# DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancement

arXiv: https://arxiv.org/abs/2106.15813 · HTML: https://mlsanity.com/paper/2106.15813/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jun 2021.

## Built on by (most cited first, 16 of 16)

- [MT3: Multi-Task Multitrack Music Transcription](https://mlsanity.com/paper/2111.03017/) (2021)
- [SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping](https://mlsanity.com/paper/2203.16749/) (2022)
- [CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement](https://mlsanity.com/paper/2209.11112/) (2022)
- [Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations](https://mlsanity.com/paper/2303.01664/) (2023)
- [Insights Into Deep Non-linear Filters for Improved Multi-channel Speech Enhancement](https://mlsanity.com/paper/2206.13310/) (2022)
- [FLEURS-R: A Restored Multilingual Speech Corpus for Generation Tasks](https://mlsanity.com/paper/2408.06227/) (2024)
- [HM-Conformer: A Conformer-based audio deepfake detection system with hierarchical pooling and multi-level classification token aggregation methods](https://mlsanity.com/paper/2309.08208/) (2023)
- [On the Role of Spatial, Spectral, and Temporal Processing for DNN-based Non-linear Multi-channel Speech Enhancement](https://mlsanity.com/paper/2206.11181/) (2022)
- [AudioSlots: A slot-centric generative model for audio separation](https://mlsanity.com/paper/2305.05591/) (2023)
- [Exploring Self-Attention Mechanisms for Speech Separation](https://mlsanity.com/paper/2202.02884/) (2022)
- [BLOOM-Net: Blockwise Optimization for Masking Networks Toward Scalable and Efficient Speech Enhancement](https://mlsanity.com/paper/2111.09372/) (2021)
- [Linguistic Knowledge Transfer Learning for Speech Enhancement](https://mlsanity.com/paper/2503.07078/) (2025)
- [Exploiting Time-Frequency Conformers for Music Audio Enhancement](https://mlsanity.com/paper/2308.12599/) (2023)
- [Miipher-2: A Universal Speech Restoration Model for Million-Hour Scale Data Restoration](https://mlsanity.com/paper/2505.04457/) (2025)
- [Sampling-Frequency-Independent Universal Sound Separation](https://mlsanity.com/paper/2309.12581/) (2023)
- [UniPASE: A Generative Model for Universal Speech Enhancement with High Fidelity and Low Hallucinations](https://mlsanity.com/paper/2604.14606/) (2026)

## Abstract (arXiv)

Single-channel speech enhancement (SE) is an important task in speech processing. A widely used framework combines an analysis/synthesis filterbank with a mask prediction network, such as the Conv-TasNet architecture. In such systems, the denoising performance and computational efficiency are mainly affected by the structure of the mask prediction network. In this study, we aim to improve the sequential modeling ability of Conv-TasNet architectures by integrating Conformer layers into a new mask prediction network. To make the model computationally feasible, we extend the Conformer using linear complexity attention and stacked 1-D dilated depthwise convolution layers. We trained the model on 3,396 hours of noisy speech data, and show that (i) the use of linear complexity attention avoids high computational complexity, and (ii) our model achieves higher scale-invariant signal-to-noise ratio than the improved time-dilated convolution network (TDCN++), an extended version of Conv-TasNet.