WEnets: A Convolutional Framework for Evaluating Audio Waveforms

Understand

We describe a new convolutional framework for waveform evaluation, WEnets, and build a Narrowband Audio Waveform Evaluation Network, or NAWEnet, using this framework.

• NAWEnet is single-ended (or no-reference) and was trained three separate times in order to emulate PESQ, POLQA, or STOI with testing correlations 0.95, 0.92, and 0.95, respectively when training on only 50% of available data and testing on 40%.
• Stacks of 1-D convolutional layers and non-linear downsampling learn which features are important for quality or intelligibility estimation.
• This straightforward architecture simplifies the interpretation of its inner workings and paves the way for future investigations into higher sample rates and accurate no-reference subjective speech quality predictions.