Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Kexin Zhao

DiffWave: A Versatile Diffusion Model for Audio Synthesis


Sep 21, 2020
Zhifeng Kong, Wei Ping, Jiaji Huang, Kexin Zhao, Bryan Catanzaro


  Access Paper or Ask Questions

WaveFlow: A Compact Flow-based Model for Raw Audio


Jan 10, 2020
Wei Ping, Kainan Peng, Kexin Zhao, Zhao Song


  Access Paper or Ask Questions

Multi-Speaker End-to-End Speech Synthesis


Jul 09, 2019
Jihyun Park, Kexin Zhao, Kainan Peng, Wei Ping


  Access Paper or Ask Questions

Parallel Neural Text-to-Speech


Jun 05, 2019
Kainan Peng, Wei Ping, Zhao Song, Kexin Zhao

* v2: we improve the synthesis speed of ParaNet by sharing the attention masking at all attention layers 

  Access Paper or Ask Questions

Trace norm regularization and faster inference for embedded speech recognition RNNs


Feb 06, 2018
Markus Kliegl, Siddharth Goyal, Kexin Zhao, Kavya Srinet, Mohammad Shoeybi

* Our optimized inference kernels are available at: https://github.com/PaddlePaddle/farm (Note: This paper was submitted to, but rejected from, ICLR 2018. We believe it may still be of value to others. Please see the discussion here: https://openreview.net/forum?id=B1tC-LT6W

  Access Paper or Ask Questions