TU1.P2.1
REAL-TIME JOINT NOISE SUPPRESSION AND BANDWIDTH EXTENSION OF NOISY REVERBERANT WIDEBAND SPEECH
Esteban Gómez, Voicemod Inc and Aalto University, Spain; Tom Bäckström, Aalto University, Finland
Session:
TU1.P2: Poster Session II: Noise reduction, Dereverberation Poster
Track:
Acoustic echo and feedback suppression
Location:
Indgangsfoyer
Presentation Time:
Tue, 10 Sep, 10:00 - 12:00 Central European Time (UTC +1)
Session Chair:
Tomohiro Nakatani, NTT Corporation
Presentation
Discussion
Resources
No resources available.
Session TU1.P2
TU1.P2.1: REAL-TIME JOINT NOISE SUPPRESSION AND BANDWIDTH EXTENSION OF NOISY REVERBERANT WIDEBAND SPEECH
Esteban Gómez, Voicemod Inc and Aalto University, Spain; Tom Bäckström, Aalto University, Finland
TU1.P2.2: MATRIX STUDY OF FEATURE COMPRESSION TYPES AND INSTRUMENTAL SPEECH QUALITY METRICS IN ULTRA-LIGHT DNN-BASED SPECTRAL SPEECH ENHANCEMENT
Aleksej Chinaev, Till Spitz, Carl von Ossietzky Universität Oldenburg, Germany; Stefan Thaleiser, Ruhr-Universität Bochum, Germany; Gerald Enzner, Carl von Ossietzky Universität Oldenburg, Germany
TU1.P2.3: ANALYSIS OF EARBUD-MOUNTED BONE-CONDUCTION MICROPHONES
Christoph Weyer, Peter Jax, RWTH Aachen University, Germany
TU1.P2.4: COMPARATIVE ANALYSIS OF DISCRIMINATIVE DEEP LEARNING-BASED NOISE REDUCTION METHODS IN LOW SNR SCENARIOS
Shrishti Saha Shetu, Emanuel A. P. Habets, Andreas Brendel, Fraunhofer-Institut für Integrierte Schaltungen (IIS), Germany
TU1.P2.5: UNCERTAINTY-BASED REMIXING FOR UNSUPERVISED DOMAIN ADAPTATION IN DEEP SPEECH ENHANCEMENT
Huajian Fang, Timo Gerkmann, University of Hamburg, Germany
TU1.P2.6: CONCATENET: DIALOGUE SEPARATION USING LOCAL AND GLOBAL FEATURE CONCATENATION
Mhd Modar Halimeh, Matteo Torcoli, Fraunhofer IIS, Germany; Emanuël Habets, Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany
TU1.P2.7: MULTI-STREAM DIFFUSION MODEL FOR PROBABILISTIC INTEGRATION OF MODEL-BASED AND DATA-DRIVEN SPEECH ENHANCEMENT
Tomohiro Nakatani, Naoyuki Kamo, Marc Delcroix, Shoko Araki, NTT Corporation, Japan
TU1.P2.8: ON THE IMPACT OF FREQUENCY RESOLUTION ON FEMALE AND MALE SPEECH IN DNN-BASED NOISE REDUCTION SYSTEMS
Maurice Oberhag, Yan Zeng, Rainer Martin, Ruhr-Universität Bochum, Germany
TU1.P2.9: MONAURAL SPEECH ENHANCEMENT ON DRONE VIA ADAPTER BASED TRANSFER LEARNING
Xingyu Chen, Hanwen Bi, Wei-Ting Lai, Fei Ma, Australian National University, Australia
TU1.P2.10: LASER: LANGUAGE-QUERIED SPEECH ENHANCER
Danilo de Oliveira, Universität Hamburg, Germany; Eric Grinstein, Patrick Naylor, Imperial College London, Germany; Timo Gerkmann, Universität Hamburg, Germany
TU1.P2.11: SPHERICAL MAPPING OF SHORT-TIME SPECTRAL COMPONENTS
Yu Morinaga, Naoto Kotake, Iori Hashimoto, Suehiro Shimauchi, Shigeaki Aoki, Kanazawa Institute of Technology, Japan
TU1.P2.12: SUPPRESSING NOISE DISPARITY IN TRAINING DATA FOR AUTOMATIC PATHOLOGICAL SPEECH DETECTION
Mahdi Amiri, Ina Kodrasi, Idiap Research Institute, Switzerland
TU1.P2.13: PLUG-AND-PLAY AUDIO RESTORATION WITH DIFFUSION DENOISER
Michal Švento, Pavel Rajmic, Ondřej Mokrý, Brno University of Technology, Czechia
TU1.P2.14: BUDDY: SINGLE-CHANNEL BLIND UNSUPERVISED DEREVERBERATION WITH DIFFUSION MODELS
Eloi Moliner, Aalto University, Finland; Jean-Marie Lemercier, Simon Welker, Timo Gerkmann, Universität Hamburg, Germany; Vesa Välimäki, Aalto University, Finland
TU1.P2.15: REFERENCE MICROPHONE SELECTION FOR THE WEIGHTED PREDICTION ERROR ALGORITHM USING THE NORMALIZED L-P NORM
Anselm Lohmann, Carl von Ossietzky Universität Oldenburg, Germany; Toon van Waterschoot, KU Leuven, Belgium; Joerg Bitzer, Fraunhofer IDMT, Germany; Simon Doclo, Carl von Ossietzky Universität Oldenburg, Fraunhofer IDMT, Germany