Metricnet: Towards Improved Modeling For Non-intrusive Speech Quality Assessment

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyu2021metricnet

Related papers

• Quality-net: An End-to-end Non-intrusive Speech Quality Assessment Model Based On BLSTM (2018)15.62
• Multi-task Pseudo-label Learning For Non-intrusive Speech Quality Assessment Model (2023)0.00
• Non-intrusive Speech Quality Assessment Using Neural Networks (2019)13.74
• Multi-cmgan+/+: Leveraging Multi-objective Speech Quality Metric Prediction For Speech Enhancement (2023)0.00
• More For Less: Non-intrusive Speech Quality Assessment With Limited Annotations (2021)7.16
• Stoi-net: A Deep Learning Based Non-intrusive Speech Intelligibility Assessment Model (2020)0.00
• On The Behavior Of Intrusive And Non-intrusive Speech Enhancement Metrics In Predictive And Generative Settings (2023)0.00
• Mosnet: Deep Learning Based Objective Assessment For Voice Conversion (2019)16.90