# WEnets: A Convolutional Framework for Evaluating Audio Waveforms

arXiv: https://arxiv.org/abs/1909.09024 · HTML: https://mlsanity.com/paper/1909.09024/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Sep 2019.

## Built on by (most cited first, 2 of 2)

- [Wideband Audio Waveform Evaluation Networks: Efficient, Accurate Estimation of Speech Qualities](https://mlsanity.com/paper/2206.13272/) (2022)
- [Full-Reference Speech Quality Estimation with Attentional Siamese Neural Networks](https://mlsanity.com/paper/2105.00783/) (2021)

## Abstract (arXiv)

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.