# Dual-Signal Transformation LSTM Network for Real-Time Noise Suppression

arXiv: https://arxiv.org/abs/2005.07551 · HTML: https://mlsanity.com/paper/2005.07551/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 May 2020.

## Built on by (most cited first, 13 of 13)

- [Real-time Denoising and Dereverberation with Tiny Recurrent U-Net](https://mlsanity.com/paper/2102.03207/) (2021)
- [Speech Denoising in the Waveform Domain with Self-Attention](https://mlsanity.com/paper/2202.07790/) (2022)
- [Weight, Block or Unit? Exploring Sparsity Tradeoffs for Speech Enhancement on Tiny Neural Accelerators](https://mlsanity.com/paper/2111.02351/) (2021)
- [DeepVQE: Real Time Deep Voice Quality Enhancement for Joint Acoustic Echo Cancellation, Noise Suppression and Dereverberation](https://mlsanity.com/paper/2306.03177/) (2023)
- [ABC-KD: Attention-Based-Compression Knowledge Distillation for Deep Learning-Based Noise Suppression](https://mlsanity.com/paper/2305.16665/) (2023)
- [Diffusion-based Signal Refiner for Speech Enhancement and Separation](https://mlsanity.com/paper/2305.05857/) (2023)
- [Improving Character Error Rate Is Not Equal to Having Clean Speech: Speech Enhancement for ASR Systems with Black-box Acoustic Models](https://mlsanity.com/paper/2110.05968/) (2021)
- [CleanUNet 2: A Hybrid Speech Denoising Model on Waveform and Spectrogram](https://mlsanity.com/paper/2309.05975/) (2023)
- [Training DeepFilterNet with Accurate Room Acoustic Simulations Improves Single-Channel Speech Enhancement](https://mlsanity.com/paper/2608.20971/) (2026)
- [Adaptive Speech Quality Aware Complex Neural Network for Acoustic Echo Cancellation with Supervised Contrastive Learning](https://mlsanity.com/paper/2210.16791/) (2022)
- [LC4SV: A Denoising Framework Learning to Compensate for Unseen Speaker Verification Models](https://mlsanity.com/paper/2311.16604/) (2023)
- [Leveraging Local and Global Knowledge Integration with Time-Frequency Calibrated Distillation for Speech Enhancement](https://mlsanity.com/paper/2506.13127/) (2025)
- [DBHN-Net: Dual-Branch Hybrid Neural Network For Low-Complexity Monaural Speech Enhancement](https://mlsanity.com/paper/2606.05911/) (2026)

## Abstract (arXiv)

This paper introduces a dual-signal transformation LSTM network (DTLN) for real-time speech enhancement as part of the Deep Noise Suppression Challenge (DNS-Challenge). This approach combines a short-time Fourier transform (STFT) and a learned analysis and synthesis basis in a stacked-network approach with less than one million parameters. The model was trained on 500 h of noisy speech provided by the challenge organizers. The network is capable of real-time processing (one frame in, one frame out) and reaches competitive results. Combining these two types of signal transformations enables the DTLN to robustly extract information from magnitude spectra and incorporate phase information from the learned feature basis. The method shows state-of-the-art performance and outperforms the DNS-Challenge baseline by 0.24 points absolute in terms of the mean opinion score (MOS).