mlsanityData to 14 Oct 2026

Investigating Training Objectives for Generative Speech Enhancement

arXiv 2409.10753 ↗First posted 16 Sep 2024eess.AS cs.SDcited by 20

Not on the map. Why?

Abstract (arXiv)

Generative speech enhancement has recently shown promising advancements in improving speech quality in noisy environments. Multiple diffusion-based frameworks exist, each employing distinct training objectives and learning techniques. This paper aims to explain the differences between these frameworks by focusing our investigation on score-based generative models and the Schr"odinger bridge. We conduct a series of comprehensive experiments to compare their performance and highlight differing training behaviors. Furthermore, we propose a novel perceptual loss function tailored for the Schr"odinger bridge framework, demonstrating enhanced performance and improved perceptual quality of the enhanced speech signals. All experimental code and pre-trained models are publicly available to facilitate further research and development in this domain.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). First posted on arXiv 16 Sep 2024.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 15; 2026: 5.

20 papers.

Sort:

By area:

  1. 2025A Composite Predictive-Generative Approach to Monaural Universal Speech Enhancementcited by 4
  2. 2025Robust One-step Speech Enhancement via Consistency Distillationcited by 4
  3. 2025Schr"odinger Bridge Consistency Trajectory Models for Speech Enhancementcited by 4
  4. 2025VoiceBridge: General Speech Restoration with One-step Latent Bridge Modelscited by 4
  5. 2025Real-Time Streamable Generative Speech Restoration with Flow Matchingcited by 4
  6. 2025Flowing Straighter with Conditional Flow Matching for Accurate Speech Enhancementcited by 3
  7. 2025Schr"odinger Bridge Mamba for One-Step Speech Enhancementcited by 3
  8. 2025LipDiffuser: Lip-to-Speech Generation with Conditional Diffusion Modelscited by 2
  9. 2025ArtiFree: Detecting and Reducing Generative Artifacts in Diffusion-based Speech Enhancementcited by 2
  10. 2025Dale meets Langevin: A Multiplicative Denoising Diffusion Modelcited by 2
  11. 2025Audio Generation Through Score-Based Generative Modeling: Design Principles and Implementationcited by 1
  12. 2025Regularized Schr"odinger Bridge via Distortion-Perception Perturbation for High-Fidelity Speech Enhancementcited by 1
8 more
  1. 2025Investigating training objective for flow matching-based speech enhancementcited by 1
  2. 2026Time-Unconditional Generative Speech Enhancement via Autonomous Rectified Flowcited by 1
  3. 2025Combining Deterministic Enhanced Conditions with Dual-Streaming Encoding for Diffusion-Based Speech Enhancementcited by 0
  4. 2025WaveLLDM: Design and Development of a Lightweight Latent Diffusion Model for Speech Enhancement and Restorationcited by 0
  5. 2026A Fast Solver for Interpolating Stochastic Differential Equation Diffusion Models for Speech Restorationcited by 0
  6. 2026Diff-VS: Efficient Audio-Aware Diffusion U-Net for Vocals Separationcited by 0
  7. 2026Predictive-Generative Drift Decomposition for Speech Enhancement and Separationcited by 0
  8. 2026Perceptual Quality Loss or Loss of Perceptual Quality?cited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Diffusion-based Speech Enhancement with Schr"odinger Bridge and Symmetric Noise Schedule
  2. 2026SB-RF: Schr"odinger Bridge Rectified Flow for One-Step Robust Speech Enhancement
  3. 2025Few-step Adversarial Schr"odinger Bridge for Generative Speech Enhancement
  4. 2026HybridSB-MoE: Dual-Domain Schr"odinger Bridges with Scene-Adaptive Expert Routing for Speech Enhancement
  5. 2026Rethinking Flow and Diffusion Bridge Models for Speech Enhancement
  6. 2026SE-MSB: End-to-End Unpaired Speech Enhancement using Mamba Schr"odinger Bridges
  7. 2022Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain
  8. 2023Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based Speech Enhancement