# PCNN: A Lightweight Parallel Conformer Neural Network for Efficient Monaural Speech Enhancement

arXiv: https://arxiv.org/abs/2307.15251 · HTML: https://mlsanity.com/paper/2307.15251/

## Key facts

- Cited by 2 papers in the map (data through 19 Oct 2026).
- Placed in Speech enhancement and noise suppression, one of 11 directions in Speech and audio language models.
- Builds on 18 of its 30 references that are in the map.
- First posted on arXiv 28 Jul 2023.

## Placed in

- Speech and audio language models / [Speech enhancement and noise suppression](https://mlsanity.com/speech/speech-enhancement-and-noise-suppression/)

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation](https://mlsanity.com/paper/1809.07454/) (2018)
- [Selective Kernel Networks](https://mlsanity.com/paper/1903.06586/) (2019)
- [ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks](https://mlsanity.com/paper/1908.03930/) (2019)
- [TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domain](https://mlsanity.com/paper/2103.09963/) (2021)
- [A Fully Convolutional Neural Network for Speech Enhancement](https://mlsanity.com/paper/1609.07132/) (2016)
- [Dual-branch Attention-In-Attention Transformer for single-channel speech enhancement](https://mlsanity.com/paper/2110.06467/) (2021)
- [Self-Attentional Acoustic Models](https://mlsanity.com/paper/1803.09519/) (2018)
- [FurcaNeXt: End-to-end monaural speech separation with dynamic gated dilated temporal convolutional networks](https://mlsanity.com/paper/1902.04891/) (2019)
- [Magic ELF: Image Deraining Meets Association Learning and Transformer](https://mlsanity.com/paper/2207.10455/) (2022)
- [U-Former: Improving Monaural Speech Enhancement with Multi-head Self and Cross Attention](https://mlsanity.com/paper/2205.08681/) (2022)
- [GLD-Net: Improving Monaural Speech Enhancement by Learning Global and Local Dependency Features with GLD Block](https://mlsanity.com/paper/2206.14962/) (2022)
- [Selector-Enhancer: Learning Dynamic Selection of Local and Non-local Attention Operation for Speech Enhancement](https://mlsanity.com/paper/2212.03408/) (2022)

## Built on by (most cited first, 2 of 2)

- [Improving Speech Enhancement by Integrating Inter-Channel and Band Features with Dual-branch Conformer](https://mlsanity.com/paper/2407.06524/) (2024)
- [Improving Speech Enhancement by Cross- and Sub-band Processing with State Space Model](https://mlsanity.com/paper/2502.16207/) (2025)

## Abstract (arXiv)

Convolutional neural networks (CNN) and Transformer have wildly succeeded in multimedia applications. However, more effort needs to be made to harmonize these two architectures effectively to satisfy speech enhancement. This paper aims to unify these two architectures and presents a Parallel Conformer for speech enhancement. In particular, the CNN and the self-attention (SA) in the Transformer are fully exploited for local format patterns and global structure representations. Based on the small receptive field size of CNN and the high computational complexity of SA, we specially designed a multi-branch dilated convolution (MBDC) and a self-channel-time-frequency attention (Self-CTFA) module. MBDC contains three convolutional layers with different dilation rates for the feature from local to non-local processing. Experimental results show that our method performs better than state-of-the-art methods in most evaluation criteria while maintaining the lowest model parameters.