Picture for Hyewon Han

Hyewon Han

A cross-talk robust multichannel VAD model for multiparty agent interactions trained using synthetic re-recordings

Add code
Feb 15, 2024
Viaarxiv icon

HD-DEMUCS: General Speech Restoration with Heterogeneous Decoders

Add code
Jun 02, 2023
Figure 1 for HD-DEMUCS: General Speech Restoration with Heterogeneous Decoders
Figure 2 for HD-DEMUCS: General Speech Restoration with Heterogeneous Decoders
Figure 3 for HD-DEMUCS: General Speech Restoration with Heterogeneous Decoders
Figure 4 for HD-DEMUCS: General Speech Restoration with Heterogeneous Decoders
Viaarxiv icon

Learning Audio-Text Agreement for Open-vocabulary Keyword Spotting

Add code
Jul 01, 2022
Figure 1 for Learning Audio-Text Agreement for Open-vocabulary Keyword Spotting
Figure 2 for Learning Audio-Text Agreement for Open-vocabulary Keyword Spotting
Figure 3 for Learning Audio-Text Agreement for Open-vocabulary Keyword Spotting
Figure 4 for Learning Audio-Text Agreement for Open-vocabulary Keyword Spotting
Viaarxiv icon

Phase Continuity: Learning Derivatives of Phase Spectrum for Speech Enhancement

Add code
Feb 24, 2022
Figure 1 for Phase Continuity: Learning Derivatives of Phase Spectrum for Speech Enhancement
Figure 2 for Phase Continuity: Learning Derivatives of Phase Spectrum for Speech Enhancement
Figure 3 for Phase Continuity: Learning Derivatives of Phase Spectrum for Speech Enhancement
Figure 4 for Phase Continuity: Learning Derivatives of Phase Spectrum for Speech Enhancement
Viaarxiv icon