Difference between revisions of "Wangd-wiki-article-2020-nb"

From cslt Wiki
Jump to: navigation, search
(以“==2017== * Back to 2017, we set our goal of deep speech factorizatoin. The first paper is published on ICASSP 2018 :* Lantian Li, Dong Wang, Yixiang Chen, Ying Shi,...”为内容创建页面)
 
Line 17: Line 17:
  
 
==2020==
 
==2020==
*
+
* 2019/11/12, CYQ start to work on DNF, using the subspace of the dimension to discriminte speakers [cvss 714]
 +
* 2019/12/20, I start to work on NF with constraint training. More understanding acheived for LDA. [cvss 741]
 +
* 2020/1/23,  I noticed a bug in the DNF code, where the residual space was infact trained, so it is not a true dim-split DNF we hoped.  [cvss 741]
 +
* 2020/1/27,  I conjectured the normalization role of DNF, and informed YQ to perform a full-space experiment. The results are good. [http://166.111.134.19:7777/wangd/public/img/dnf/512-dnf.png] [http://166.111.134.19:7777/wangd/public/img/dnf/512-dnf2.png]
 +
* 2020/1/28, I confirmed the normalization role of LDA for x-vectors. This forms the basic argument for the deep norm paper. [cvss 741]
 +
*
 +
* 2020/02/10, Dong Wang, Deep Generative Models for Discriminative Tasks, CSLT weekly meeting. Present DNF

Revision as of 04:15, 28 March 2020

2017

  • Back to 2017, we set our goal of deep speech factorizatoin. The first paper is published on ICASSP 2018
  • Lantian Li, Dong Wang, Yixiang Chen, Ying Shi, Zhiyuan Tang, "DEEP FACTORIZATION FOR SPEECH SIGNAL", ICASSP 2018. [1]
  • We noticed the problem of soft-max based training, due to the discardxing of the output layers
  • Lantian Li, Zhiyuan Tang, Dong Wang, "FULL-INFO TRAINING FOR DEEP SPEAKER FEATURE LEARNING", ICASSP 2018. [2]

2018

  • 2018/12/26, propose the idea of deep statistical speaker representation. That was based on VAE [3]

2019

  • We noticed the impact of irregulation of deep speaker vectors, and tried to present normalization approaches
  • Yang Zhang and Lantian Li and Dong Wang, VAE-based regularization for deep speaker embedding, Interspeech 2019. [4]
  • 2019/04/20, "Normalization in speaker embedding", Speaker recognition workshop, Kunshan, Shanghai, [5]
  • 2019/07/17, Deep Feature Learning and Normalization for Speaker Recognition, report in India summr school [6]
  • 2019/08/14, present the first proposal that uses flow to model deep speaker featrues. (Report in Huawei group discussion)
  • 2019/10/27, present the initial idea of using flow to perform factorization, CSLT weekly meeting [7]

2020

  • 2019/11/12, CYQ start to work on DNF, using the subspace of the dimension to discriminte speakers [cvss 714]
  • 2019/12/20, I start to work on NF with constraint training. More understanding acheived for LDA. [cvss 741]
  • 2020/1/23, I noticed a bug in the DNF code, where the residual space was infact trained, so it is not a true dim-split DNF we hoped. [cvss 741]
  • 2020/1/27, I conjectured the normalization role of DNF, and informed YQ to perform a full-space experiment. The results are good. [8] [9]
  • 2020/1/28, I confirmed the normalization role of LDA for x-vectors. This forms the basic argument for the deep norm paper. [cvss 741]
  • 2020/02/10, Dong Wang, Deep Generative Models for Discriminative Tasks, CSLT weekly meeting. Present DNF