mlsanityData to 7 Oct 2026

SepIt: Approaching a Single Channel Speech Separation Bound

arXiv 2205.11801 ↗First posted 24 May 2022eess.AS cs.LG cs.SDcited by 16

Not on the map. Why?

Abstract (arXiv)

We present an upper bound for the Single Channel Speech Separation task, which is based on an assumption regarding the nature of short segments of speech. Using the bound, we are able to show that while the recent methods have made significant progress for a few speakers, there is room for improvement for five and ten speakers. We then introduce a Deep neural network, SepIt, that iteratively improves the different speakers' estimation. At test time, SpeIt has a varying number of iterations per test sample, based on a mutual information criterion that arises from our analysis. In an extensive set of experiments, SepIt outperforms the state-of-the-art neural networks for 2, 3, 5, and 10 speakers.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 14 of its 22 references that are in the map. First posted on arXiv 24 May 2022.

Builds on

14 of 22 references.

References · 14

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018SDR - half-baked or well done?cited by 420
  3. 2018Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separationcited by 400
  4. 2015Deep clustering: Discriminative embeddings for segmentation and separationcited by 211
  5. 2020Attention is All You Need in Speech Separationcited by 184
  6. 2019Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separationcited by 182
  7. 2020LibriMix: An Open-Source Dataset for Generalizable Speech Separationcited by 154
  8. 2017TasNet: time-domain audio separation network for real-time, single-channel speech separationcited by 115
  9. 2020Wavesplit: End-to-End Speech Separation by Speaker Clusteringcited by 74
  10. 2020Voice Separation with an Unknown Number of Multiple Speakerscited by 46
  11. 2021Speech Separation Using an Asynchronous Fully Recurrent Convolutional Neural Networkcited by 32
  12. 2021Many-Speakers Single Channel Speech Separation with Optimal Permutation Trainingcited by 11
2 more
  1. 2021Stepwise-Refining Speech Separation Network via Fine-Grained Encoding in High-order Latent Domaincited by 4
  2. 2019Cram'er-Rao Bounds for Complex-Valued Independent Component Extraction: Determined and Piecewise Determined Mixing Modelscited by 1

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 6; 2024: 3; 2025: 3.

16 papers.

Sort:

By area:

  1. 2023MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentionscited by 27
  2. 2023Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separationcited by 14
  3. 2022Resource-Efficient Separation Transformercited by 11
  4. 2022OCD: Learning to Overfit with Conditional Diffusion Modelscited by 9
  5. 2024Noise-robust Speech Separation with Fast Generative Correctioncited by 9
  6. 2023X-SepFormer: End-to-end Speaker Extraction Network with Explicit Optimization on Speaker Confusioncited by 6
  7. 2022MedleyVox: An Evaluation Dataset for Multiple Singing Voices Separationcited by 3
  8. 2022Deep neural network techniques for monaural speech enhancement: state of the art analysiscited by 3
  9. 2024Multiple Choice Learning for Efficient Speech Separation with Many Speakerscited by 3
  10. 2025Knowing When to Quit: Probabilistic Early Exits for Speech Separationcited by 2
  11. 2023DeCoR: Defy Knowledge Forgetting by Predicting Earlier Audio Codescited by 1
  12. 2024Papez: Resource-Efficient Speech Separation with Auditory Working Memorycited by 1
4 more
  1. 2023Improving Target Speaker Extraction with Sparse LDA-transformed Speaker Embeddingscited by 0
  2. 2023Monaural Multi-Speaker Speech Separation Using Efficient Transformer Modelcited by 0
  3. 2025Learned Bayesian Cram'er-Rao Bound for Unknown Measurement Models Using Score Neural Networkscited by 0
  4. 2025Speech Separation for Hearing-Impaired Children in the Classroomcited by 0