# Mel-McNet: A Mel-Scale Framework for Online Multichannel Speech Enhancement

arXiv: https://arxiv.org/abs/2505.19576 · HTML: https://mlsanity.com/paper/2505.19576/

## 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 23 of its 30 references that are in the map.
- First posted on arXiv 26 May 2025.

## 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, 23 of 23)

- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [Supervised Speech Separation Based on Deep Learning: An Overview](https://mlsanity.com/paper/1708.07524/) (2017)
- [DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors](https://mlsanity.com/paper/2110.01763/) (2021)
- [Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis](https://mlsanity.com/paper/2306.00814/) (2023)
- [AISHELL-2: Transforming Mandarin ASR Research Into Industrial Scale](https://mlsanity.com/paper/1808.10583/) (2018)
- [TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separation](https://mlsanity.com/paper/2211.12433/) (2022)
- [ICASSP 2023 Deep Noise Suppression Challenge](https://mlsanity.com/paper/2303.11510/) (2023)
- [PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network](https://mlsanity.com/paper/1911.04697/) (2019)
- [EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation](https://mlsanity.com/paper/2406.06185/) (2024)
- [FaSNet: Low-latency Adaptive Beamforming for Multi-microphone Audio Processing](https://mlsanity.com/paper/1909.13387/) (2019)
- [THCHS-30 : A Free Chinese Speech Corpus](https://mlsanity.com/paper/1512.01882/) (2015)
- [SpatialNet: Extensively Learning Spatial Information for Multichannel Joint Speech Separation, Denoising and Dereverberation](https://mlsanity.com/paper/2307.16516/) (2023)
- [Multichannel Long-Term Streaming Neural Speech Enhancement for Static and Moving Speakers](https://mlsanity.com/paper/2403.07675/) (2024)
- [Insights Into Deep Non-linear Filters for Improved Multi-channel Speech Enhancement](https://mlsanity.com/paper/2206.13310/) (2022)
- [Embedding and Beamforming: All-neural Causal Beamformer for Multichannel Speech Enhancement](https://mlsanity.com/paper/2109.00265/) (2021)
- [TPARN: Triple-path Attentive Recurrent Network for Time-domain Multichannel Speech Enhancement](https://mlsanity.com/paper/2110.10757/) (2021)
- [A Multi-Phase Gammatone Filterbank for Speech Separation via TasNet](https://mlsanity.com/paper/1910.11615/) (2019)
- [McNet: Fuse Multiple Cues for Multichannel Speech Enhancement](https://mlsanity.com/paper/2211.08872/) (2022)
- [Unsupervised Speech Enhancement Based on Multichannel NMF-Informed Beamforming for Noise-Robust Automatic Speech Recognition](https://mlsanity.com/paper/1903.09341/) (2019)
- [Multichannel Speech Enhancement without Beamforming](https://mlsanity.com/paper/2110.13130/) (2021)
- [Deep Neural Mel-Subband Beamformer for In-car Speech Separation](https://mlsanity.com/paper/2211.12590/) (2022)
- [Ultra Dual-Path Compression For Joint Echo Cancellation And Noise Suppression](https://mlsanity.com/paper/2308.11053/) (2023)
- [Mel-FullSubNet: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR](https://mlsanity.com/paper/2402.13511/) (2024)

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

- [U-PAST: A Phase-Aware Audio Spectrogram Transformer-U-Net for Single-Channel Speech Enhancement](https://mlsanity.com/paper/2609.00431/) (2026)
- [DualSpecSE: A Dual-Path Speech Enhancement Network Integrating Mel and Complex Spectrograms](https://mlsanity.com/paper/2609.13911/) (2026)

## Abstract (arXiv)

Online multichannel speech enhancement has been intensively studied recently. Though Mel-scale frequency is more matched with human auditory perception and computationally efficient than linear frequency, few works are implemented in a Mel-frequency domain. To this end, this work proposes a Mel-scale framework (namely Mel-McNet). It processes spectral and spatial information with two key components: an effective STFT-to-Mel module compressing multi-channel STFT features into Mel-frequency representations, and a modified McNet backbone directly operating in the Mel domain to generate enhanced LogMel spectra. The spectra can be directly fed to vocoders for waveform reconstruction or ASR systems for transcription. Experiments on CHiME-3 show that Mel-McNet can reduce computational complexity by 60% while maintaining comparable enhancement and ASR performance to the original McNet. Mel-McNet also outperforms other SOTA methods, verifying the potential of Mel-scale speech enhancement.