[HTML][HTML] Nonintrusive objective measurement of speech intelligibility: A review of methodology

Y Feng, F Chen - Biomedical Signal Processing and Control, 2022 - Elsevier
Speech intelligibility (SI) measurement has attracted great attention in the speech
communication community over the last decade. It is a critical consideration for speech …

ASR-based speech intelligibility prediction: A review

M Karbasi, D Kolossa - Hearing Research, 2022 - Elsevier
Various types of methods and approaches are available to predict the intelligibility of speech
signals, but many of these still suffer from two major problems: first, their required prior …

Deep learning-based non-intrusive multi-objective speech assessment model with cross-domain features

RE Zezario, SW Fu, F Chen, CS Fuh… - … on Audio, Speech …, 2022 - ieeexplore.ieee.org
This study proposes a cross-domain multi-objective speech assessment model, called
MOSA-Net, which can simultaneously estimate the speech quality, intelligibility, and …

NORESQA: A framework for speech quality assessment using non-matching references

P Manocha, B Xu, A Kumar - Advances in neural …, 2021 - proceedings.neurips.cc
The perceptual task of speech quality assessment (SQA) is a challenging task for machines
to do. Objective SQA methods that rely on the availability of the corresponding clean …

Conferencingspeech 2022 challenge: Non-intrusive objective speech quality assessment (NISQA) challenge for online conferencing applications

G Yi, W Xiao, Y Xiao, B Naderi, S Möller… - arXiv preprint arXiv …, 2022 - arxiv.org
With the advances in speech communication systems such as online conferencing
applications, we can seamlessly work with people regardless of where they are. However …

An attention enhanced multi-task model for objective speech assessment in real-world environments

X Dong, DS Williamson - ICASSP 2020-2020 IEEE …, 2020 - ieeexplore.ieee.org
Computational objective metrics that use reference signals have been shown to be effective
forms of speech assessment in simulated environments, since they are correlated with …

Metricnet: Towards improved modeling for non-intrusive speech quality assessment

M Yu, C Zhang, Y Xu, S Zhang, D Yu - arXiv preprint arXiv:2104.01227, 2021 - arxiv.org
The objective speech quality assessment is usually conducted by comparing received
speech signal with its clean reference, while human beings are capable of evaluating the …

Unsupervised uncertainty measures of automatic speech recognition for non-intrusive speech intelligibility prediction

Z Tu, N Ma, J Barker - arXiv preprint arXiv:2204.04288, 2022 - arxiv.org
Non-intrusive intelligibility prediction is important for its application in realistic scenarios,
where a clean reference signal is difficult to access. The construction of many non-intrusive …

InQSS: a speech intelligibility and quality assessment model using a multi-task learning network

YW Chen, Y Tsao - arXiv preprint arXiv:2111.02585, 2021 - arxiv.org
Speech intelligibility and quality assessment models are essential tools for researchers to
evaluate and improve speech processing models. However, only a few studies have …

Audio similarity is unreliable as a proxy for audio quality

P Manocha, Z Jin, 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 …