# Rethinking complex-valued deep neural networks for monaural speech enhancement

arXiv: https://arxiv.org/abs/2301.04320 · HTML: https://mlsanity.com/paper/2301.04320/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 27 references that are in the map.
- First posted on arXiv 11 Jan 2023.

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

- [Language Modeling with Gated Convolutional Networks](https://mlsanity.com/paper/1612.08083/) (2016)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [Deep Complex Networks](https://mlsanity.com/paper/1705.09792/) (2017)
- [DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors](https://mlsanity.com/paper/2110.01763/) (2021)
- [DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement](https://mlsanity.com/paper/2008.00264/) (2020)
- [The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results](https://mlsanity.com/paper/2005.13981/) (2020)
- [Phase-aware Speech Enhancement with Deep Complex U-Net](https://mlsanity.com/paper/1903.03107/) (2019)
- [DCCRN+: Channel-wise Subband DCCRN with SNR Estimation for Speech Enhancement](https://mlsanity.com/paper/2106.08672/) (2021)
- [Complex spectrogram enhancement by convolutional neural network with multi-metrics learning](https://mlsanity.com/paper/1704.08504/) (2017)
- [Speech Quality Assessment through MOS using Non-Matching References](https://mlsanity.com/paper/2206.12285/) (2022)
- [S-DCCRN: Super Wide Band DCCRN with learnable complex feature for speech enhancement](https://mlsanity.com/paper/2111.08387/) (2021)
- [Listening to Sounds of Silence for Speech Denoising](https://mlsanity.com/paper/2010.12013/) (2020)
- [Monaural Speech Enhancement with Complex Convolutional Block Attention Module and Joint Time Frequency Losses](https://mlsanity.com/paper/2102.01993/) (2021)
- [End-to-End Complex-Valued Multidilated Convolutional Neural Network for Joint Acoustic Echo Cancellation and Noise Suppression](https://mlsanity.com/paper/2110.00745/) (2021)

## Built on by (most cited first, 6 of 6)

- [Investigating the Design Space of Diffusion Models for Speech Enhancement](https://mlsanity.com/paper/2312.04370/) (2023)
- [Assessing the Generalization Gap of Learning-Based Speech Enhancement Systems in Noisy and Reverberant Environments](https://mlsanity.com/paper/2309.06183/) (2023)
- [A Mask Free Neural Network for Monaural Speech Enhancement](https://mlsanity.com/paper/2306.04286/) (2023)
- [A Survey of Deep Learning for Complex Speech Spectrograms](https://mlsanity.com/paper/2505.08694/) (2025)
- [Leveraging Joint Spectral and Spatial Learning with MAMBA for Multichannel Speech Enhancement](https://mlsanity.com/paper/2409.10376/) (2024)
- [Hybrid Real- and Complex-valued Neural Network Architecture](https://mlsanity.com/paper/2504.03497/) (2025)

## Abstract (arXiv)

Despite multiple efforts made towards adopting complex-valued deep neural networks (DNNs), it remains an open question whether complex-valued DNNs are generally more effective than real-valued DNNs for monaural speech enhancement. This work is devoted to presenting a critical assessment by systematically examining complex-valued DNNs against their real-valued counterparts. Specifically, we investigate complex-valued DNN atomic units, including linear layers, convolutional layers, long short-term memory (LSTM), and gated linear units. By comparing complex- and real-valued versions of fundamental building blocks in the recently developed gated convolutional recurrent network (GCRN), we show how different mechanisms for basic blocks affect the performance. We also find that the use of complex-valued operations hinders the model capacity when the model size is small. In addition, we examine two recent complex-valued DNNs, i.e. deep complex convolutional recurrent network (DCCRN) and deep complex U-Net (DCUNET). Evaluation results show that both DNNs produce identical performance to their real-valued counterparts while requiring much more computation. Based on these comprehensive comparisons, we conclude that complex-valued DNNs do not provide a performance gain over their real-valued counterparts for monaural speech enhancement, and thus are less desirable due to their higher computational costs.