{"total":86,"rows":[{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342,"area":null},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657,"area":null},{"id":"2102.01192","title":"Generative Spoken Language Modeling from Raw Audio","created":"2021-02-01","cited_by_count":340,"area":null},{"id":"2201.08164","title":"From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI","created":"2022-01-20","cited_by_count":302,"area":null},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295,"area":null},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2104.00355","title":"Speech Resynthesis from Discrete Disentangled Self-Supervised Representations","created":"2021-04-01","cited_by_count":243,"area":null},{"id":"2104.01027","title":"Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training","created":"2021-04-02","cited_by_count":151,"area":null},{"id":"2110.12091","title":"Contrastively Disentangled Sequential Variational Autoencoder","created":"2021-10-22","cited_by_count":34,"area":null},{"id":"2106.15610","title":"An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wild","created":"2021-06-29","cited_by_count":30,"area":null},{"id":"2111.07402","title":"Textless Speech Emotion Conversion using Discrete and Decomposed Representations","created":"2021-11-14","cited_by_count":29,"area":null},{"id":"2203.16705","title":"Robust Disentangled Variational Speech Representation Learning for Zero-shot Voice Conversion","created":"2022-03-30","cited_by_count":28,"area":null},{"id":"2303.17264","title":"Multifactor Sequential Disentanglement via Structured Koopman Autoencoders","created":"2023-03-30","cited_by_count":24,"area":null},{"id":"2101.07496","title":"Disentangled Recurrent Wasserstein Autoencoder","created":"2021-01-19","cited_by_count":22,"area":null},{"id":"2305.11072","title":"Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clustering","created":"2023-05-18","cited_by_count":22,"area":null},{"id":"2310.18615","title":"Temporally Disentangled Representation Learning under Unknown Nonstationarity","created":"2023-10-28","cited_by_count":22,"area":null},{"id":"2202.02262","title":"Decoupling Local and Global Representations of Time Series","created":"2022-02-04","cited_by_count":17,"area":null},{"id":"2103.14017","title":"Scaling-up Disentanglement for Image Translation","created":"2021-03-25","cited_by_count":15,"area":null},{"id":"2306.15354","title":"3D-Speaker: A Large-Scale Multi-Device, Multi-Distance, and Multi-Dialect Corpus for Speech Representation Disentanglement","created":"2023-06-27","cited_by_count":15,"area":null},{"id":"2203.11284","title":"A Contrastive Objective for Learning Disentangled Representations","created":"2022-03-21","cited_by_count":14,"area":null},{"id":"2310.01128","title":"Disentangling Voice and Content with Self-Supervision for Speaker Recognition","created":"2023-10-02","cited_by_count":13,"area":null},{"id":"2412.11402","title":"Modeling Inter-Intra Heterogeneity for Graph Federated Learning","created":"2024-12-16","cited_by_count":12,"area":null},{"id":"2208.05445","title":"Non-Contrastive Self-supervised Learning for Utterance-Level Information Extraction from Speech","created":"2022-08-10","cited_by_count":10,"area":null},{"id":"2305.15924","title":"Sample and Predict Your Latent: Modality-free Sequential Disentanglement via Contrastive Estimation","created":"2023-05-25","cited_by_count":10,"area":null},{"id":"2203.01829","title":"A Brief Overview of Unsupervised Neural Speech Representation Learning","created":"2022-03-01","cited_by_count":9,"area":null},{"id":"2107.06642","title":"Many-to-Many Voice Conversion based Feature Disentanglement using Variational Autoencoder","created":"2021-07-11","cited_by_count":7,"area":null},{"id":"2206.02512","title":"Unsupervised TTS Acoustic Modeling for TTS with Conditional Disentangled Sequential VAE","created":"2022-06-06","cited_by_count":7,"area":null},{"id":"2211.01522","title":"Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing","created":"2022-11-02","cited_by_count":7,"area":null},{"id":"2406.18131","title":"Sequential Disentanglement by Extracting Static Information From A Single Sequence Element","created":"2024-06-26","cited_by_count":7,"area":null},{"id":"2407.15089","title":"Learning Physics for Unveiling Hidden Earthquake Ground Motions via Conditional Generative Modeling","created":"2024-07-21","cited_by_count":7,"area":null},{"id":"2205.05871","title":"Towards Robust Unsupervised Disentanglement of Sequential Data -- A Case Study Using Music Audio","created":"2022-05-12","cited_by_count":6,"area":null},{"id":"2410.03843","title":"TrustEMG-Net: Using Representation-Masking Transformer with U-Net for Surface Electromyography Enhancement","created":"2024-10-04","cited_by_count":6,"area":null},{"id":"2102.05507","title":"On Disentanglement in Gaussian Process Variational Autoencoders","created":"2021-02-10","cited_by_count":5,"area":null},{"id":"2104.11051","title":"Protecting gender and identity with disentangled speech representations","created":"2021-04-22","cited_by_count":5,"area":null},{"id":"2112.01641","title":"Hamiltonian latent operators for content and motion disentanglement in image sequences","created":"2021-12-02","cited_by_count":5,"area":null},{"id":"2207.00323","title":"Learning Subject-Invariant Representations from Speech-Evoked EEG Using Variational Autoencoders","created":"2022-07-01","cited_by_count":5,"area":null},{"id":"2209.00905","title":"From latent dynamics to meaningful representations","created":"2022-09-02","cited_by_count":5,"area":null},{"id":"2208.04035","title":"TGAVC: Improving Autoencoder Voice Conversion with Text-Guided and Adversarial Training","created":"2022-08-08","cited_by_count":4,"area":null},{"id":"2302.10890","title":"Learning Interpretable Low-dimensional Representation via Physical Symmetry","created":"2023-02-05","cited_by_count":4,"area":null},{"id":"2403.00529","title":"VoxGenesis: Unsupervised Discovery of Latent Speaker Manifold for Speech Synthesis","created":"2024-03-01","cited_by_count":4,"area":null},{"id":"2408.05599","title":"Sequential Representation Learning via Static-Dynamic Conditional Disentanglement","created":"2024-08-10","cited_by_count":4,"area":null},{"id":"2409.02384","title":"STAB: Speech Tokenizer Assessment Benchmark","created":"2024-09-04","cited_by_count":4,"area":null},{"id":"2102.00324","title":"Video Reenactment as Inductive Bias for Content-Motion Disentanglement","created":"2021-01-30","cited_by_count":3,"area":null},{"id":"2208.05413","title":"Non-Contrastive Self-Supervised Learning of Utterance-Level Speech Representations","created":"2022-08-10","cited_by_count":3,"area":null},{"id":"2408.10807","title":"DisMix: Disentangling Mixtures of Musical Instruments for Source-level Pitch and Timbre Manipulation","created":"2024-08-20","cited_by_count":3,"area":null},{"id":"2601.14777","title":"FunCineForge: A Unified Dataset Toolkit and Model for Zero-Shot Movie Dubbing in Diverse Cinematic Scenes","created":"2026-01-21","cited_by_count":3,"area":null},{"id":"2105.04458","title":"Learning Robust Latent Representations for Controllable Speech Synthesis","created":"2021-05-10","cited_by_count":2,"area":null},{"id":"2105.06660","title":"Estimating Disentangled Belief about Hidden State and Hidden Task for Meta-RL","created":"2021-05-14","cited_by_count":2,"area":null},{"id":"2204.07075","title":"Learning and controlling the source-filter representation of speech with a variational autoencoder","created":"2022-04-14","cited_by_count":2,"area":null},{"id":"2207.03478","title":"Red PANDA: Disambiguating Anomaly Detection by Removing Nuisance Factors","created":"2022-07-07","cited_by_count":2,"area":null},{"id":"2211.08191","title":"Improved disentangled speech representations using contrastive learning in factorized hierarchical variational autoencoder","created":"2022-11-15","cited_by_count":2,"area":null},{"id":"2311.08149","title":"Modeling Complex Disease Trajectories using Deep Generative Models with Semi-Supervised Latent Processes","created":"2023-11-14","cited_by_count":2,"area":null},{"id":"2407.03824","title":"Unsupervised Disentanglement of Content and Style via Variance-Invariance Constraints","created":"2024-07-04","cited_by_count":2,"area":null},{"id":"2410.05564","title":"Unsupervised Representation Learning from Sparse Transformation Analysis","created":"2024-10-07","cited_by_count":2,"area":null},{"id":"2510.19640","title":"Latent Space Factorization in LoRA","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2101.09500","title":"Disentangled Sequence Clustering for Human Intention Inference","created":"2021-01-23","cited_by_count":1,"area":null},{"id":"2109.13425","title":"The JHU submission to VoxSRC-21: Track 3","created":"2021-09-28","cited_by_count":1,"area":null},{"id":"2202.12707","title":"Benchmarking Generative Latent Variable Models for Speech","created":"2022-02-22","cited_by_count":1,"area":null},{"id":"2210.04023","title":"Multi-Task Dynamical Systems","created":"2022-10-08","cited_by_count":1,"area":null},{"id":"2303.09404","title":"Speech Modeling with a Hierarchical Transformer Dynamical VAE","created":"2023-03-07","cited_by_count":1,"area":null},{"id":"2303.09446","title":"Controllable Prosody Generation With Partial Inputs","created":"2023-03-14","cited_by_count":1,"area":null},{"id":"2309.04156","title":"Cross-Utterance Conditioned VAE for Speech Generation","created":"2023-09-08","cited_by_count":1,"area":null},{"id":"2407.02543","title":"Towards the Next Frontier in Speech Representation Learning Using Disentanglement","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2409.02385","title":"Unified Framework with Consistency across Modalities for Human Activity Recognition","created":"2024-09-04","cited_by_count":1,"area":null},{"id":"2410.15620","title":"Acoustic Model Optimization over Multiple Data Sources: Merging and Valuation","created":"2024-10-21","cited_by_count":1,"area":null},{"id":"2510.17313","title":"Disentanglement Beyond Static vs. Dynamic: A Benchmark and Evaluation Framework for Multi-Factor Sequential Representations","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2601.06844","title":"Variational decomposition autoencoding improves disentanglement of latent representations","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2601.09050","title":"SITA: Learning Speaker-Invariant and Tone-Aware Speech Representations for Low-Resource Tonal Languages","created":"2026-01-14","cited_by_count":1,"area":null},{"id":"2601.19399","title":"Residual Tokens Enhance Masked Autoencoders for Speech Modeling","created":"2026-01-27","cited_by_count":1,"area":null},{"id":"2103.14963","title":"Particle Filter Bridge Interpolation","created":"2021-03-27","cited_by_count":0,"area":null},{"id":"2104.10492","title":"Skimming and Scanning for Untrimmed Video Action Recognition","created":"2021-04-21","cited_by_count":0,"area":null},{"id":"2105.01786","title":"Voice Conversion Based Speaker Normalization for Acoustic Unit Discovery","created":"2021-05-04","cited_by_count":0,"area":null},{"id":"2110.09928","title":"CycleFlow: Purify Information Factors by Cycle Loss","created":"2021-10-18","cited_by_count":0,"area":null},{"id":"2112.03164","title":"Feature Disentanglement of Robot Trajectories","created":"2021-12-06","cited_by_count":0,"area":null},{"id":"2204.11286","title":"Improved far-field speech recognition using Joint Variational Autoencoder","created":"2022-04-24","cited_by_count":0,"area":null},{"id":"2205.02670","title":"Unsupervised Mismatch Localization in Cross-Modal Sequential Data with Application to Mispronunciations Localization","created":"2022-05-05","cited_by_count":0,"area":null},{"id":"2210.08182","title":"Learning Invariant Representation and Risk Minimized for Unsupervised Accent Domain Adaptation","created":"2022-10-15","cited_by_count":0,"area":null},{"id":"2308.12888","title":"Inducing Causal Structure for Abstractive Text Summarization","created":"2023-08-24","cited_by_count":0,"area":null},{"id":"2310.11940","title":"Interpretable Spectral Variational AutoEncoder (ISVAE) for time series clustering","created":"2023-10-18","cited_by_count":0,"area":null},{"id":"2407.11427","title":"Semi-Supervised Generative Models for Disease Trajectories: A Case Study on Systemic Sclerosis","created":"2024-07-16","cited_by_count":0,"area":null},{"id":"2408.07016","title":"Rethinking Disentanglement under Dependent Factors of Variation","created":"2024-08-13","cited_by_count":0,"area":null},{"id":"2408.12936","title":"Smooth InfoMax -- Towards Easier Post-Hoc Interpretability","created":"2024-08-23","cited_by_count":0,"area":null},{"id":"2506.05325","title":"Quasiparticle Interference Kernel Extraction with Variational Autoencoders via Latent Alignment","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2603.05577","title":"Koopman Regularized Deep Speech Disentanglement for Speaker Verification","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2608.26473","title":"DTD-VAE: Disentangled Temporal Dependencies VAE for Credit Risk Prediction","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2610.14497","title":"DEFT: Disentanglement-Enhanced Fine-Tuning for EEG Foundation Models","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}