Keisuke Kinoshita, Tomohiro Nakatani
2019 J jnl
SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition.
CoRR
Lukas Drude, Jens Heitkaemper, Christoph Böddeker, Reinhold Haeb-Umbach
2019 A conf
Unsupervised Training of Neural Mask-Based Beamforming.
INTERSPEECH
Lukas Drude, Jahn Heymann, Reinhold Haeb-Umbach
2019 Misc conf
Unsupervised Training of a Deep Clustering Model for Multichannel Blind Source Separation.
ICASSP
Lukas Drude, Daniel Hasenklever, Reinhold Haeb-Umbach
2019 J jnl
Unsupervised training of a deep clustering model for multichannel blind source separation.
CoRR
Lukas Drude, Daniel Hasenklever, Reinhold Haeb-Umbach
2019 J jnl
Unsupervised training of neural mask-based beamforming.
CoRR
Lukas Drude, Jahn Heymann, Reinhold Haeb-Umbach
2019 — conf
Weakly Supervised Sound Activity Detection and Event Classification in Acoustic Sensor Networks.
CAMSAP
Janek Ebbers, Lukas Drude, Reinhold Haeb-Umbach, Andreas Brendel, Walter Kellermann
2018 Misc conf
Deep Attractor Networks for Speaker Re-Identification and Blind Source Separation.
ICASSP
Lukas Drude, Thilo von Neumann, Reinhold Haeb-Umbach
2018 Misc conf
Dual Frequency- and Block-Permutation Alignment for Deep Learning Based Block-Online Blind Source Separation.
ICASSP
Lukas Drude, Takuya Higuchi, Keisuke Kinoshita, Tomohiro Nakatani, Reinhold Haeb-Umbach
2018 — conf
Frame-Online DNN-WPE Dereverberation.
IWAENC
Jahn Heymann, Lukas Drude, Reinhold Haeb-Umbach, Keisuke Kinoshita, Tomohiro Nakatani
2018 A conf
Integrating Neural Network Based Beamforming and Weighted Prediction Error Dereverberation.
INTERSPEECH
Lukas Drude, Christoph Böddeker, Jahn Heymann, Reinhold Haeb-Umbach, Keisuke Kinoshita, Marc Delcroix, Tomohiro Nakatani
2018 Misc conf
Listening to Each Speaker One by One with Recurrent Selective Hearing Networks.
ICASSP
Keisuke Kinoshita, Lukas Drude, Marc Delcroix, Tomohiro Nakatani
2018 — conf
NARA-WPE: A Python package for weighted prediction error dereverberation in Numpy and Tensorflow for online and offline processing.
ITG Symposium on Speech Communication
Lukas Drude, Jahn Heymann, Christoph Böddeker, Reinhold Haeb-Umbach
2017 J jnl
A generic neural acoustic beamforming architecture for robust multi-channel speech processing.
Comput. Speech Lang.
Jahn Heymann, Lukas Drude, Reinhold Haeb-Umbach
2017 Misc conf
Beamnet: End-to-end training of a beamformer-supported multi-channel ASR system.
ICASSP
Jahn Heymann, Lukas Drude, Christoph Böddeker, Patrick Hanebrink, Reinhold Haeb-Umbach
2017 J jnl
Directional Statistics and Filtering Using libDirectional.
CoRR
Gerhard Kurz, Igor Gilitschenski, Florian Pfaff, Lukas Drude, Uwe D. Hanebeck, Reinhold Haeb-Umbach, Roland Yves Siegwart
2017 A conf
Hidden Markov Model Variational Autoencoder for Acoustic Unit Discovery.
INTERSPEECH
Janek Ebbers, Jahn Heymann, Lukas Drude, Thomas Glarner, Reinhold Haeb-Umbach, Bhiksha Raj
2017 C conf
Multi-stage coherence drift based sampling rate synchronization for acoustic beamforming.
MMSP
Joerg Schmalenstroeer, Jahn Heymann, Lukas Drude, Christoph Böddeker, Reinhold Haeb-Umbach
2017 J jnl
On the Computation of Complex-valued Gradients with Application to Statistically Optimum Beamforming.
CoRR
Christoph Böddeker, Patrick Hanebrink, Lukas Drude, Jahn Heymann, Reinhold Haeb-Umbach
2017 Misc conf
Optimizing neural-network supported acoustic beamforming by algorithmic differentiation.
ICASSP
Christoph Böddeker, Patrick Hanebrink, Lukas Drude, Jahn Heymann, Reinhold Haeb-Umbach
2017 J jnl
The Incredible Shrinking Neural Network: New Perspectives on Learning Representations Through The Lens of Pruning.
CoRR
Nikolas Wolfe, Aditya Sharma, Lukas Drude, Bhiksha Raj
2017 A conf
Tight Integration of Spatial and Spectral Features for BSS with Deep Clustering Embeddings.
INTERSPEECH
Lukas Drude, Reinhold Haeb-Umbach
2016 Misc conf
Blind speech separation based on complex spherical k-mode clustering.
ICASSP
Lukas Drude, Christoph Böddeker, Reinhold Haeb-Umbach
2016 — conf
Factor Graph Decoding for Speech Presence Probability Estimation.
ITG Symposium on Speech Communication
Thomas Glarner, Mohammad Mahdi Momenzadeh, Lukas Drude, Reinhold Haeb-Umbach
2016 Misc conf
Neural network based spectral mask estimation for acoustic beamforming.
ICASSP
Jahn Heymann, Lukas Drude, Reinhold Haeb-Umbach
2016 — conf
Noise-Presence-Probability-Based Noise PSD Estimation by Using DNNs.
ITG Symposium on Speech Communication
Aleksej Chinaev, Jahn Heymann, Lukas Drude, Reinhold Haeb-Umbach
2016 A conf
On the Appropriateness of Complex-Valued Neural Networks for Speech Enhancement.
INTERSPEECH
Lukas Drude, Bhiksha Raj, Reinhold Haeb-Umbach
2015 C conf
BLSTM supported GEV beamformer front-end for the 3RD CHiME challenge.
ASRU
Jahn Heymann, Lukas Drude, Aleksej Chinaev, Reinhold Haeb-Umbach
2015 — conf
DOA-estimation based on a complex Watson kernel method.
EUSIPCO
Lukas Drude, Florian Jacob, Reinhold Haeb-Umbach
2015 Misc conf
Source counting in speech mixtures by nonparametric Bayesian estimation of an infinite Gaussian mixture model.
ICASSP
Oliver Walter, Lukas Drude, Reinhold Haeb-Umbach
2014 Misc conf
Source counting in speech mixtures using a variational EM approach for complex WATSON mixture models.
ICASSP
Lukas Drude, Aleksej Chinaev, Dang Hai Tran Vu, Reinhold Haeb-Umbach
2014 — conf
Towards online source counting in speech mixtures applying a variational EM for complex Watson mixture models.
IWAENC
Lukas Drude, Aleksej Chinaev, Dang Hai Tran Vu, Reinhold Haeb-Umbach