MBI-Net: A non-intrusive multi-branched speech intelligibility prediction model for hearing aids

RE Zezario, F Chen, CS Fuh, HM Wang… - arXiv preprint arXiv …, 2022 - arxiv.org
Improving the user's hearing ability to understand speech in noisy environments is critical to
the development of hearing aid (HA) devices. For this, it is important to derive a metric that …

MTI-Net: A multi-target speech intelligibility prediction model

RE Zezario, S Fu, F Chen, CS Fuh, HM Wang… - arXiv preprint arXiv …, 2022 - arxiv.org
Recently, deep learning (DL)-based non-intrusive speech assessment models have
attracted great attention. Many studies report that these DL-based models yield satisfactory …

[HTML][HTML] Improved swarm intelligent blind source separation based on signal cross-correlation

J Zi, D Lv, J Liu, X Huang, W Yao, M Gao, R Xi… - Sensors, 2021 - mdpi.com
In recent years, separating effective target signals from mixed signals has become a hot and
challenging topic in signal research. The SI-BSS (Blind source separation (BSS) based on …

[PDF][PDF] Non-intrusive Speech Quality Assessment with a Multi-Task Learning based Subband Adaptive Attention Temporal Convolutional Neural Network.

X Shu, Y Chen, C Shang, Y Zhao, C Zhao, Y Zhu… - …, 2022 - cliffzhao.github.io
In terms of subjective evaluations, speech quality has been generally described by a mean
opinion score (MOS). In recent years, non-intrusive speech quality assessment shows an …

From the perspective of perceptual speech quality: The robustness of frequency bands to noise

J Fan, DS Williamson - The Journal of the Acoustical Society of …, 2024 - pubs.aip.org
Speech quality is one of the main foci of speech-related research, where it is frequently
studied with speech intelligibility, another essential measurement. Band-level perceptual …

Acoustic signal enhancement using autoregressive PixelCNN architecture

S Kar - Journal of Integrated Science and Technology, 2024 - pubs.thesciencein.org
Acoustic Signals such as speech and sound are easily degraded by interferences present in
our surroundings. The present work explores the usage of the Pixel CNN architecture for the …

SWIM: An Attention-Only Model for Speech Quality Assessment Under Subjective Variance

IE Kibria, DS Williamson - arXiv preprint arXiv:2410.12675, 2024 - arxiv.org
Speech quality is best evaluated by human feedback using mean opinion scores (MOS).
However, variance in ratings between listeners can introduce noise in the true quality label …

VC-ENHANCE: Speech Restoration with Integrated Noise Suppression and Voice Conversion

K Byun, J Filos, E Visser, S Moon - arXiv preprint arXiv:2409.06126, 2024 - arxiv.org
Noise suppression (NS) algorithms are effective in improving speech quality in many cases.
However, aggressive noise suppression can damage the target speech, reducing both …

Automatic voice quality evaluation method of IVR service in call center based on Stacked Auto Encoder

L Wang, Z Wang, G Zhao, Y Su, J Zhao… - IOP Conference Series …, 2021 - iopscience.iop.org
The basic features extracted by traditional methods for speech quality evaluation are not
clear, which leads to the small correlation coefficient of subjective and objective evaluation …

Optimizing Audio Compression Through Entropy-Controlled Dithering

E Murray, M Kasher, P Spasojevic - arXiv preprint arXiv:2501.02293, 2025 - arxiv.org
This paper explores entropy-controlled dithering techniques in audio compression,
examining the application of standard and modified TPDFs, combined with noise shaping …