# Dynamic Gated Recurrent Neural Network for Compute-efficient Speech Enhancement

arXiv: https://arxiv.org/abs/2408.12425 · HTML: https://mlsanity.com/paper/2408.12425/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 30 references that are in the map.
- First posted on arXiv 22 Aug 2024.

## Builds on (most cited first, 22 of 22)

- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [Supervised Speech Separation Based on Deep Learning: An Overview](https://mlsanity.com/paper/1708.07524/) (2017)
- [Real Time Speech Enhancement in the Waveform Domain](https://mlsanity.com/paper/2006.12847/) (2020)
- [Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation](https://mlsanity.com/paper/1910.06379/) (2019)
- [DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement](https://mlsanity.com/paper/2008.00264/) (2020)
- [The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results](https://mlsanity.com/paper/2005.13981/) (2020)
- [Phased LSTM: Accelerating Recurrent Network Training for Long or Event-based Sequences](https://mlsanity.com/paper/1610.09513/) (2016)
- [FullSubNet: A Full-Band and Sub-Band Fusion Model for Real-Time Single-Channel Speech Enhancement](https://mlsanity.com/paper/2010.15508/) (2020)
- [Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks](https://mlsanity.com/paper/1708.06834/) (2017)
- [TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids](https://mlsanity.com/paper/2005.11138/) (2020)
- [DeepFilterNet: A Low Complexity Speech Enhancement Framework for Full-Band Audio based on Deep Filtering](https://mlsanity.com/paper/2110.05588/) (2021)
- [DPT-FSNet: Dual-path Transformer Based Full-band and Sub-band Fusion Network for Speech Enhancement](https://mlsanity.com/paper/2104.13002/) (2021)
- [FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement](https://mlsanity.com/paper/2203.12188/) (2022)
- [Spartus: A 9.4 TOp/s FPGA-based LSTM Accelerator Exploiting Spatio-Temporal Sparsity](https://mlsanity.com/paper/2108.02297/) (2021)
- [Delta Networks for Optimized Recurrent Network Computation](https://mlsanity.com/paper/1612.05571/) (2016)
- [High Fidelity Speech Enhancement with Band-split RNN](https://mlsanity.com/paper/2212.00406/) (2022)
- [DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement](https://mlsanity.com/paper/2107.05429/) (2021)
- [TPARN: Triple-path Attentive Recurrent Network for Time-domain Multichannel Speech Enhancement](https://mlsanity.com/paper/2110.10757/) (2021)
- [Inference skipping for more efficient real-time speech enhancement with parallel RNNs](https://mlsanity.com/paper/2207.11108/) (2022)
- [Ultra Dual-Path Compression For Joint Echo Cancellation And Noise Suppression](https://mlsanity.com/paper/2308.11053/) (2023)
- [A General Unfolding Speech Enhancement Method Motivated by Taylor's Theorem](https://mlsanity.com/paper/2211.16764/) (2022)
- [Complexity Scaling for Speech Denoising](https://mlsanity.com/paper/2309.07757/) (2023)

## Built on by (most cited first, 5 of 5)

- [Modulating State Space Model with SlowFast Framework for Compute-Efficient Ultra Low-Latency Speech Enhancement](https://mlsanity.com/paper/2411.02019/) (2024)
- [CleanUMamba: A Compact Mamba Network for Speech Denoising using Channel Pruning](https://mlsanity.com/paper/2410.11062/) (2024)
- [From Diet to Free Lunch: Estimating Auxiliary Signal Properties using Dynamic Pruning Masks in Speech Enhancement Networks](https://mlsanity.com/paper/2602.10666/) (2026)
- [Neural Networks with LSTM and GRU in Modeling Active Fires in the Amazon](https://mlsanity.com/paper/2409.02681/) (2024)
- [Towards Lightweight Adaptation of Speech Enhancement Models in Real-World Environments](https://mlsanity.com/paper/2603.07471/) (2026)

## Abstract (arXiv)

This paper introduces a new Dynamic Gated Recurrent Neural Network (DG-RNN) for compute-efficient speech enhancement models running on resource-constrained hardware platforms. It leverages the slow evolution characteristic of RNN hidden states over steps, and updates only a selected set of neurons at each step by adding a newly proposed select gate to the RNN model. This select gate allows the computation cost of the conventional RNN to be reduced during network inference. As a realization of the DG-RNN, we further propose the Dynamic Gated Recurrent Unit (D-GRU) which does not require additional parameters. Test results obtained from several state-of-the-art compute-efficient RNN-based speech enhancement architectures using the DNS challenge dataset, show that the D-GRU based model variants maintain similar speech intelligibility and quality metrics comparable to the baseline GRU based models even with an average 50% reduction in GRU computes.