[PDF][PDF] Joint blind source separation and dereverberation for automatic speech recognition using delayed-subsource MNMF with localization prior

M Fras, M Witkowski, K Kowalczyk - Proc. Interspeech, 2023 - isca-archive.org
Overlap** speech and high room reverberation deteriorate the accuracy of automatic
speech recognition (ASR). This paper proposes a method for jointly optimum source …

Reverberant Source Separation Using NTF With Delayed Subsources and Spatial Priors

M Fraś, K Kowalczyk - IEEE/ACM Transactions on Audio …, 2024 - ieeexplore.ieee.org
Speech signals recorded by distant microphones are often contaminated with room
reverberation and signals of interfering speakers. This article addresses the problem of joint …

Joint Dereverberation and Beamforming With Blind Estimation of the Shape Parameter of the Desired Source Prior

SK Yadav, NV George - IEEE/ACM Transactions on Audio …, 2023 - ieeexplore.ieee.org
Dereverberation and acoustic beamforming is used to capture the speech of a desired
speaker in the presence of interfering speakers in a reverberant room using an array of …

Opine: Leveraging a Optimization-Inspired Deep Unfolding Method for Multi-Channel Speech Enhancement

A Li, R Chen, Y Gu, C Weng… - ICASSP 2024-2024 IEEE …, 2024 - ieeexplore.ieee.org
Proximal gradient theory has demonstrated its superiority in the compressive sensing field
for complex signal recovery. As an early trial in the speech front-end field, we propose …

Speech Enhancement via Maximum Likelihood Modal Beamforming with Complex Gaussian and Laplacian Priors

SK Yadav, NV George - 2023 31st European Signal Processing …, 2023 - ieeexplore.ieee.org
Capturing speech from a target source in the presence of interfering sources and noise
using acoustic beamforming is an important processing tool for machine listening. When the …