activity
20242026
most citedDynamic Gated Recurrent Neural Network for Compute-efficient Speech Enhancement

12 citations · 12 across the 12 of their papers we have counts for

collaborators
Showing eess.ASShow all

5 papers · 1 filter

eess.AS2026

Unified Diffusion Refinement for Multi-Channel Speech Enhancement and Separation

Zhongweiyang Xu, Ashutosh Pandey, Juan Azcarreta +4

We propose Uni-ArrayDPS, a novel diffusion-based refinement framework for unified multi-channel speech enhancement and separation. Existing methods for multi-channel speech enhance…

eess.AS2026

ArrayDPS-Refine: Generative Refinement of Discriminative Multi-Channel Speech Enhancement

Zhongweiyang Xu, Ashutosh Pandey, Juan Azcarreta +3

Multi-channel speech enhancement aims to recover clean speech from noisy multi-channel recordings. Most deep learning methods employ discriminative training, which can lead to non-…

eess.AS2025

Improving Resource-Efficient Speech Enhancement via Neural Differentiable DSP Vocoder Refinement

Heitor R. Guimarães, Ke Tan, Juan Azcarreta +4

Deploying speech enhancement (SE) systems in wearable devices, such as smart glasses, is challenging due to the limited computational resources on the device. Although deep learnin…

eess.AS2024

Modulating State Space Model with SlowFast Framework for Compute-Efficient Ultra Low-Latency Speech Enhancement

Longbiao Cheng, Ashutosh Pandey, Buye Xu +3

Deep learning-based speech enhancement (SE) methods often face significant computational challenges when needing to meet low-latency requirements because of the increased number of…

eess.AS202412 cited

Dynamic Gated Recurrent Neural Network for Compute-efficient Speech Enhancement

Longbiao Cheng, Ashutosh Pandey, Buye Xu +2

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 l…