View source for Wangd-wiki-article-2020-nb

==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. [http://wangd.cslt.org/public/pdf/spkfact.pdf]
* 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. [https://arxiv.org/abs/1711.00366]

==2018==
* 2018/12/26, propose the idea of deep statistical speaker representation. That was based on VAE [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/4/48/V.pdf]

==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. [https://arxiv.org/abs/1904.03617]
* 2019/04/20, "Normalization in speaker embedding", Speaker recognition workshop, Kunshan, Shanghai, [http://wangd.cslt.org/talks/pdf/kunshan.pptx]
* 2019/07/17, Deep Feature Learning and Normalization for Speaker Recognition, report in India summr school [http://wangd.cslt.org/talks/pdf/india.pdf]
* 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 [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/f/f9/Back_to_Matrix.pdf]

==2020==
* 2019/11/12, Yunqi 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]
* 2020/2/10,  Dong Wang, Deep Generative Models for Discriminative Tasks, CSLT weekly meeting. Present DNF
* 2020/2/18,  Deep norm paper submitted to IEEE Transactions. 
* 2020/2/24,  I start working on optimal scoring for SRE, and establish the NL theory. The paper was submitted on 3.17 to APSIPA transaction.
* 2020/3/21,  I coined the NDA model, and completed the verification in 3 hours. This model can be used for scoring.
* 2020/3/25,  I designed the VAE-NF model, using NF to perform the generation net in VAE. It can generate more informative latent codes but the theory is not completed. 
* 2020/3/27,  I extend the NDA to neural linear Gaussian model.
* 2020/3/28,  I extend the NDA to neural Bayesian model.
* 2020/4/01,  I started to work on NPCA. A simple L2 constraind algorithm was obtained, but this seems cannot find flexible manifold. Stop the work on 04/04.
* 2020/4/04,   Lantian demonstrated the NDA model with x-vector
* 2020/4/06,  I proposed the VAE-like NDA
* 2020/4/08,  Yunqi demonstrated VAE-like NDA with x-vector
* 2020/4/10,  I found the convergnece of the NDA model in simulation test (convergence of SB)
* 2020/4/12,  I proposed the Bayesian denoising approach
* 2020/4/18,  Lantian demonstrated the convergence of the NDA model with x vector
* 2020/4/20,  Zhiyuan demonstrated the capability of Bayesian denoising with white noise
* 2020/4/21,  I proposed to use Bayesian denoising with noise NF, and the architecture for speech separation based on the Bayesian inference.
* 2020/4/24,  Lantian demonstrated PLDA and linear NDA are equivalent using x-vector, and found the importance of length norm.
* 2020/5/05, Dong Wang designed the discriminative training method for DNF, using small set of x-vector to test.
* 2020/5/18,  Yunqi demonstrated DT training for DNF, with the entropy contraint.
* 2020/5/23,  Dong Wang proposed multiple flow based denoising.