Deep Speech Factorization-2 - 版本历史

Cslt：/* Flow Model */

2020-04-12T12:14:32Z

‎Flow Model

2020年4月12日 (日) 12:13 Cslt

2020-04-12T12:13:47Z

Cslt：/* VAE Model */

2020-04-12T06:43:22Z

‎VAE Model

2020年4月12日 (日) 06:41 Cslt

2020-04-12T06:41:52Z

2020年4月12日 (日) 06:41 Cslt

2020-04-12T06:41:05Z

2020年3月29日 (日) 04:58 Caiyq

2020-03-29T04:58:04Z

2020年3月29日 (日) 02:09 Caiyq

2020-03-29T02:09:39Z

2020年3月29日 (日) 02:08 Caiyq

2020-03-29T02:08:07Z

2019年12月11日 (三) 01:45 Cslt

2019-12-11T01:45:36Z

Sunhaoran：/* Talks */

2019-11-04T06:02:13Z

‎Talks

@@ 第135行： / 第135行： @@
 * Research
+:2020
 :# Structured Output Learning with Conditional Generative Flows, [https://arxiv.org/pdf/1905.13288.pdf]

@@ 第55行： / 第55行： @@
 =Further reading=
-===Old===
+==Old==
 # Barlow, Unsupervised learning, Neural computation, 1989. [http://wangd.cslt.org/refs/Barlow_1989.pdf]
@@ 第67行： / 第67行： @@
 # Aapo Hyvarinen and Petteri Pajunen, "Nonlinear independent component analysis: Existence and uniqueness results", Neural networks, 1999. [https://www.sciencedirect.com/science/article/pii/S0893608098001403]
-===Linguistics===
+==Linguistics==
 # Hiroya Fujisaki, “Prosody, models, and spontaneous speech,” in Computing prosody, pp. 27–42. Springer,1997.
-===ML===
+==ML==
 # Laurent Dinh David Krueger Yoshua Bengio,"NICE: NON-LINEAR INDEPENDENT COMPONENTS ESTIMATION", ICLR 2015 [https://arxiv.org/pdf/1410.8516.pdf]
@@ 第89行： / 第89行： @@
-===ASR===
+==ASR==
 # Chan et al., "Listen, attend and spell: A neural network for large vocabulary conversational speech recognition", 2016.
@@ 第98行： / 第98行： @@
 # Tsai et al., "Learning Factorized Multimodal Representations", 2019
-===SID===
+==SID==
 # E. Variani, X. Lei, E. McDermott, I. Lopez Moreno, and J. Gonzalez-Dominguez, “Deep neural networks for small footprint text-dependent speaker verification,”2014.
 # G. Heigold, I. Moreno, S. Bengio, and N. Shazeer, “End-to-end textdependent speaker verification,” 2016.
-===TTS===
+==TTS==
 # Wang,  et al., "Tacotron: A fully end-to-end text-to-speech synthesis model." CoRR, abs/1703.10135, 2017.
@@ 第112行： / 第112行： @@
 # Wei-Ning Hsu, DISENTANGLING CORRELATED SPEAKER AND NOISE FOR SPEECH SYNTHESIS VIA DATA AUGMENTATION AND ADVERSARIAL FACTORIZATION, ICASSP 2019.
-===Flow Model===
+==Flow Model==
 * Overview
 :* Papamakarios, "Normalizing Flows for Probabilistic Modeling and Inference" [https://arxiv.org/pdf/1912.02762.pdf]
@@ 第133行： / 第133行： @@
 ::*  Danilo Jimenez Rezende et al., Variational Inference with Normalizing Flows, [https://arxiv.org/abs/1505.05770] (First apply to variational inference)
-===VAE Model===
+* Research
 -2015
@@ 第177行： / 第183行： @@
 :# 2019 Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapse, [https://www.bibsonomy.org/bibtex/4700607448c23d9abeb9cb387c852f93]
 :# 2019 Learning Hierarchical Priors in VAEs, [https://www.semanticscholar.org/paper/Learning-Hierarchical-Priors-in-VAEs-Klushyn-Chen/6bb61321d45960f18098568f54eeb1ce413b7abe]

@@ 第134行： / 第134行： @@
 ===VAE Model===
 :# 2014 Auto-Encoding Variational Bayes, [https://arxiv.org/abs/1312.6114]  (First composition)
 :# 2015 The Variational Fair Autoencoder, [https://arxiv.org/abs/1511.00830]
 :# 2015 Learning Structured Output Representation using Deep Conditional Generative Models, [https://pdfs.semanticscholar.org/3f25/e17eb717e5894e0404ea634451332f85d287.pdf?_ga 2.204795282.388480789.1585412171-912935264.1544959736]
-:* 2017 Variational Lossy Autoencoder, [https://arxiv.org/abs/1611.02731]
+:# 2017 Variational Lossy Autoencoder, [https://arxiv.org/abs/1611.02731]
-:* 2017 Grammar Variational Autoencoder, [https://arxiv.org/abs/1703.01925]
+:# 2017 Grammar Variational Autoencoder, [https://arxiv.org/abs/1703.01925]
-:* 2017 beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework, [https://www.semanticscholar.org/paper/beta-VAE%3A-Learning-Basic-Visual-Concepts-with-a-Higgins-Matthey/a90226c41b79f8b06007609f39f82757073641e2]
+:# 2017 beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework, [https://www.semanticscholar.org/paper/beta-VAE%3A-Learning-Basic-Visual-Concepts-with-a-Higgins-Matthey/a90226c41b79f8b06007609f39f82757073641e2]
-:* 2017 Deep Variational Information Bottleneck, [https://arxiv.org/abs/1612.00410]
+:# 2017 Deep Variational Information Bottleneck, [https://arxiv.org/abs/1612.00410]
-:* 2017 Understanding disentangling in β-VAE, [https://arxiv.org/abs/1804.03599]
+:# 2017 Understanding disentangling in β-VAE, [https://arxiv.org/abs/1804.03599]
-:* 2017 Deepcoder: Semi-parametric variational autoencoders for automatic facial action coding, [http://openaccess.thecvf.com/content_ICCV_2017/papers/Tran_DeepCoder_Semi-Parametric_Variational_ICCV_2017_paper.pdf]
+:# 2017 Deepcoder: Semi-parametric variational autoencoders for automatic facial action coding, [http://openaccess.thecvf.com/content_ICCV_2017/papers/Tran_DeepCoder_Semi-Parametric_Variational_ICCV_2017_paper.pdf]
-:* 2017 Hierarchical Variational Autoencoders for Music, [https://nips2017creativity.github.io/doc/Hierarchical_Variational_Autoencoders_for_Music.pdf]
+:# 2017 Hierarchical Variational Autoencoders for Music, [https://nips2017creativity.github.io/doc/Hierarchical_Variational_Autoencoders_for_Music.pdf]
-:* 2017 A Classifying Variational Autoencoder with Application to Polyphonic Music Generation, [https://arxiv.org/pdf/1711.07050.pdf]
+:# 2017 A Classifying Variational Autoencoder with Application to Polyphonic Music Generation, [https://arxiv.org/pdf/1711.07050.pdf]
-:* 2018 VAE with a VampPrior, [https://arxiv.org/abs/1705.07120]
-:* 2018 Hyperspherical Variational Auto-Encoders, [http://auai.org/uai2018/proceedings/papers/309.pdf]
-:* 2018 Isolating Sources of Disentanglement in Variational Autoencoders, [https://arxiv.org/pdf/1802.04942v2.pdf]
-:* 2018 Variational Autoencoders Pursue PCA Directions, [http://openaccess.thecvf.com/content_CVPR_2019/papers/Rolinek_Variational_Autoencoders_Pursue_PCA_Directions_by_Accident_CVPR_2019_paper.pdf]
-:* 2018 Variational Autoencoders for Collaborative Filtering, [https://dl.acm.org/doi/10.1145/3178876.3186150]
-:* 2018 Learning Latent Subspaces in Variational Autoencoders, [http://www.cs.toronto.edu/~zemel/documents/Conditional_Subspace_VAE_all.pdf]
-:* 2019 Structured Disentangled Representations, [http://proceedings.mlr.press/v89/esmaeili19a.html]
-:* 2019 Variational Autoencoders with Jointly Optimized Latent Dependency Structure, [https://www.cs.sfu.ca/~mori/research/papers/he-iclr19.pdf]
-:* 2019 Correlated Variational Auto-Encoders, [http://proceedings.mlr.press/v97/tang19b/tang19b.pdf]
-:* 2019 From Variational to Deterministic Autoencoders, [https://arxiv.org/pdf/1903.12436v1.pdf]
-:* 2019 Variational Laplace Autoencoders, [http://proceedings.mlr.press/v97/park19a.html]
-:* 2019 Disentangling Disentanglement in Variational Autoencoders, [http://proceedings.mlr.press/v97/mathieu19a.html]
-:* 2019 Modeling assumptions and evaluation schemes: On the assessment of deep latent variable models, [http://openaccess.thecvf.com/content_CVPRW_2019/papers/Uncertainty%20and%20Robustness%20in%20Deep%20Visual%20Learning/Butepage_Modeling_assumptions_and_evaluation_schemes_On_the_assessment_of_deep_CVPRW_2019_paper.pdf]
-:* 2019 Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders, [http://openaccess.thecvf.com/content_CVPR_2019/html/Schonfeld_Generalized_Zero-_and_Few-Shot_Learning_via_Aligned_Variational_Autoencoders_CVPR_2019_paper.html]
-:* 2019 A Joint Generative Model for Zero-Shot Learning, [https://link.springer.com/chapter/10.1007%2F978-3-030-11018-5_50]
-:* 2019 A Contrastive Divergence for Combining Variational Inference and MCMC, [http://proceedings.mlr.press/v97/ruiz19a.html]
-:* 2019 Resisting Adversarial Attacks Using Gaussian Mixture Variational Autoencoders, [https://aaai.org/ojs/index.php/AAAI/article/view/3828]
-:* 2019 Hierarchical Decompositional Mixtures of Variational Autoencoders, [http://proceedings.mlr.press/v97/tan19b.html]
-:* 2019 Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs, [http://proceedings.mlr.press/v97/balaji19a.html]
-:* 2019 InfoVAE: Balancing Learning and Inference in Variational Autoencoders, [https://aimagazine.org/ojs/index.php/AAAI/article/view/4538]
-:* 2019 Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing, [https://aclweb.org/anthology/papers/N/N19/N19-1021/]
-:* 2019 Sparse Multi-Channel Variational Autoencoder for the Joint Analysis of Heterogeneous Data, [http://proceedings.mlr.press/v97/antelmi19a.html]
-:* 2019 Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapse, [https://www.bibsonomy.org/bibtex/4700607448c23d9abeb9cb387c852f93]
-:* 2019 Learning Hierarchical Priors in VAEs, [https://www.semanticscholar.org/paper/Learning-Hierarchical-Priors-in-VAEs-Klushyn-Chen/6bb61321d45960f18098568f54eeb1ce413b7abe]
-:* 2020 Mixed-curvature Variational Autoencoders, [https://openreview.net/pdf?id=S1g6xeSKDS]
-:* 2020 Variational Autoencoders for Highly Multivariate Spatial Point Processes Intensities, [https://openreview.net/pdf?id=B1lj20NFDS]
-:* 2020 Mitigating Posterior Collapse in Strongly Conditioned Variational Autoencoders, [https://openreview.net/forum?id=rJlHea4Kvr]
-:* 2020 When Do Variational Autoencoders Know What They Don't Know?, [https://openreview.net/pdf?id Skg7VAEKDS]
 ==Tools==

@@ 第134行： / 第134行： @@
 ===VAE Model===
-:* 2014 Auto-Encoding Variational Bayes, [https://arxiv.org/abs/1312.6114]  (First composition)
+:# 2014 Auto-Encoding Variational Bayes, [https://arxiv.org/abs/1312.6114]  (First composition)
-:* 2015 The Variational Fair Autoencoder, [https://arxiv.org/abs/1511.00830]
+:# 2015 The Variational Fair Autoencoder, [https://arxiv.org/abs/1511.00830]
-:* 2015 Learning Structured Output Representation using Deep Conditional Generative Models, [https://pdfs.semanticscholar.org/3f25/e17eb717e5894e0404ea634451332f85d287.pdf?_ga 2.204795282.388480789.1585412171-912935264.1544959736]
+:# 2015 Learning Structured Output Representation using Deep Conditional Generative Models, [https://pdfs.semanticscholar.org/3f25/e17eb717e5894e0404ea634451332f85d287.pdf?_ga 2.204795282.388480789.1585412171-912935264.1544959736]
 :* 2017 Variational Lossy Autoencoder, [https://arxiv.org/abs/1611.02731]
 :* 2017 Grammar Variational Autoencoder, [https://arxiv.org/abs/1703.01925]

@@ 第169行： / 第169行： @@
 :* 2019 Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapse, [https://www.bibsonomy.org/bibtex/4700607448c23d9abeb9cb387c852f93]
 :* 2019 Learning Hierarchical Priors in VAEs, [https://www.semanticscholar.org/paper/Learning-Hierarchical-Priors-in-VAEs-Klushyn-Chen/6bb61321d45960f18098568f54eeb1ce413b7abe]
-:* 2020 Mixed-curvature Variational Autoencoders, [https://openreview.net/pdf?id S1g6xeSKDS]
+:* 2020 Mixed-curvature Variational Autoencoders, [https://openreview.net/pdf?id=S1g6xeSKDS]
-:* 2020 Variational Autoencoders for Highly Multivariate Spatial Point Processes Intensities, [https://openreview.net/pdf?id B1lj20NFDS]
+:* 2020 Variational Autoencoders for Highly Multivariate Spatial Point Processes Intensities, [https://openreview.net/pdf?id=B1lj20NFDS]
-:* 2020 Mitigating Posterior Collapse in Strongly Conditioned Variational Autoencoders, [https://openreview.net/attachment?id rJlHea4Kvr&name original_pdf]
+:* 2020 Mitigating Posterior Collapse in Strongly Conditioned Variational Autoencoders, [https://openreview.net/forum?id=rJlHea4Kvr]
 :* 2020 When Do Variational Autoencoders Know What They Don't Know?, [https://openreview.net/pdf?id Skg7VAEKDS]

@@ 第166行： / 第166行： @@
 :* Sparse Multi-Channel Variational Autoencoder for the Joint Analysis of Heterogeneous Data,[http://proceedings.mlr.press/v97/antelmi19a.html]
 :* Deepcoder: Semi-parametric variational autoencoders for automatic facial action coding,[http://openaccess.thecvf.com/content_ICCV_2017/papers/Tran_DeepCoder_Semi-Parametric_Variational_ICCV_2017_paper.pdf]
-:* Mitigating Posterior Collapse in Strongly Conditioned Variational Autoencoders,[https://openreview.net/attachment?id=rJlHea4Kvr&name=original_pdf,[When Do Variational Autoencoders Know What They Don't Know?,[https://openreview.net/pdf?id=Skg7VAEKDS]
+:* Mitigating Posterior Collapse in Strongly Conditioned Variational Autoencoders,[https://openreview.net/attachment?id=rJlHea4Kvr&name=original_pdf]
 :* Learning Latent Subspaces in Variational Autoencoders,[http://www.cs.toronto.edu/~zemel/documents/Conditional_Subspace_VAE_all.pdf]
 :* Hierarchical Variational Autoencoders for Music,[https://nips2017creativity.github.io/doc/Hierarchical_Variational_Autoencoders_for_Music.pdf]

@@ 第87行： / 第87行： @@
 # Makhzani, "Adversarial Autoencoders", 2015.
 # Locatello et al., "Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations", 2019.
 ===ASR===
@@ 第111行： / 第112行： @@
 # Wei-Ning Hsu, DISENTANGLING CORRELATED SPEAKER AND NOISE FOR SPEECH SYNTHESIS VIA DATA AUGMENTATION AND ADVERSARIAL FACTORIZATION, ICASSP 2019.
 ==Tools==

@@ 第51行： / 第51行： @@
 * [[媒体文件:Lda_flow.pdf|Nolinear_Flow (Yunqi Cai, 2019/11/02)]]
 * [[媒体文件:Flow_introduction.pdf|Flow_introduction (Yunqi Cai, 2019/11/04)]]
 =Further reading=