# SepIt: Approaching a Single Channel Speech Separation Bound

arXiv: https://arxiv.org/abs/2205.11801 · HTML: https://mlsanity.com/paper/2205.11801/

## Key facts

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

## Builds on (most cited first, 14 of 14)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation](https://mlsanity.com/paper/1809.07454/) (2018)
- [Deep clustering: Discriminative embeddings for segmentation and separation](https://mlsanity.com/paper/1508.04306/) (2015)
- [Attention is All You Need in Speech Separation](https://mlsanity.com/paper/2010.13154/) (2020)
- [Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation](https://mlsanity.com/paper/1910.06379/) (2019)
- [LibriMix: An Open-Source Dataset for Generalizable Speech Separation](https://mlsanity.com/paper/2005.11262/) (2020)
- [TasNet: time-domain audio separation network for real-time, single-channel speech separation](https://mlsanity.com/paper/1711.00541/) (2017)
- [Wavesplit: End-to-End Speech Separation by Speaker Clustering](https://mlsanity.com/paper/2002.08933/) (2020)
- [Voice Separation with an Unknown Number of Multiple Speakers](https://mlsanity.com/paper/2003.01531/) (2020)
- [Speech Separation Using an Asynchronous Fully Recurrent Convolutional Neural Network](https://mlsanity.com/paper/2112.02321/) (2021)
- [Many-Speakers Single Channel Speech Separation with Optimal Permutation Training](https://mlsanity.com/paper/2104.08955/) (2021)
- [Stepwise-Refining Speech Separation Network via Fine-Grained Encoding in High-order Latent Domain](https://mlsanity.com/paper/2110.04791/) (2021)
- [Cram'er-Rao Bounds for Complex-Valued Independent Component Extraction: Determined and Piecewise Determined Mixing Models](https://mlsanity.com/paper/1907.08790/) (2019)

## Built on by (most cited first, 16 of 16)

- [MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated Single-Head Transformer with Convolution-Augmented Joint Self-Attentions](https://mlsanity.com/paper/2302.11824/) (2023)
- [Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separation](https://mlsanity.com/paper/2301.10752/) (2023)
- [Resource-Efficient Separation Transformer](https://mlsanity.com/paper/2206.09507/) (2022)
- [OCD: Learning to Overfit with Conditional Diffusion Models](https://mlsanity.com/paper/2210.00471/) (2022)
- [Noise-robust Speech Separation with Fast Generative Correction](https://mlsanity.com/paper/2406.07461/) (2024)
- [X-SepFormer: End-to-end Speaker Extraction Network with Explicit Optimization on Speaker Confusion](https://mlsanity.com/paper/2303.05023/) (2023)
- [MedleyVox: An Evaluation Dataset for Multiple Singing Voices Separation](https://mlsanity.com/paper/2211.07302/) (2022)
- [Deep neural network techniques for monaural speech enhancement: state of the art analysis](https://mlsanity.com/paper/2212.00369/) (2022)
- [Multiple Choice Learning for Efficient Speech Separation with Many Speakers](https://mlsanity.com/paper/2411.18497/) (2024)
- [Learned Bayesian Cram'er-Rao Bound for Unknown Measurement Models Using Score Neural Networks](https://mlsanity.com/paper/2502.00724/) (2025)
- [Knowing When to Quit: Probabilistic Early Exits for Speech Separation](https://mlsanity.com/paper/2507.09768/) (2025)
- [DeCoR: Defy Knowledge Forgetting by Predicting Earlier Audio Codes](https://mlsanity.com/paper/2305.18441/) (2023)
- [Papez: Resource-Efficient Speech Separation with Auditory Working Memory](https://mlsanity.com/paper/2407.00888/) (2024)
- [Improving Target Speaker Extraction with Sparse LDA-transformed Speaker Embeddings](https://mlsanity.com/paper/2301.06277/) (2023)
- [Monaural Multi-Speaker Speech Separation Using Efficient Transformer Model](https://mlsanity.com/paper/2308.00010/) (2023)
- [Speech Separation for Hearing-Impaired Children in the Classroom](https://mlsanity.com/paper/2511.07677/) (2025)

## 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.