“Deep Generative Factorization For Speech Signal(ICASSP21)”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
第33行： 第33行：
 
==Factor manipulation==
 
==Factor manipulation==
  
−
:<i>x' = f(f<sup>−1</sup>(x) + µ<sub>A,c<sub>2</sub></sub> − µ<sub>A,c<sub>1</sub></sub>)</i>
+
:x' = f(f<sup>−1</sup>(x) + µ<sub>A,c<sub>2</sub></sub> − µ<sub>A,c<sub>1</sub></sub>)
 
* MLP posteriors on the target class before and after phone/speaker manipulation. ‘f-DNF’ denotes factorial DNF. δ(·) denotes the difference on posteriors p(·|x') and p(·|x)
 
* MLP posteriors on the target class before and after phone/speaker manipulation. ‘f-DNF’ denotes factorial DNF. δ(·) denotes the difference on posteriors p(·|x') and p(·|x)
 
-----------------------------------------------------------------
 
-----------------------------------------------------------------

2020年10月23日 (五) 08:06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

Fdnf tsne.png

Factor manipulation

x' = f(f−1(x) + µA,c2 − µA,c1)
  • MLP posteriors on the target class before and after phone/speaker manipulation. ‘f-DNF’ denotes factorial DNF. δ(·) denotes the difference on posteriors p(·|x') and p(·|x) 
                        Phone Manipulation
 Model |  p(q2|x) | p(q2|x') |  δ(q2)  ||  p(s|x) |  p(s|x') |   δ(s)
  VAE  |   0.013  |  0.312   |  0.299   ||  0.612  |  0.454   |  -0.158 
  NF   |   0.013  |  0.410   |  0.397   ||  0.612  |  0.489   |  -0.123 
  DNF  |   0.013  |  0.619   |  0.606   ||  0.612  |  0.335   |  -0.277  
 f-DNF |   0.013  |  0.636  |  0.623   ||  0.612  |  0.536  |  -0.076 

                        Speaker Manipulation
 Model |  p(s2|x) | p(s2|x') |  δ(s2)  ||  p(q|x) |  p(q|x') |   δ(q)
  VAE  |   0.010  |  0.303   |  0.293   ||  0.520  |  0.509  |  -0.011
  NF   |   0.010  |  0.435   |  0.425   ||  0.520  |  0.484   |  -0.036 
  DNF  |   0.010  |  0.700   |  0.690   ||  0.520  |  0.349   |  -0.171  
 f-DNF |   0.010  |  0.710  |  0.700   ||  0.520  |  0.503   |  -0.017

Future Work

  • Test factorial DNF on larger datasets.
  • Establish general theories for deep generative factorization.
取自“http://index.cslt.org/mediawiki/index.php?title=Deep_Generative_Factorization_For_Speech_Signal(ICASSP21)&oldid=35579”