Intrusive and Non-Intrusive Perceptual Speech Quality Assessment Using a Convolutional Neural Network
Authors:
- 1 October 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 85-89
Abstract
Speech quality, as perceived by humans, is an important performance metric for telephony and voice services. It is typically measured through subjective listening tests, which can be tedious and expensive. Algorithms such as PESQ and POLQA serve as a computational proxy for subjective listening tests. Here we propose using a convolutional neural network to predict the perceived quality of speech with noise, reverberation, and distortions, both intrusively and non-intrusively, i.e., with and without a clean reference signal. The network model is trained and evaluated on a corpus of about ten thousand utterances labeled by human listeners to derive a Mean Opinion Score (MOS) for each utterance. It is shown to provide more accurate MOS estimates than existing speech quality metrics, including PESQ and POLQA. The proposed method reduces the root mean squared error from 0.48 to 0.35 MOS points and increases the Pearson correlation from 0.78 to 0.89 compared to the state-of-the-art POLQA algorithm.Keywords
This publication has 11 references indexed in Scilit:
- Blind Estimation of the Speech Transmission Index for Speech Quality Prediction2018
- CNTK2016
- A data-driven non-intrusive measure of speech quality and intelligibilitySpeech Communication, 2016
- The Hearing-Aid Speech Quality Index (HASQI) Version 2Journal of the Audio Engineering Society, 2014
- A Non-Intrusive Quality and Intelligibility Measure of Reverberant and Dereverberated SpeechIEEE Transactions on Audio, Speech, and Language Processing, 2010
- Quality assessment of interactive voice applicationsComputer Networks, 2008
- Extreme learning machine: Theory and applicationsNeurocomputing, 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
- Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs2002
- New objective measures for characterisation of noise suppression algorithms2002