“Flow-based Speech Analysis”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
Publications
Publications
 
(相同用户的3个中间修订版本未显示)
第13行: 第13行:
 
===Publications===
 
===Publications===
  
* Haoran Sun, Yunqi Cai, Lantian Li, Dong Wang, "On Investigation of Unsupervised Speech Factorization Based in Normalization Flow", 2019. [[文件:Flow.pdf|pdf]
+
* Haoran Sun, Yunqi Cai, Lantian Li, Dong Wang, "On Investigation of Unsupervised Speech Factorization Based in Normalization Flow", 2019. [[媒体文件:Flow.pdf|pdf]]
  
 
===Source Code===
 
===Source Code===

2019年10月29日 (二) 12:58的最后版本

Introduction

  • We present a preliminary investigation on unsupervised speech factorization based on the normalization flow model.

This model constructs a complex invertible transform, by which we can project speech segments into a latent code space where the distribution is a simple diagonal Gaussian.

  • Our preliminary investigation on the TIMIT database shows that this code space exhibits favorable properties such as denseness and pseudo linearity,

and perceptually important factors such as phonetic content and speaker trait can be represented as particular directions within the code space.

  • Index Terms: speech factorization, normalization flow, deep learning

Members

  • Dong Wang, Haoran Sun, Yunqi Cai, Lantian Li

Publications

  • Haoran Sun, Yunqi Cai, Lantian Li, Dong Wang, "On Investigation of Unsupervised Speech Factorization Based in Normalization Flow", 2019. pdf

Source Code

  • Glow model implemented by Yuki-Chai in PyTorch. glow-pytorch

Experiments

  • Right click "figs" or "wavs" and select "save as" to save the spectrogram figures or related audio files.

Fig3 flow.jpg

  • Interpolation: figs wavs (right click)

Fig4 flow.jpg

Fig5 flow.jpg

Future Work

  • To conduct more thorough studies on large databases and continuous speech.
  • To investigate discriminative flow models which take class information into consideration.