Dynamic Gated Recurrent Neural Network For Compute-efficient Speech Enhancement

Abstract

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.

Stats

• citations12
• S2 citations—
• github stars0
• HF likes0
• heat score8.35
• arxiv keycheng2024dynamic

Related papers

• Dynamically Slimmable Speech Enhancement Network With Metric-guided Training (2025)0.00
• Dynamic Attention Based Generative Adversarial Network With Phase Post-processing For Speech Enhancement (2020)0.00
• Light Gated Recurrent Units For Speech Recognition (2018)18.90
• Improving Speech Recognition By Revising Gated Recurrent Units (2017)11.19
• Inference Skipping For More Efficient Real-time Speech Enhancement With Parallel Rnns (2022)10.35
• DCCRGAN: Deep Complex Convolution Recurrent Generator Adversarial Network For Speech Enhancement (2020)0.00
• Unsupervised Speech Enhancement With Deep Dynamical Generative Speech And Noise Models (2023)0.00
• Memory Visualization For Gated Recurrent Neural Networks In Speech Recognition (2016)11.76