mlsanityData to 7 Oct 2026

SDR - half-baked or well done?

arXiv 1811.02508 ↗First posted 6 Nov 2018cs.SD eess.AScited by 420

Not on the map. Why?

Cited by 81 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In speech enhancement and source separation, signal-to-noise ratio is a ubiquitous objective measure of denoising/separation quality. A decade ago, the BSS_eval toolkit was developed to give researchers worldwide a way to evaluate the quality of their algorithms in a simple, fair, and hopefully insightful way: it attempted to account for channel variations, and to not only evaluate the total distortion in the estimated signal but also split it in terms of various factors such as remaining interference, newly added artifacts, and channel errors. In recent years, hundreds of papers have been relying on this toolkit to evaluate their proposed methods and compare them to previous works, often arguing that differences on the order of 0.1 dB proved the effectiveness of a method over others. We argue here that the signal-to-distortion ratio (SDR) implemented in the BSS_eval toolkit has generally been improperly used and abused, especially in the case of single-channel separation, resulting in misleading results. We propose to use a slightly modified definition, resulting in a simpler, more robust measure, called scale-invariant SDR (SI-SDR). We present various examples of critical failure of the original SDR that SI-SDR overcomes.

Key facts. Cited by 420 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 45; 2022: 62; 2023: 75; 2024: 71; 2025: 101; 2026: 66.

420 papers.

Sort:

By area:

  1. 2023High-Fidelity Audio Compression with Improved RVQGANcited by 423
  2. 2023Voicebox: Text-Guided Multilingual Universal Speech Generation at Scalecited by 373
  3. 2022Speech Enhancement and Dereverberation with Diffusion-based Generative Modelscited by 195
  4. 2022NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Qualitycited by 151
  5. 2022StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberationcited by 105
  6. 2022Speech Enhancement with Score-Based Generative Models in the Complex STFT Domaincited by 102
  7. 2023Multi-Source Diffusion Models for Simultaneous Music Generation and Separationcited by 63
  8. 2024EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberationcited by 62
  9. 2024An Investigation of Incorporating Mamba for Speech Enhancementcited by 61
  10. 2023GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restorationcited by 58
  11. 2023Generative Pre-training for Speech with Flow Matchingcited by 55
  12. 2022HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancementcited by 49
38 more
  1. 2024Scaling Transformers for Low-Bitrate High-Quality Speech Codingcited by 48
  2. 2022Separate What You Describe: Language-Queried Audio Source Separationcited by 45
  3. 2024Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separationcited by 45
  4. 2023Separate Anything You Describecited by 43
  5. 2022Diffusion-based Generative Speech Source Separationcited by 41
  6. 2021DeepFilterNet: A Low Complexity Speech Enhancement Framework for Full-Band Audio based on Deep Filteringcited by 38
  7. 2022An efficient encoder-decoder architecture with top-down attention for speech separationcited by 38
  8. 2025Kling-Foley: Multimodal Diffusion Transformer for High-Quality Video-to-Audio Generationcited by 38
  9. 2021Move2Hear: Active Audio-Visual Source Separationcited by 35
  10. 2022Analysing Diffusion-based Generative Approaches versus Discriminative Approaches for Speech Restorationcited by 34
  11. 2024Music2Latent: Consistency Autoencoders for Latent Audio Compressioncited by 33
  12. 2021Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Featurescited by 32
  13. 2025SepPrune: Structured Pruning for Efficient Deep Speech Separationcited by 31
  14. 2023Reducing the Prior Mismatch of Stochastic Differential Equations for Diffusion-based Speech Enhancementcited by 30
  15. 2021EasyCom: An Augmented Reality Dataset to Support Algorithms for Easy Communication in Noisy Environmentscited by 29
  16. 2021Variational Autoencoder for Speech Enhancement with a Noise-Aware Encodercited by 28
  17. 2021Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoderscited by 28
  18. 2023MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentionscited by 27
  19. 2022AudioScopeV2: Audio-Visual Attention Architectures for Calibrated Open-Domain On-Screen Sound Separationcited by 24
  20. 2024FlowAVSE: Efficient Audio-Visual Speech Enhancement with Conditional Flow Matchingcited by 23
  21. 2022Real-Time Target Sound Extractioncited by 22
  22. 2024Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesiscited by 22
  23. 2022RemixIT: Continual self-training of speech enhancement models via bootstrapped remixingcited by 20
  24. 2025FlowSE: Flow Matching-based Speech Enhancementcited by 20
  25. 2021Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamicscited by 19
  26. 2022On loss functions and evaluation metrics for music source separationcited by 17
  27. 2021Real-time Denoising and Dereverberation with Tiny Recurrent U-Netcited by 16
  28. 2022Active Audio-Visual Separation of Dynamic Sound Sourcescited by 16
  29. 2022SepIt: Approaching a Single Channel Speech Separation Boundcited by 16
  30. 2021Compute and memory efficient universal sound source separationcited by 15
  31. 2023Target Speech Extraction with Conditional Diffusion Modelcited by 15
  32. 2023Single and Few-step Diffusion for Generative Speech Enhancementcited by 15
  33. 2024Instruct-MusicGen: Unlocking Text-to-Music Editing for Music Language Models via Instruction Tuningcited by 15
  34. 2025FlowDec: A flow-based full-band general audio codec with high perceptual qualitycited by 15
  35. 2022Diffiner: A Versatile Diffusion-based Generative Refiner for Speech Enhancementcited by 14
  36. 2023Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separationcited by 14
  37. 2022Heterogeneous Target Speech Separationcited by 13
  38. 2024Generalized Multi-Source Inference for Text Conditioned Music Diffusion Modelscited by 13

50 most cited of 420 All 420 (JSON)