# Full Attention Bidirectional Deep Learning Structure for Single Channel Speech Enhancement

arXiv: https://arxiv.org/abs/2108.12105 · HTML: https://mlsanity.com/paper/2108.12105/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 24 references that are in the map.
- First posted on arXiv 27 Aug 2021.

## Builds on (most cited first, 6 of 6)

- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [SEGAN: Speech Enhancement Generative Adversarial Network](https://mlsanity.com/paper/1703.09452/) (2017)
- [A Wavenet for Speech Denoising](https://mlsanity.com/paper/1706.07162/) (2017)
- [THCHS-30 : A Free Chinese Speech Corpus](https://mlsanity.com/paper/1512.01882/) (2015)
- [A Hybrid DSP/Deep Learning Approach to Real-Time Full-Band Speech Enhancement](https://mlsanity.com/paper/1709.08243/) (2017)
- [T-GSA: Transformer with Gaussian-weighted self-attention for speech enhancement](https://mlsanity.com/paper/1910.06762/) (2019)

## Abstract (arXiv)

As the cornerstone of other important technologies, such as speech recognition and speech synthesis, speech enhancement is a critical area in audio signal processing. In this paper, a new deep learning structure for speech enhancement is demonstrated. The model introduces a "full" attention mechanism to a bidirectional sequence-to-sequence method to make use of latent information after each focal frame. This is an extension of the previous attention-based RNN method. The proposed bidirectional attention-based architecture achieves better performance in terms of speech quality (PESQ), compared with OM-LSA, CNN-LSTM, T-GSA and the unidirectional attention-based LSTM baseline.