# Ultra-Lightweight Speech Separation via Group Communication

arXiv: https://arxiv.org/abs/2011.08397 · HTML: https://mlsanity.com/paper/2011.08397/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Nov 2020.

## Built on by (most cited first, 8 of 8)

- [Music Source Separation with Band-split RNN](https://mlsanity.com/paper/2209.15174/) (2022)
- [RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing](https://mlsanity.com/paper/2202.08862/) (2022)
- [Compute and memory efficient universal sound source separation](https://mlsanity.com/paper/2103.02644/) (2021)
- [Resource-Efficient Separation Transformer](https://mlsanity.com/paper/2206.09507/) (2022)
- [Separate but Together: Unsupervised Federated Learning for Speech Enhancement from Non-IID Data](https://mlsanity.com/paper/2105.04727/) (2021)
- [Continual self-training with bootstrapped remixing for speech enhancement](https://mlsanity.com/paper/2110.10103/) (2021)
- [Efficient Personalized Speech Enhancement through Self-Supervised Learning](https://mlsanity.com/paper/2104.02017/) (2021)
- [Scaling strategies for on-device low-complexity source separation with Conv-Tasnet](https://mlsanity.com/paper/2303.03005/) (2023)

## Abstract (arXiv)

Model size and complexity remain the biggest challenges in the deployment of speech enhancement and separation systems on low-resource devices such as earphones and hearing aids. Although methods such as compression, distillation and quantization can be applied to large models, they often come with a cost on the model performance. In this paper, we provide a simple model design paradigm that explicitly designs ultra-lightweight models without sacrificing the performance. Motivated by the sub-band frequency-LSTM (F-LSTM) architectures, we introduce the group communication (GroupComm), where a feature vector is split into smaller groups and a small processing block is used to perform inter-group communication. Unlike standard F-LSTM models where the sub-band outputs are concatenated, an ultra-small module is applied on all the groups in parallel, which allows a significant decrease on the model size. Experiment results show that comparing with a strong baseline model which is already lightweight, GroupComm can achieve on par performance with 35.6 times fewer parameters and 2.3 times fewer operations.