Picture for Ke Tan

Ke Tan

FoVNet: Configurable Field-of-View Speech Enhancement with Low Computation and Distortion for Smart Glasses

Add code
Aug 12, 2024
Viaarxiv icon

AV-CrossNet: an Audiovisual Complex Spectral Mapping Network for Speech Separation By Leveraging Narrow- and Cross-Band Modeling

Add code
Jun 17, 2024
Viaarxiv icon

A Closer Look at Wav2Vec2 Embeddings for On-Device Single-Channel Speech Enhancement

Add code
Mar 03, 2024
Figure 1 for A Closer Look at Wav2Vec2 Embeddings for On-Device Single-Channel Speech Enhancement
Figure 2 for A Closer Look at Wav2Vec2 Embeddings for On-Device Single-Channel Speech Enhancement
Figure 3 for A Closer Look at Wav2Vec2 Embeddings for On-Device Single-Channel Speech Enhancement
Figure 4 for A Closer Look at Wav2Vec2 Embeddings for On-Device Single-Channel Speech Enhancement
Viaarxiv icon

Holmes: Towards Distributed Training Across Clusters with Heterogeneous NIC Environment

Add code
Dec 11, 2023
Figure 1 for Holmes: Towards Distributed Training Across Clusters with Heterogeneous NIC Environment
Figure 2 for Holmes: Towards Distributed Training Across Clusters with Heterogeneous NIC Environment
Figure 3 for Holmes: Towards Distributed Training Across Clusters with Heterogeneous NIC Environment
Figure 4 for Holmes: Towards Distributed Training Across Clusters with Heterogeneous NIC Environment
Viaarxiv icon

TorchAudio-Squim: Reference-less Speech Quality and Intelligibility measures in TorchAudio

Add code
Apr 04, 2023
Viaarxiv icon

Rethinking complex-valued deep neural networks for monaural speech enhancement

Add code
Jan 11, 2023
Viaarxiv icon

Leveraging Heteroscedastic Uncertainty in Learning Complex Spectral Mapping for Single-channel Speech Enhancement

Add code
Nov 16, 2022
Figure 1 for Leveraging Heteroscedastic Uncertainty in Learning Complex Spectral Mapping for Single-channel Speech Enhancement
Figure 2 for Leveraging Heteroscedastic Uncertainty in Learning Complex Spectral Mapping for Single-channel Speech Enhancement
Figure 3 for Leveraging Heteroscedastic Uncertainty in Learning Complex Spectral Mapping for Single-channel Speech Enhancement
Figure 4 for Leveraging Heteroscedastic Uncertainty in Learning Complex Spectral Mapping for Single-channel Speech Enhancement
Viaarxiv icon

Location-based training for multi-channel talker-independent speaker separation

Add code
Oct 08, 2021
Figure 1 for Location-based training for multi-channel talker-independent speaker separation
Figure 2 for Location-based training for multi-channel talker-independent speaker separation
Figure 3 for Location-based training for multi-channel talker-independent speaker separation
Figure 4 for Location-based training for multi-channel talker-independent speaker separation
Viaarxiv icon

Bridging the Gap Between Monaural Speech Enhancement and Recognition with Distortion-Independent Acoustic Modeling

Add code
Mar 13, 2019
Figure 1 for Bridging the Gap Between Monaural Speech Enhancement and Recognition with Distortion-Independent Acoustic Modeling
Figure 2 for Bridging the Gap Between Monaural Speech Enhancement and Recognition with Distortion-Independent Acoustic Modeling
Figure 3 for Bridging the Gap Between Monaural Speech Enhancement and Recognition with Distortion-Independent Acoustic Modeling
Figure 4 for Bridging the Gap Between Monaural Speech Enhancement and Recognition with Distortion-Independent Acoustic Modeling
Viaarxiv icon

Deep Learning Based Phase Reconstruction for Speaker Separation: A Trigonometric Perspective

Add code
Nov 22, 2018
Figure 1 for Deep Learning Based Phase Reconstruction for Speaker Separation: A Trigonometric Perspective
Figure 2 for Deep Learning Based Phase Reconstruction for Speaker Separation: A Trigonometric Perspective
Figure 3 for Deep Learning Based Phase Reconstruction for Speaker Separation: A Trigonometric Perspective
Figure 4 for Deep Learning Based Phase Reconstruction for Speaker Separation: A Trigonometric Perspective
Viaarxiv icon