ISCA Archive Interspeech 2021
ISCA Archive Interspeech 2021

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

Meng Yu, Chunlei Zhang, Yong Xu, Shi-Xiong Zhang, Dong Yu

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.

doi: 10.21437/Interspeech.2021-659

Cite as: Yu, M., Zhang, C., Xu, Y., Zhang, S.-X., Yu, D. (2021) MetricNet: Towards Improved Modeling For Non-Intrusive Speech Quality Assessment. Proc. Interspeech 2021, 2142-2146, doi: 10.21437/Interspeech.2021-659

  author={Meng Yu and Chunlei Zhang and Yong Xu and Shi-Xiong Zhang and Dong Yu},
  title={{MetricNet: Towards Improved Modeling For Non-Intrusive Speech Quality Assessment}},
  booktitle={Proc. Interspeech 2021},