mlsanityData to 14 Oct 2026

Efficient Transformer-based Speech Enhancement Using Long Frames and STFT Magnitudes

arXiv 2206.11703 ↗First posted 23 Jun 2022eess.AS cs.LG cs.SDcited by 10

Not on the map. Why?

Abstract (arXiv)

The SepFormer architecture shows very good results in speech separation. Like other learned-encoder models, it uses short frames, as they have been shown to obtain better performance in these cases. This results in a large number of frames at the input, which is problematic; since the SepFormer is transformer-based, its computational complexity drastically increases with longer sequences. In this paper, we employ the SepFormer in a speech enhancement task and show that by replacing the learned-encoder features with a magnitude short-time Fourier transform (STFT) representation, we can use long frames without compromising perceptual enhancement performance. We obtained equivalent quality and intelligibility evaluation scores while reducing the number of operations by a factor of approximately 8 for a 10-second utterance.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 17 of its 30 references that are in the map. First posted on arXiv 23 Jun 2022.

Builds on

17 of 30 references.

References · 17

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  4. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  5. 2018SDR - half-baked or well done?cited by 423
  6. 2018Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separationcited by 406
  7. 2020Attention is All You Need in Speech Separationcited by 185
  8. 2019Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separationcited by 182
  9. 2020The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Resultscited by 133
  10. 2020Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separationcited by 68
  11. 2019T-GSA: Transformer with Gaussian-weighted self-attention for speech enhancementcited by 34
  12. 2019Filterbank design for end-to-end speech separationcited by 16
5 more
  1. 2019Demystifying TasNet: A Dissecting Approachcited by 12
  2. 2019A Multi-Phase Gammatone Filterbank for Speech Separation via TasNetcited by 11
  3. 2020Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-trainingcited by 6
  4. 2022Phase-Aware Deep Speech Enhancement: It's All About The Frame Lengthcited by 5
  5. 2020SNR-Based Features and Diverse Training Data for Robust DNN-Based Speech Enhancementcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 1; 2025: 5; 2026: 1.

10 papers.

  1. 2025Speech Enhancement Using Continuous Embeddings of Neural Audio Codeccited by 7
  2. 2023On the Behavior of Intrusive and Non-intrusive Speech Enhancement Metrics in Predictive and Generative Settingscited by 6
  3. 2025xLSTM-SENet: xLSTM for Single-Channel Speech Enhancementcited by 4
  4. 2022Deep neural network techniques for monaural speech enhancement: state of the art analysiscited by 3
  5. 2025Linguistic Knowledge Transfer Learning for Speech Enhancementcited by 3
  6. 2025MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancementcited by 2
  7. 2023ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attentioncited by 1
  8. 2024Effective Noise-aware Data Simulation for Domain-adaptive Speech Enhancement Leveraging Dynamic Stochastic Perturbationcited by 1
  9. 2025Active Speech Enhancement: Active Speech Denoising Decliping and Deveraberationcited by 0
  10. 2026Universal Robust Speech Adaptation for Cross-Domain Speech Recognition and Enhancementcited by 0