# SkiM: Skipping Memory LSTM for Low-Latency Real-Time Continuous Speech Separation

arXiv: https://arxiv.org/abs/2201.10800 · HTML: https://mlsanity.com/paper/2201.10800/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jan 2022.

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

- [Open-Source Conversational AI with SpeechBrain 1.0](https://mlsanity.com/paper/2407.00463/) (2024)
- [Resource-Efficient Separation Transformer](https://mlsanity.com/paper/2206.09507/) (2022)
- [ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding](https://mlsanity.com/paper/2207.09514/) (2022)
- [Diffusion-based Generative Modeling with Discriminative Guidance for Streamable Speech Enhancement](https://mlsanity.com/paper/2406.13471/) (2024)
- [SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios](https://mlsanity.com/paper/2410.01481/) (2024)
- [Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation](https://mlsanity.com/paper/2210.15305/) (2022)
- [On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments](https://mlsanity.com/paper/2310.06125/) (2023)
- [End-to-End Integration of Speech Separation and Voice Activity Detection for Low-Latency Diarization of Telephone Conversations](https://mlsanity.com/paper/2303.12002/) (2023)
- [Sound Source Separation Using Latent Variational Block-Wise Disentanglement](https://mlsanity.com/paper/2402.06683/) (2024)
- [HiFi-Stream: Streaming Speech Enhancement with Generative Adversarial Networks](https://mlsanity.com/paper/2503.17141/) (2025)
- [Time-Frequency-Based Attention Cache Memory Model for Real-Time Speech Separation](https://mlsanity.com/paper/2505.13094/) (2025)
- [Improving Label Assignments Learning by Dynamic Sample Dropout Combined with Layer-wise Optimization in Speech Separation](https://mlsanity.com/paper/2311.12199/) (2023)
- [Effects of Dataset Sampling Rate for Noise Cancellation through Deep Learning](https://mlsanity.com/paper/2405.20884/) (2024)
- [Causal Self-supervised Pretrained Frontend with Predictive Code for Speech Separation](https://mlsanity.com/paper/2504.02302/) (2025)
- [Robust Target Speaker Diarization and Separation via Augmented Speaker Embedding Sampling](https://mlsanity.com/paper/2508.06393/) (2025)
- [TF-MoE: Time-Frequency Mixture-of-Experts for Efficient Speech Separation](https://mlsanity.com/paper/2606.29575/) (2026)

## Abstract (arXiv)

Continuous speech separation for meeting pre-processing has recently become a focused research topic. Compared to the data in utterance-level speech separation, the meeting-style audio stream lasts longer, has an uncertain number of speakers. We adopt the time-domain speech separation method and the recently proposed Graph-PIT to build a super low-latency online speech separation model, which is very important for the real application. The low-latency time-domain encoder with a small stride leads to an extremely long feature sequence. We proposed a simple yet efficient model named Skipping Memory (SkiM) for the long sequence modeling. Experimental results show that SkiM achieves on par or even better separation performance than DPRNN. Meanwhile, the computational cost of SkiM is reduced by 75% compared to DPRNN. The strong long sequence modeling capability and low computational cost make SkiM a suitable model for online CSS applications. Our fastest real-time model gets 17.1 dB signal-to-distortion (SDR) improvement with less than 1-millisecond latency in the simulated meeting-style evaluation.