mlsanityData to 7 Oct 2026

Unsupervised speech enhancement with deep dynamical generative speech and noise models

arXiv 2306.07820 ↗First posted 13 Jun 2023eess.AS cs.LG cs.SDcited by 1

Not on the map. Why?

Abstract (arXiv)

This work builds on a previous work on unsupervised speech enhancement using a dynamical variational autoencoder (DVAE) as the clean speech model and non-negative matrix factorization (NMF) as the noise model. We propose to replace the NMF noise model with a deep dynamical generative model (DDGM) depending either on the DVAE latent variables, or on the noisy observations, or on both. This DDGM can be trained in three configurations: noise-agnostic, noise-dependent and noise adaptation after noise-dependent training. Experimental results show that the proposed method achieves competitive performance compared to state-of-the-art unsupervised speech enhancement methods, while the noise-dependent training configuration yields a much more time-efficient inference process.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 27 of its 40 references that are in the map. First posted on arXiv 13 Jun 2023.

Builds on

27 of 40 references.

References · 27

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  3. 2018SDR - half-baked or well done?cited by 420
  4. 2016Ladder Variational Autoencoderscited by 315
  5. 2017Supervised Speech Separation Based on Deep Learning: An Overviewcited by 213
  6. 2022Speech Enhancement and Dereverberation with Diffusion-based Generative Modelscited by 195
  7. 2017SEGAN: Speech Enhancement Generative Adversarial Networkcited by 165
  8. 2022Conditional Diffusion Probabilistic Model for Speech Enhancementcited by 132
  9. 2020Dynamical Variational Autoencoders: A Comprehensive Reviewcited by 127
  10. 2021MetricGAN+: An Improved Version of MetricGAN for Speech Enhancementcited by 114
  11. 2019MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancementcited by 104
  12. 2019A Recurrent Variational Autoencoder for Speech Enhancementcited by 38
15 more
  1. 2017Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorizationcited by 33
  2. 2019A variance modeling framework based on variational autoencoders for speech enhancementcited by 33
  3. 2021Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoderscited by 28
  4. 2021MetricGAN-U: Unsupervised speech enhancement/ dereverberation based only on noisy/ reverberated speechcited by 18
  5. 2021Speech Denoising Without Clean Training Data: A Noise2Noise Approachcited by 17
  6. 2021Noisy-target Training: A Training Strategy for DNN-based Speech Enhancement without Clean Speechcited by 15
  7. 2018Semi-supervised multichannel speech enhancement with variational autoencoders and non-negative matrix factorizationcited by 14
  8. 2021Guided Variational Autoencoder for Speech Enhancement With a Supervised Classifiercited by 12
  9. 2019Speech enhancement with variational autoencoders and alpha-stable distributionscited by 7
  10. 2021CycleGAN-based Non-parallel Speech Enhancement with an Adaptive Attention-in-attention Mechanismcited by 7
  11. 2019Improving Deep Speech Denoising by Noisy2Noisy Signal Mappingcited by 6
  12. 2019A Statistically Principled and Computationally Efficient Approach to Speech Enhancement using Variational Autoencoderscited by 6
  13. 2021A Benchmark of Dynamical Variational Autoencoders applied to Speech Spectrogram Modelingcited by 6
  14. 2022Fast and efficient speech enhancement with variational autoencoderscited by 2
  15. 2022A Bayesian Permutation training deep representation learning method for speech enhancement with variational autoencodercited by 1

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024Diffusion-based Unsupervised Audio-visual Speech Enhancementcited by 8