Speech quality assessment through MOS using non-matching references

P Manocha, A Kumar - arxiv preprint arxiv:2206.12285, 2022‏ - arxiv.org
Human judgments obtained through Mean Opinion Scores (MOS) are the most reliable way
to assess the quality of speech signals. However, several recent attempts to automatically …

Preference-based training framework for automatic speech quality assessment using deep neural network

CH Hu, Y Yasuda, T Toda - arxiv preprint arxiv:2308.15203, 2023‏ - arxiv.org
One objective of Speech Quality Assessment (SQA) is to estimate the ranks of synthetic
speech systems. However, recent SQA models are typically trained using low-precision …

Audio similarity is unreliable as a proxy for audio quality

P Manocha, Z **, A Finkelstein - arxiv preprint arxiv:2206.13411, 2022‏ - arxiv.org
Many audio processing tasks require perceptual assessment. However, the time and
expense of obtaining``gold standard''human judgments limit the availability of such data …

Non-intrusive speech quality assessment: A survey

K Shen, D Yan, J Hu, Z Ye - Neurocomputing, 2024‏ - Elsevier
Speech quality is a critical consideration for applications such as speech enhancement,
coding, transmission, and synthesis. Accurately evaluating the quality of degraded speech …

Nord: Non-matching reference based relative depth estimation from binaural speech

P Manocha, ID Gebru, A Kumar… - ICASSP 2023-2023 …, 2023‏ - ieeexplore.ieee.org
We propose NORD: a novel framework for estimating the relative depth between two
binaural speech recordings. In contrast to existing depth estimation techniques, ours only …

Personalized Audio Quality Preference Prediction

CC Wang, YC Lin, YT Hsu… - 2023 Asia Pacific Signal …, 2023‏ - ieeexplore.ieee.org
This paper proposes to use both audio input and subject information to predict the
personalized preference of two audio segments with the same content in different qualities …

Do We Need a Reference Signal for Speech Quality Assessment?

P Manocha - 2024‏ - search.proquest.com
This thesis investigates new metrics for assessing speech quality that aim to align more
closely with human auditory perception than current methods. It aims to improve the …

Exploring audio compression in time-frequency domain with sparse CNNs

G Scodeller - 2023‏ - unitesi.unive.it
Audio data compression and decompression is usually implemented via software codecs
which are handmade crafted, often exploiting spectral properties of the signal. In this thesis …