Wawenets: A No-Reference Convolutional Waveform-Based Approach to Estimating Narrowband and Wideband Speech Quality
Authors:
- 1 May 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 331-335
Abstract
Building on prior work we have developed a no-reference (NR) waveform-based convolutional neural network (CNN) architecture that can accurately estimate speech quality or intelligibility of narrowband and wideband speech segments. These Wideband Audio Waveform Evaluation Networks, or WAWEnets, achieve very high per-speech-segment correlation (ρ seg ≥ 0.92, RMSE ≤ 0.38) to established full-reference quality and intelligibility estimators (PESQ, POLQA, PEMO, STOI) based on over 17 hours of speech from 127 previously unseen talkers speaking in 13 different languages; just 10% of our total data. NR correlations at this level across such a broad scope are unprecedented. This achievement was made possible by using full-reference estimates as training targets so that WAWEnets could learn implicit undistorted speech models and exploit them to produce accurate NR estimates.Keywords
This publication has 16 references indexed in Scilit:
- Learning-Based Reference-Free Speech Quality Measures for Hearing Aid ApplicationsIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2018
- Blind Estimation of the Speech Transmission Index for Speech Quality Prediction2018
- Single-ended prediction of listening effort using deep neural networksHearing Research, 2018
- Predicting speech intelligibility with deep neural networksComputer Speech & Language, 2018
- Novel deep autoencoder features for non-intrusive speech quality assessment2016
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- An Algorithm for Intelligibility Prediction of Time–Frequency Weighted Noisy SpeechIEEE Transactions on Audio, Speech, and Language Processing, 2011
- Subjective and Objective Quality Assessment of Audio Source SeparationIEEE Transactions on Audio, Speech, and Language Processing, 2011
- Single-Ended Speech Quality Measurement Using Machine Learning MethodsIEEE Transactions on Audio, Speech, and Language Processing, 2006
- PEMO-Q—A New Method for Objective Audio Quality Assessment Using a Model of Auditory PerceptionIEEE Transactions on Audio, Speech, and Language Processing, 2006