Metricgan+: An improved version of metricgan for speech enhancement
The discrepancy between the cost function used for training a speech enhancement model
and human auditory perception usually makes the quality of enhanced speech …
and human auditory perception usually makes the quality of enhanced speech …
Unsupervised noise adaptive speech enhancement by discriminator-constrained optimal transport
This paper presents a novel discriminator-constrained optimal transport network (DOTN) that
performs unsupervised domain adaptation for speech enhancement (SE), which is an …
performs unsupervised domain adaptation for speech enhancement (SE), which is an …
D4AM: A general denoising framework for downstream acoustic models
The performance of acoustic models degrades notably in noisy environments. Speech
enhancement (SE) can be used as a front-end strategy to aid automatic speech recognition …
enhancement (SE) can be used as a front-end strategy to aid automatic speech recognition …
LC4SV: A Denoising Framework Learning to Compensate for Unseen Speaker Verification Models
The performance of speaker verification (SV) models may drop dramatically in noisy
environments. A speech enhancement (SE) module can be used as a front-end strategy …
environments. A speech enhancement (SE) module can be used as a front-end strategy …
A two-stage deep neuroevolutionary technique for self-adaptive speech enhancement
R LeBlanc, SA Selouani - IEEE Access, 2022 - ieeexplore.ieee.org
This paper presents a novel self-adaptive approach for speech enhancement in the context
of highly nonstationary noise. A two-stage deep neuroevolutionary technique for speech …
of highly nonstationary noise. A two-stage deep neuroevolutionary technique for speech …
Leveraging Self-Supervised Speech Representations for Domain Adaptation in Speech Enhancement
Deep learning based speech enhancement (SE) approaches could suffer from performance
degradation due to mismatch between training and testing environments. A realistic situation …
degradation due to mismatch between training and testing environments. A realistic situation …
NASTAR: Noise Adaptive Speech Enhancement with Target-Conditional Resampling
For deep learning-based speech enhancement (SE) systems, the training-test acoustic
mismatch can cause notable performance degradation. To address the mismatch issue …
mismatch can cause notable performance degradation. To address the mismatch issue …
Speech recovery for real-world self-powered intermittent devices
The incompleteness of speech inputs severely degrades the performance of all the related
speech signal processing applications. Although many researches have been proposed to …
speech signal processing applications. Although many researches have been proposed to …
[PDF][PDF] Citear: A two-stage end-to-end system for noisy-reverberant hearing-aid processing
CC Lee, HW Chen, R Chao, TT Liu… - Proc. Clarity-CEC2 …, 2022 - claritychallenge.org
In this report, we present a hybrid neural network system on the task of the 2nd Clarity
Enhancement Challenge. The system, consisting of two stages, handles noisy-reverberant …
Enhancement Challenge. The system, consisting of two stages, handles noisy-reverberant …
CITISEN: A Deep Learning-Based Speech Signal-Processing Mobile Application
This study presents a deep learning-based speech signal-processing mobile application
known as CITISEN. The CITISEN can perform three functions: speech enhancement (SE) …
known as CITISEN. The CITISEN can perform three functions: speech enhancement (SE) …