Non-intrusive speech quality assessment with attention-based ResNet-BiLSTM

Speech quality is frequently affected by a variety factors in online conferencing applications, such as background noise, reverberation, packet loss and network jitter. In real scenarios, it is impossible to obtain a clean reference signal for evaluating the quality of the conferencing speech. Therefore, an effective non-intrusive speech quality assessment (NISQA) method is necessary. In this paper, we propose a new network framework for NISQA based on ResNet and BiLSTM. ResNet is utilized to extract local features, while BiLSTM is used to integrate representative features with long-term time dependencies and sequential characteristics. Considering that ResNet may result in the loss of context information when applied to the NISQA task, we propose a variant of ResNet which can preserve the time series information of the conferencing speech. The experimental results demonstrate that the proposed method has a high correlation with the mean opinion score of clean, noisy and processed speech.

Automated summary

Speech quality in online conferencing applications is often influenced by various factors like background noise, reverberation, packet loss, and network jitter. It is challenging to evaluate the quality of conferencing speech without a clean reference signal. Therefore, an effective non-intrusive speech quality assessment method is needed. This paper proposes a network framework for NISQA based on ResNet and BiLSTM, which can extract local features and integrate representative features with long-term time dependencies and sequential characteristics. Experimental results show a strong correlation between the proposed method and the mean opinion score of clean, noisy, and processed speech.