Universal Neural Vocoding with Parallel WaveNet
This provides a practical solution for speech synthesis applications needing broad adaptability, though it appears incremental as an extension of Parallel WaveNet.
The authors tackled the problem of creating a universal neural vocoder for speech synthesis across diverse speakers, languages, and styles, achieving real-time high-quality results that significantly outperform speaker-dependent vocoders and other neural architectures.
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.