mlsanityData to 14 Oct 2026

A Recurrent Variational Autoencoder for Speech Enhancement

arXiv 1910.10942 ↗First posted 24 Oct 2019cs.LG cs.AI cs.NEcited by 38

Not on the map. Why?

Abstract (arXiv)

This paper presents a generative approach to speech enhancement based on a recurrent variational autoencoder (RVAE). The deep generative speech model is trained using clean speech signals only, and it is combined with a nonnegative matrix factorization noise model for speech enhancement. We propose a variational expectation-maximization algorithm where the encoder of the RVAE is fine-tuned at test time, to approximate the distribution of the latent variables given the noisy speech observations. Compared with previous approaches based on feed-forward fully-connected architectures, the proposed recurrent deep generative speech model induces a posterior temporal dynamic over the latent variables, which is shown to improve the speech enhancement results.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). First posted on arXiv 24 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 8; 2023: 14; 2024: 3; 2025: 5; 2026: 4.

38 papers.

Sort:

By area:

  1. 2022Conditional Diffusion Probabilistic Model for Speech Enhancementcited by 132
  2. 2023A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AIcited by 68
  3. 2021A Study on Speech Enhancement Based on Diffusion Probabilistic Modelcited by 53
  4. 2023Deep networks for system identification: a Surveycited by 37
  5. 2023Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecastingcited by 34
  6. 2021Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoderscited by 28
  7. 2024MADiff: Motion-Aware Mamba Diffusion Models for Hand Trajectory Prediction on Egocentric Videoscited by 18
  8. 2022SRTNet: Time Domain Speech Enhancement Via Stochastic Refinementcited by 12
  9. 2023Unsupervised speech enhancement with diffusion-based generative modelscited by 12
  10. 2023SE-Bridge: Speech Enhancement with Consistent Brownian Bridgecited by 7
  11. 2023Diffusion-based speech enhancement with a weighted generative-supervised learning losscited by 7
  12. 2024Neural Blind Source Separation and Diarization for Distant Speech Recognitioncited by 6
26 more
  1. 2022Deep neural network techniques for monaural speech enhancement: state of the art analysiscited by 3
  2. 2021Learning Robust Latent Representations for Controllable Speech Synthesiscited by 2
  3. 2021GANtron: Emotional Speech Synthesis with Generative Adversarial Networkscited by 2
  4. 2022Learning and controlling the source-filter representation of speech with a variational autoencodercited by 2
  5. 2022Audio-visual speech enhancement with a deep Kalman filter generative modelcited by 2
  6. 2022Fast and efficient speech enhancement with variational autoencoderscited by 2
  7. 2023Diff-SV: A Unified Hierarchical Framework for Noise-Robust Speaker Verification Using Score-Based Diffusion Probabilistic Modelscited by 2
  8. 2024HaHeAE: Learning Generalisable Joint Representations of Human Hand and Head Movements in Extended Realitycited by 2
  9. 2025A Hybrid Model for Weakly-Supervised Speech Dereverberationcited by 2
  10. 2025Plasma State Monitoring and Disruption Characterization using Multimodal VAEscited by 2
  11. 2023Speech Modeling with a Hierarchical Transformer Dynamical VAEcited by 1
  12. 2023Unsupervised speech enhancement with deep dynamical generative speech and noise modelscited by 1
  13. 2023On the Impact of Sampling on Deep Sequential State Estimationcited by 1
  14. 2023Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separationcited by 1
  15. 2025Leveraging Discriminative Latent Representations for Conditioning GAN-Based Speech Enhancementcited by 1
  16. 2022Unsupervised Multiple-Object Tracking with a Dynamical Variational Autoencodercited by 0
  17. 2022A weighted-variance variational autoencoder model for speech enhancementcited by 0
  18. 2023Integrating Uncertainty into Neural Network-based Speech Enhancementcited by 0
  19. 2023Posterior sampling algorithms for unsupervised speech enhancement with recurrent variational autoencodercited by 0
  20. 2023Exploiting the capacity of deep networks only at training stage for nonlinear black-box system identificationcited by 0
  21. 2025Posterior Transition Modeling for Unsupervised Diffusion-Based Speech Enhancementcited by 0
  22. 2025Lightweight Wasserstein Audio-Visual Model for Unified Speech Enhancement and Separationcited by 0
  23. 2026SlimDiffuSE: Towards Efficient Diffusion-Based Speech Enhancement using Slimmable Networkscited by 0
  24. 2026Discriminative Flow Matching: Beyond Time-Conditioning in Generative Restoration via Flow-State Representationscited by 0
  25. 2026Neural Multichannel Distant Speaker Diarization with Heavy-tailed Source Separation Modelcited by 0
  26. 2026HAP: A Hand-Driven Active Perception Framework for Egocentric Head Motion Predictioncited by 0