Universal Neural Vocoding with Parallel Wavenet

We present a universal neural vocoder based on Parallel WaveNet, with an additional conditioning network called Audio Encoder. Our universal vocoder offers real-time high-quality speech synthesis on a wide range of use cases. We tested it on 43 internal speakers of diverse age and gender, speaking 2...

Full description

Saved in:
Bibliographic Details
Published inICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 6044 - 6048
Main Authors Jiao, Yunlong, Gabrys, Adam, Tinchev, Georgi, Putrycz, Bartosz, Korzekwa, Daniel, Klimkov, Viacheslav
Format Conference Proceeding
LanguageEnglish
Published IEEE 06.06.2021
Subjects
Benchmark testing
Conferences
Neural vocoder
Production
Real-time systems
Scalability
Signal processing
Text-to-speech
Training
Vocoders
Online AccessGet full text

Cover

More Information
Summary:We present a universal neural vocoder based on Parallel WaveNet, with an additional conditioning network called Audio Encoder. Our universal vocoder offers real-time high-quality speech synthesis on a wide range of use cases. We tested it on 43 internal speakers of diverse age and gender, speaking 20 languages in 17 unique styles, of which 7 voices and 5 styles were not exposed during training. We show that the proposed universal vocoder significantly outperforms speaker-dependent vocoders overall. We also show that the proposed vocoder outperforms several existing neural vocoder architectures in terms of naturalness and universality. These findings are consistent when we further test on more than 300 open-source voices.
ISSN:2379-190X
DOI:10.1109/ICASSP39728.2021.9414444