mlsanityData to 14 Oct 2026

Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data

arXiv 1709.07902 ↗First posted 22 Sep 2017cs.LG cs.CL cs.SDcited by 93

Not on the map. Why?

Abstract (arXiv)

We present a factorized hierarchical variational autoencoder, which learns disentangled and interpretable representations from sequential data without supervision. Specifically, we exploit the multi-scale nature of information in sequential data by formulating it explicitly within a factorized hierarchical graphical model that imposes sequence-dependent priors and sequence-independent priors to different sets of latent variables. The model is evaluated on two speech corpora to demonstrate, qualitatively, its ability to transform speakers or linguistic content by manipulating different sets of latent variables; and quantitatively, its ability to outperform an i-vector baseline for speaker verification and reduce the word error rate by as much as 35% in mismatched train/test scenarios for automatic speech recognition tasks.

Key facts. Cited by 93 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Sep 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 26; 2022: 23; 2023: 14; 2024: 18; 2025: 5; 2026: 7.

93 papers.

Sort:

By area:

  1. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  2. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  3. 2021Generative Spoken Language Modeling from Raw Audiocited by 340
  4. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 302
  5. 2022AudioGen: Textually Guided Audio Generationcited by 295
  6. 2022Self-Supervised Speech Representation Learning: A Reviewcited by 260
  7. 2021Speech Resynthesis from Discrete Disentangled Self-Supervised Representationscited by 243
  8. 2021Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Trainingcited by 151
  9. 2021Contrastively Disentangled Sequential Variational Autoencodercited by 34
  10. 2021An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wildcited by 30
  11. 2021Textless Speech Emotion Conversion using Discrete and Decomposed Representationscited by 29
  12. 2022Robust Disentangled Variational Speech Representation Learning for Zero-shot Voice Conversioncited by 28
38 more
  1. 2023Multifactor Sequential Disentanglement via Structured Koopman Autoencoderscited by 24
  2. 2021Disentangled Recurrent Wasserstein Autoencodercited by 22
  3. 2023Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clusteringcited by 22
  4. 2023Temporally Disentangled Representation Learning under Unknown Nonstationaritycited by 22
  5. 2022Decoupling Local and Global Representations of Time Seriescited by 17
  6. 2021Scaling-up Disentanglement for Image Translationcited by 15
  7. 20233D-Speaker: A Large-Scale Multi-Device, Multi-Distance, and Multi-Dialect Corpus for Speech Representation Disentanglementcited by 15
  8. 2022A Contrastive Objective for Learning Disentangled Representationscited by 14
  9. 2023Disentangling Voice and Content with Self-Supervision for Speaker Recognitioncited by 13
  10. 2024Modeling Inter-Intra Heterogeneity for Graph Federated Learningcited by 12
  11. 2021Uncertainty Estimation Using Riemannian Model Dynamics for Offline Reinforcement Learningcited by 10
  12. 2022Non-Contrastive Self-supervised Learning for Utterance-Level Information Extraction from Speechcited by 10
  13. 2023Sample and Predict Your Latent: Modality-free Sequential Disentanglement via Contrastive Estimationcited by 10
  14. 2022A Brief Overview of Unsupervised Neural Speech Representation Learningcited by 9
  15. 2021Many-to-Many Voice Conversion based Feature Disentanglement using Variational Autoencodercited by 7
  16. 2022Unsupervised TTS Acoustic Modeling for TTS with Conditional Disentangled Sequential VAEcited by 7
  17. 2022Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processingcited by 7
  18. 2024Sequential Disentanglement by Extracting Static Information From A Single Sequence Elementcited by 7
  19. 2024Learning Physics for Unveiling Hidden Earthquake Ground Motions via Conditional Generative Modelingcited by 7
  20. 2021VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Expertscited by 6
  21. 2022Towards Robust Unsupervised Disentanglement of Sequential Data -- A Case Study Using Music Audiocited by 6
  22. 2024TrustEMG-Net: Using Representation-Masking Transformer with U-Net for Surface Electromyography Enhancementcited by 6
  23. 2021On Disentanglement in Gaussian Process Variational Autoencoderscited by 5
  24. 2021Protecting gender and identity with disentangled speech representationscited by 5
  25. 2021Hamiltonian latent operators for content and motion disentanglement in image sequencescited by 5
  26. 2022Learning Subject-Invariant Representations from Speech-Evoked EEG Using Variational Autoencoderscited by 5
  27. 2022From latent dynamics to meaningful representationscited by 5
  28. 2022TGAVC: Improving Autoencoder Voice Conversion with Text-Guided and Adversarial Trainingcited by 4
  29. 2023Learning Interpretable Low-dimensional Representation via Physical Symmetrycited by 4
  30. 2024VoxGenesis: Unsupervised Discovery of Latent Speaker Manifold for Speech Synthesiscited by 4
  31. 2024Disentangling Representations through Multi-task Learningcited by 4
  32. 2024Sequential Representation Learning via Static-Dynamic Conditional Disentanglementcited by 4
  33. 2024STAB: Speech Tokenizer Assessment Benchmarkcited by 4
  34. 2021Video Reenactment as Inductive Bias for Content-Motion Disentanglementcited by 3
  35. 2022Non-Contrastive Self-Supervised Learning of Utterance-Level Speech Representationscited by 3
  36. 2024DisMix: Disentangling Mixtures of Musical Instruments for Source-level Pitch and Timbre Manipulationcited by 3
  37. 2025Can Diffusion Models Disentangle? A Theoretical Perspectivecited by 3
  38. 2026FunCineForge: A Unified Dataset Toolkit and Model for Zero-Shot Movie Dubbing in Diverse Cinematic Scenescited by 3

50 most cited of 93 All 93 (JSON)