MetricNet: Towards Improved Modeling For Non-Intrusive Speech Quality Assessment

by   Meng Yu, et al.

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 speech quality without any reference, such as in the mean opinion score (MOS) tests. Non-intrusive speech quality assessment has attracted much attention recently due to the lack of access to clean reference signals for objective evaluations in real scenarios. In this paper, we propose a novel non-intrusive speech quality measurement model, MetricNet, which leverages label distribution learning and joint speech reconstruction learning to achieve significantly improved performance compared to the existing non-intrusive speech quality measurement models. We demonstrate that the proposed approach yields promisingly high correlation to the intrusive objective evaluation of speech quality on clean, noisy and processed speech data.



There are no comments yet.


page 1

page 2

page 3

page 4


Quality-Net: An End-to-End Non-intrusive Speech Quality Assessment Model based on BLSTM

Nowadays, most of the objective speech quality assessment tools (e.g., p...

NORESQA – A Framework for Speech Quality Assessment using Non-Matching References

The perceptual task of speech quality assessment (SQA) is a challenging ...

More for Less: Non-Intrusive Speech Quality Assessment with Limited Annotations

Non-intrusive speech quality assessment is a crucial operation in multim...

Improving pronunciation assessment via ordinal regression with anchored reference samples

Sentence level pronunciation assessment is important for Computer Assist...

Exploration of Audio Quality Assessment and Anomaly Localisation Using Attention Models

Many applications of speech technology require more and more audio data....

AQP: An Open Modular Python Platform for Objective Speech and Audio Quality Metrics

Audio quality assessment has been widely researched in the signal proces...

NIMA: Neural Image Assessment

Automatically learned quality assessment for images has recently become ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.