# Time-Frequency-Based Attention Cache Memory Model for Real-Time Speech Separation

arXiv: https://arxiv.org/abs/2505.13094 · HTML: https://mlsanity.com/paper/2505.13094/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 31 references that are in the map.
- First posted on arXiv 19 May 2025.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [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)
- [Supervised Speech Separation Based on Deep Learning: An Overview](https://mlsanity.com/paper/1708.07524/) (2017)
- [Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation](https://mlsanity.com/paper/1607.00325/) (2016)
- [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)
- [WHAM!: Extending Speech Separation to Noisy Environments](https://mlsanity.com/paper/1907.01160/) (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)
- [Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation](https://mlsanity.com/paper/2007.13975/) (2020)
- [WHAMR!: Noisy and Reverberant Single-Channel Speech Separation](https://mlsanity.com/paper/1910.10279/) (2019)
- [TF-GridNet: Making Time-Frequency Domain Models Great Again for Monaural Speaker Separation](https://mlsanity.com/paper/2209.03952/) (2022)
- [An efficient encoder-decoder architecture with top-down attention for speech separation](https://mlsanity.com/paper/2209.15200/) (2022)
- [Speech Separation Using an Asynchronous Fully Recurrent Convolutional Neural Network](https://mlsanity.com/paper/2112.02321/) (2021)
- [Recognizing Overlapped Speech in Meetings: A Multichannel Separation Approach Using Neural Networks](https://mlsanity.com/paper/1810.03655/) (2018)
- [Advances in Online Audio-Visual Meeting Transcription](https://mlsanity.com/paper/1912.04979/) (2019)
- [SkiM: Skipping Memory LSTM for Low-Latency Real-Time Continuous Speech Separation](https://mlsanity.com/paper/2201.10800/) (2022)
- [On the Use of Deep Mask Estimation Module for Neural Source Separation Systems](https://mlsanity.com/paper/2206.07347/) (2022)
- [Resource-Efficient Separation Transformer](https://mlsanity.com/paper/2206.09507/) (2022)
- [IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation](https://mlsanity.com/paper/2308.08143/) (2023)
- [On the Design and Training Strategies for RNN-based Online Neural Speech Separation Systems](https://mlsanity.com/paper/2206.07340/) (2022)
- [Multi-Channel Target Speaker Extraction with Refinement: The WavLab Submission to the Second Clarity Enhancement Challenge](https://mlsanity.com/paper/2302.07928/) (2023)
- [An End-to-end Architecture of Online Multi-channel Speech Separation](https://mlsanity.com/paper/2009.03141/) (2020)

## Built on by (most cited first, 1 of 1)

- [Inside the Latent Flow: Causal Deciphering of Attention Dynamics in Audio Separation Foundation Models](https://mlsanity.com/paper/2606.10046/) (2026)

## Abstract (arXiv)

Existing causal speech separation models often underperform compared to non-causal models due to difficulties in retaining historical information. To address this, we propose the Time-Frequency Attention Cache Memory (TFACM) model, which effectively captures spatio-temporal relationships through an attention mechanism and cache memory (CM) for historical information storage. In TFACM, an LSTM layer captures frequency-relative positions, while causal modeling is applied to the time dimension using local and global representations. The CM module stores past information, and the causal attention refinement (CAR) module further enhances time-based feature representations for finer granularity. Experimental results showed that TFACM achieveed comparable performance to the SOTA TF-GridNet-Causal model, with significantly lower complexity and fewer trainable parameters. For more details, visit the project page: https://cslikai.cn/TFACM/.