2020年10月23日 (五) 07:31的版本

Introduction

• This paper presented a speech information factorization method based on a novel deep generative model that we called factorial discriminative normalization flow.

Qualitative and quantitative experimental results show that compared to all other models, the proposed factorial DNF can retain the class structure corresponding to multiple information factors, and changing one factor will cause little distortion on other factors. This demonstrates that factorial DNF can well factorize speech signal into different information factors.

Members

• Haoran Sun, Lantian Li, Yunqi Cai, Yang Zhang, Thomas Fang Zheng, Dong Wang

Publications

• Haoran Sun, Lantian Li, Yunqi Cai, Yang Zhang, Thomas Fang Zheng, Dong Wang, "Deep Generative Factorization For Speech Signal", 2020. pdf

Source Code

• xxx

Factorial DNF

• xxx

Experiments

Data

• xx

Encoding

• xx

Factor manipulation

• Sampling: figs wavs (right click)

                        Phone Manipulation
  Model    |p(q2|x)|    bap(dim=5)   |   mgc(dim=60) 
   VAE     | 0.013 |     130000      |   160000    
   NF    |      130000      |     500000      |   6200000    
DNF  |      60000       |     300000      |   3580000
 f-DNF  |      1:1.3:0.6   |     1:4:2+      |   1:40:20+

Future Work

• Test factorial DNF on larger datasets.
• Establish general theories for deep generative factorization.