Wangd-wiki-article-2020-nb - 版本历史

Cslt：/* 2020 */

2020-05-23T08:37:19Z

‎2020

2020年5月9日 (六) 08:07 Cslt

2020-05-09T08:07:18Z

2020年4月24日 (五) 12:56 Cslt

2020-04-24T12:56:01Z

2020年4月21日 (二) 11:12 Cslt

2020-04-21T11:12:15Z

2020年4月8日 (三) 13:18 Cslt

2020-04-08T13:18:51Z

2020年3月28日 (六) 05:32 Cslt

2020-03-28T05:32:23Z

2020年3月28日 (六) 05:27 Cslt

2020-03-28T05:27:48Z

2020年3月28日 (六) 05:22 Cslt

2020-03-28T05:22:09Z

2020年3月28日 (六) 03:15 Cslt

2020-03-28T03:15:04Z

Cslt：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

2020-03-28T02:48:25Z

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

新页面

==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==
*

←上一版本		2020年5月23日 (六) 08:37的版本
第40行：		第40行：
	* 2020/4/24, Lantian demonstrated PLDA and linear NDA are equivalent using x-vector, and found the importance of length norm.		* 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.		* 2020/5/05, 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.

←上一版本		2020年5月9日 (六) 08:07的版本
第39行：		第39行：
	* 2020/4/21, I proposed to use Bayesian denoising with noise NF, and the architecture for speech separation based on the Bayesian inference.		* 2020/4/21, 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.		* 2020/4/24, 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.

←上一版本		2020年4月24日 (五) 12:56的版本
第38行：		第38行：
	* 2020/4/20, Zhiyuan demonstrated the capability of Bayesian denoising with white noise		* 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.		* 2020/4/21, 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.

←上一版本		2020年4月21日 (二) 11:12的版本
第33行：		第33行：
	* 2020/4/06, I proposed the VAE-like NDA		* 2020/4/06, I proposed the VAE-like NDA
	* 2020/4/08, Yunqi demonstrated VAE-like NDA with x-vector		* 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.

@@ 第17行： / 第17行： @@
 ==2020==
-* 2019/11/12, CYQ start to work on DNF, using the subspace of the dimension to discriminte speakers [cvss 714]
+* 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]
@@ 第29行： / 第29行： @@
 * 2020/3/27,  I extend the NDA to neural linear Gaussian model.
 * 2020/3/28,  I extend the NDA to neural Bayesian model.

@@ 第25行： / 第25行： @@
 * 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.
+* 2020/3/21,  I coined the NDA model, and completed the verification in 3 hours. This model can be used for scoring.
 * 2020/3/27,  I extend the NDA to neural linear Gaussian model.
 * 2020/3/28,  I extend the NDA to neural Bayesian model.

@@ 第22行： / 第22行： @@
 * 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]
 * 2020/2/18,  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.
-* 2020/02/10, Dong Wang, Deep Generative Models for Discriminative Tasks, CSLT weekly meeting. Present DNF
+* 2020/3/21,  I coined the NDA model, and completed the verification in 3 hours.

←上一版本		2020年3月28日 (六) 03:15的版本
第17行：		第17行：

	==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