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

Abstract

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 reference have been the primary go-to approaches for SQA. Clearly, these methods fail in real-world scenarios where the ground truth clean references are not available. In recent years, non-intrusive methods that train neural networks to predict ratings or scores have attracted much attention, but they suffer from several shortcomings such as lack of robustness, reliance on labeled data for training and so on. In this work, we propose a new direction for speech quality assessment. Inspired by human's innate ability to compare and assess the quality of speech signals even when they have non-matching contents, we propose a novel framework that predicts a subjective relative quality score for the given speech signal with respect to any provided reference without using any subjective data. We show that neural networks trained using our framework produce scores that correlate well with subjective mean opinion scores (MOS) and are also competitive to methods such as DNSMOS, which explicitly relies on MOS from humans for training networks. Moreover, our method also provides a natural way to embed quality-related information in neural networks, which we show is helpful for downstream tasks such as speech enhancement.

References in corpus (17)

• Adam: A Method for Stochastic Optimization
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
• Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
• When Does Label Smoothing Help?
• Contrastive Representation Learning: A Framework and Review
• MOSNet: Deep Learning based Objective Assessment for Voice Conversion
• MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement
• The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods
• The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Speech Quality and Testing Framework
• AutoMOS: Learning a non-intrusive assessor of naturalness-of-speech
• Quality-Net: An End-to-End Non-intrusive Speech Quality Assessment Model based on BLSTM
• A Sequential Self Teaching Approach for Improving Generalization in Sound Event Recognition
• HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks
• Self-Supervised Learning from Contrastive Mixtures for Personalized Speech Enhancement
• MetricNet: Towards Improved Modeling For Non-Intrusive Speech Quality Assessment
• A Differentiable Perceptual Audio Metric Learned from Just Noticeable Differences

Cited by in corpus (2)

• EBEN: Extreme bandwidth extension network applied to speech signals captured with noise-resilient body-conduction microphones
• Preference-based training framework for automatic speech quality assessment using deep neural network