Warp-Q: Quality Prediction for Generative Neural Speech Codecs
Authors:
- 6 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 401-405
Abstract
Good speech quality has been achieved using waveform matching and parametric reconstruction coders. Recently developed very low bit rate generative codecs can reconstruct high quality wideband speech with bit streams less than 3 kb/s. These codecs use a DNN with parametric input to synthesise high quality speech outputs. Existing objective speech quality models (e.g., POLQA, ViSQOL) do not accurately predict the quality of coded speech from these generative models underestimating quality due to signal differences not highlighted in subjective listening tests. We present WARP-Q, a full-reference objective speech quality metric that uses dynamic time warping cost for MFCC speech representations. It is robust to small perceptual signal changes. Evaluation using waveform matching, parametric and generative neural vocoder based codecs as well as channel and environmental noise shows that WARP-Q has better correlation and codec quality ranking for novel codecs compared to traditional metrics in addition to versatility for general quality assessment scenarios.Keywords
All Related Versions
Funding Information
- Science Foundation Ireland
This publication has 15 references indexed in Scilit:
- Waveglow: A Flow-based Generative Network for Speech Synthesis2019
- High-quality Speech Coding with Sample RNN2019
- Wavenet Based Low Rate Speech Coding2018
- Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions2018
- ViSQOL: an objective speech quality modelEURASIP Journal on Audio, Speech, and Music Processing, 2015
- TCD-VoIP, a research database of degraded speech for assessing quality in VoIP applications2015
- librosa: Audio and Music Signal Analysis in Python2015
- Speech Quality Estimation: Models and TrendsIEEE Signal Processing Magazine, 2011
- Chroma Binary Similarity and Local Alignment Applied to Cover Song IdentificationIEEE Transactions on Audio, Speech, and Language Processing, 2008
- A 2.4 kbit/s MELP coder candidate for the new U.S. Federal Standard2002