Universal Neural Vocoding with Parallel WaveNet
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Speaker-Adaptive Neural Vocoders for Parametric Speech Synthesis Systems2020
- Parallel Wavegan: A Fast Waveform Generation Model Based on Generative Adversarial Networks with Multi-Resolution Spectrogram2020
- Towards Achieving Robust Universal Neural Vocoding2019
- LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech2019
- Waveglow: A Flow-based Generative Network for Speech Synthesis2019
- Fast Spectrogram Inversion Using Multi-Head Convolutional Neural NetworksIEEE Signal Processing Letters, 2018
- Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions2018
- A Comparison of Recent Waveform Generation and Acoustic Modeling Methods for Neural-Network-Based Speech Synthesis2018