SnakeGAN: A Universal Vocoder Leveraging DDSP Prior Knowledge and Periodic Inductive Bias

no code implementations • 14 Sep 2023 • Sipan Li, Songxiang Liu, Luwen Zhang, Xiang Li, Yanyao Bian, Chao Weng, Zhiyong Wu, Helen Meng

However, it is still challenging to train a universal vocoder which can generalize well to out-of-domain (OOD) scenarios, such as unseen speaking styles, non-speech vocalization, singing, and musical pieces.

Audio Synthesis Generative Adversarial Network +1