Universal Neural Vocoding with Parallel WaveNet

02/01/2021
by   Yunlong Jiao, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/17/2022

Any-speaker Adaptive Text-To-Speech Synthesis with Diffusion Models

There has been a significant progress in Text-To-Speech (TTS) synthesis ...
research
05/08/2019

Capture, Learning, and Synthesis of 3D Speaking Styles

Audio-driven 3D facial animation has been widely explored, but achieving...
research
09/19/2023

USED: Universal Speaker Extraction and Diarization

Speaker extraction and diarization are two crucial enabling techniques f...
research
05/30/2022

StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech Synthesis

Text-to-Speech (TTS) has recently seen great progress in synthesizing hi...
research
02/22/2022

Neural Speech Synthesis on a Shoestring: Improving the Efficiency of LPCNet

Neural speech synthesis models can synthesize high quality speech but ty...
research
11/15/2018

Robust universal neural vocoding

This paper introduces a robust universal neural vocoder trained with 74 ...
research
10/07/2021

Towards Universal Neural Vocoding with a Multi-band Excited WaveNet

This paper introduces the Multi-Band Excited WaveNet a neural vocoder fo...

Please sign up or login with your details

Forgot password? Click here to reset