# Multi-View Attention Transfer for Efficient Speech Enhancement

arXiv: https://arxiv.org/abs/2208.10367 · HTML: https://mlsanity.com/paper/2208.10367/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 22 Aug 2022.

## Builds on (most cited first, 20 of 20)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [Paraphrasing Complex Network: Network Compression via Factor Transfer](https://mlsanity.com/paper/1802.04977/) (2018)
- [Real Time Speech Enhancement in the Waveform Domain](https://mlsanity.com/paper/2006.12847/) (2020)
- [The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results](https://mlsanity.com/paper/2005.13981/) (2020)
- [MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement](https://mlsanity.com/paper/2104.03538/) (2021)
- [MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement](https://mlsanity.com/paper/1905.04874/) (2019)
- [PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network](https://mlsanity.com/paper/1911.04697/) (2019)
- [TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domain](https://mlsanity.com/paper/2103.09963/) (2021)
- [MANNER: Multi-view Attention Network for Noise Erasure](https://mlsanity.com/paper/2203.02181/) (2022)
- [Knowledge Distillation for Small-footprint Highway Networks](https://mlsanity.com/paper/1608.00892/) (2016)
- [Interactive Speech and Noise Modeling for Speech Enhancement](https://mlsanity.com/paper/2012.09408/) (2020)
- [Sub-Band Knowledge Distillation Framework for Speech Enhancement](https://mlsanity.com/paper/2005.14435/) (2020)
- [Acoustic scene classification using teacher-student learning with soft-labels](https://mlsanity.com/paper/1904.10135/) (2019)
- [Compression of Acoustic Event Detection Models With Quantized Distillation](https://mlsanity.com/paper/1907.00873/) (2019)
- [Semi-supervised Acoustic Event Detection based on tri-training](https://mlsanity.com/paper/1904.12926/) (2019)
- [SNR-Based Teachers-Student Technique for Speech Enhancement](https://mlsanity.com/paper/2005.14441/) (2020)
- [Dual-path Self-Attention RNN for Real-Time Speech Enhancement](https://mlsanity.com/paper/2010.12713/) (2020)

## Built on by (most cited first, 7 of 7)

- [Two-Step Knowledge Distillation for Tiny Speech Enhancement](https://mlsanity.com/paper/2309.08144/) (2023)
- [Distil-DCCRN: A Small-footprint DCCRN Leveraging Feature-based Knowledge Distillation in Speech Enhancement](https://mlsanity.com/paper/2408.04267/) (2024)
- [MUSE: Flexible Voiceprint Receptive Fields and Multi-Path Fusion Enhanced Taylor Transformer for U-Net-based Speech Enhancement](https://mlsanity.com/paper/2406.04589/) (2024)
- [Efficient Encoder-Decoder and Dual-Path Conformer for Comprehensive Feature Learning in Speech Enhancement](https://mlsanity.com/paper/2306.05861/) (2023)
- [ROSE: A Recognition-Oriented Speech Enhancement Framework in Air Traffic Control Using Multi-Objective Learning](https://mlsanity.com/paper/2312.06118/) (2023)
- [IMSE: Efficient U-Net-based Speech Enhancement using Inception Depthwise Convolution and Amplitude-Aware Linear Attention](https://mlsanity.com/paper/2511.14515/) (2025)
- [BASENet: Band-Adapted Speech Enhancement Network with Cross-Band Attention](https://mlsanity.com/paper/2606.12662/) (2026)

## Abstract (arXiv)

Recent deep learning models have achieved high performance in speech enhancement; however, it is still challenging to obtain a fast and low-complexity model without significant performance degradation. Previous knowledge distillation studies on speech enhancement could not solve this problem because their output distillation methods do not fit the speech enhancement task in some aspects. In this study, we propose multi-view attention transfer (MV-AT), a feature-based distillation, to obtain efficient speech enhancement models in the time domain. Based on the multi-view features extraction model, MV-AT transfers multi-view knowledge of the teacher network to the student network without additional parameters. The experimental results show that the proposed method consistently improved the performance of student models of various sizes on the Valentini and deep noise suppression (DNS) datasets. MANNER-S-8.1GF with our proposed method, a lightweight model for efficient deployment, achieved 15.4x and 4.71x fewer parameters and floating-point operations (FLOPs), respectively, compared to the baseline model with similar performance.