mlsanityData to 19 Oct 2026

Attention does not guarantee best performance in speech enhancement

arXiv 2302.05690 ↗First posted 11 Feb 2023cs.SD eess.AScited by 0

On the map: Speech and audio language models → Speech enhancement and noise suppression

Abstract (arXiv)

Attention mechanism has been widely utilized in speech enhancement (SE) because theoretically it can effectively model the long-term inherent connection of signal both in time domain and spectrum domain. However, the generally used global attention mechanism might not be the best choice since the adjacent information naturally imposes more influence than the far-apart information in speech enhancement. In this paper, we validate this conjecture by replacing attention with RNN in two typical state-of-the-art (SOTA) models, multi-scale temporal frequency convolutional network (MTFAA) with axial attention and conformer-based metric-GAN network (CMGAN).

Key facts. No citing papers in the map yet (data through 19 Oct 2026). Placed in Speech enhancement and noise suppression, one of 11 directions in Speech and audio language models. Builds on 4 of its 10 references that are in the map. First posted on arXiv 11 Feb 2023.

Builds on

4 of 10 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement22 Sep

Other references · 3

  1. 2019Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separationcited by 275
  2. 2022ICASSP 2022 Deep Noise Suppression Challengecited by 107
  3. 2022Description and Discussion on DCASE 2022 Challenge Task 2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring Applying Domain Generalization Techniquescited by 21

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021CycleGAN-based Non-parallel Speech Enhancement with an Adaptive Attention-in-attention Mechanism
  2. 2021Time-Frequency Attention for Monaural Speech Enhancement
  3. 2021Full Attention Bidirectional Deep Learning Structure for Single Channel Speech Enhancement
  4. 2022Multi-View Attention Transfer for Efficient Speech Enhancement
  5. 2025LMFCA-Net: A Lightweight Model for Multi-Channel Speech Enhancement with Efficient Narrow-Band and Cross-Band Attention
  6. 2023Efficient Encoder-Decoder and Dual-Path Conformer for Comprehensive Feature Learning in Speech Enhancement
  7. 2023Real-time speech enhancement with dynamic attention span
  8. 2021Dual-branch Attention-In-Attention Transformer for single-channel speech enhancement