# A two-step approach for speech enhancement in low-SNR scenarios using cyclostationary beamforming and DNNs

arXiv: https://arxiv.org/abs/2602.12986 · HTML: https://mlsanity.com/paper/2602.12986/

## Key facts

- Cited by 1 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 11 of its 24 references that are in the map.
- First posted on arXiv 13 Feb 2026.

## 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, 11 of 11)

- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results](https://mlsanity.com/paper/2005.13981/) (2020)
- [Ultra Low Complexity Deep Learning Based Noise Suppression](https://mlsanity.com/paper/2312.08132/) (2023)
- [UNetGAN: A Robust Speech Enhancement Approach in Time Domain for Extremely Low Signal-to-noise Ratio Condition](https://mlsanity.com/paper/2010.15521/) (2020)
- [Explainable DNN-based Beamformer with Postfilter](https://mlsanity.com/paper/2411.10854/) (2024)
- [Harmonic enhancement using learnable comb filter for light-weight full-band speech enhancement model](https://mlsanity.com/paper/2306.00812/) (2023)
- [SNR-Progressive Model with Harmonic Compensation for Low-SNR Speech Enhancement](https://mlsanity.com/paper/2406.16317/) (2024)
- [Wideband Relative Transfer Function (RTF) Estimation Exploiting Frequency Correlations](https://mlsanity.com/paper/2407.14152/) (2024)
- [A Lightweight Hybrid Dual Channel Speech Enhancement System under Low-SNR Conditions](https://mlsanity.com/paper/2505.19597/) (2025)
- [Cyclic Multichannel Wiener Filter for Acoustic Beamforming](https://mlsanity.com/paper/2507.10159/) (2025)

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

- [μNet: Ultra-Low-Memory and Low-Complexity Speech Enhancement for Embedded Digital Signal Processors](https://mlsanity.com/paper/2608.21155/) (2026)

## Abstract (arXiv)

Deep Neural Networks (DNNs) often struggle to suppress noise at low signal-to-noise ratios (SNRs). This paper addresses speech enhancement in scenarios dominated by harmonic noise and proposes a framework that integrates cyclostationarity-aware preprocessing with lightweight DNN-based denoising. A cyclic minimum power distortionless response (cMPDR) spectral beamformer is used as a preprocessing block. It exploits the spectral correlations of cyclostationary noise to suppress harmonic components prior to learning-based enhancement and does not require modifications to the DNN architecture. The proposed pipeline is evaluated in a single-channel setting using two DNN architectures: a simple and lightweight convolutional recurrent neural network (CRNN), and a state-of-the-art model, namely ultra-low complexity network (ULCNet). Experiments on synthetic data and real-world recordings dominated by rotating machinery noise demonstrate consistent improvements over end-to-end DNN baselines, particularly at low SNRs. Remarkably, a parameter-efficient CRNN with cMPDR preprocessing surpasses the performance of the larger ULCNet operating on raw or Wiener-filtered inputs. These results indicate that explicitly incorporating cyclostationarity as a signal prior is more effective than increasing model capacity alone for suppressing harmonic interference.