# Wideband Audio Waveform Evaluation Networks: Efficient, Accurate Estimation of Speech Qualities

arXiv: https://arxiv.org/abs/2206.13272 · HTML: https://mlsanity.com/paper/2206.13272/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 97 references that are in the map.
- First posted on arXiv 27 Jun 2022.

## Builds on (most cited first, 28 of 28)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [Deep Complex Networks](https://mlsanity.com/paper/1705.09792/) (2017)
- [NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets](https://mlsanity.com/paper/2104.09494/) (2021)
- [DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors](https://mlsanity.com/paper/2110.01763/) (2021)
- [MOSNet: Deep Learning based Objective Assessment for Voice Conversion](https://mlsanity.com/paper/1904.08352/) (2019)
- [ViSQOL v3: An Open Source Production Ready Objective Speech and Audio Metric](https://mlsanity.com/paper/2004.09584/) (2020)
- [Generalization Ability of MOS Prediction Networks](https://mlsanity.com/paper/2110.02635/) (2021)
- [THCHS-30 : A Free Chinese Speech Corpus](https://mlsanity.com/paper/1512.01882/) (2015)
- [Quality-Net: An End-to-End Non-intrusive Speech Quality Assessment Model based on BLSTM](https://mlsanity.com/paper/1808.05344/) (2018)
- [MBNet: MOS Prediction for Synthesized Speech with Mean-Bias Network](https://mlsanity.com/paper/2103.00110/) (2021)
- [Deep Learning Based Assessment of Synthetic Speech Naturalness](https://mlsanity.com/paper/2104.11673/) (2021)
- [Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Features](https://mlsanity.com/paper/2111.02363/) (2021)
- [SESQA: semi-supervised learning for speech quality assessment](https://mlsanity.com/paper/2010.00368/) (2020)
- [WARP-Q: Quality Prediction For Generative Neural Speech Codecs](https://mlsanity.com/paper/2102.10449/) (2021)
- [MetricNet: Towards Improved Modeling For Non-Intrusive Speech Quality Assessment](https://mlsanity.com/paper/2104.01227/) (2021)
- [DNN No-Reference PSTN Speech Quality Prediction](https://mlsanity.com/paper/2007.14598/) (2020)
- [A Pyramid Recurrent Network for Predicting Crowdsourced Speech-Quality Ratings of Real-World Signals](https://mlsanity.com/paper/2007.15797/) (2020)
- [An instrumental intelligibility metric based on information theory](https://mlsanity.com/paper/1708.05132/) (2017)
- [Deep MOS Predictor for Synthetic Speech Using Cluster-Based Modeling](https://mlsanity.com/paper/2008.03710/) (2020)
- [Pansori: ASR Corpus Generation from Open Online Video Contents](https://mlsanity.com/paper/1812.09798/) (2018)
- [Bias-Aware Loss for Training Image and Speech Quality Prediction Models from Multiple Datasets](https://mlsanity.com/paper/2104.10217/) (2021)
- [WEnets: A Convolutional Framework for Evaluating Audio Waveforms](https://mlsanity.com/paper/1909.09024/) (2019)
- [More for Less: Non-Intrusive Speech Quality Assessment with Limited Annotations](https://mlsanity.com/paper/2108.08745/) (2021)
- [Controlling the Remixing of Separated Dialogue with a Non-Intrusive Quality Estimate](https://mlsanity.com/paper/2107.10151/) (2021)

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

- [Resource-Efficient Speech Quality Prediction through Quantization Aware Training and Binary Activation Maps](https://mlsanity.com/paper/2407.04578/) (2024)
- [The Perception of Phase Intercept Distortion and its Application in Data Augmentation](https://mlsanity.com/paper/2506.14571/) (2025)

## Abstract (arXiv)

Wideband Audio Waveform Evaluation Networks (WAWEnets) are convolutional neural networks that operate directly on wideband audio waveforms in order to produce evaluations of those waveforms. In the present work these evaluations give qualities of telecommunications speech (e.g., noisiness, intelligibility, overall speech quality). WAWEnets are no-reference networks because they do not require ``reference'' (original or undistorted) versions of the waveforms they evaluate. Our initial WAWEnet publication introduced four WAWEnets and each emulated the output of an established full-reference speech quality or intelligibility estimation algorithm. We have updated the WAWEnet architecture to be more efficient and effective. Here we present a single WAWEnet that closely tracks seven different quality and intelligibility values. We create a second network that additionally tracks four subjective speech quality dimensions. We offer a third network that focuses on just subjective quality scores and achieves very high levels of agreement. This work has leveraged 334 hours of speech in 13 languages, over two million full-reference target values and over 93,000 subjective mean opinion scores. We also interpret the operation of WAWEnets and identify the key to their operation using the language of signal processing: ReLUs strategically move spectral information from non-DC components into the DC component. The DC values of 96 output signals define a vector in a 96-D latent space and this vector is then mapped to a quality or intelligibility value for the input waveform.