12 citations · 13 across the 15 of their papers we have counts for
7 papers · 1 filter
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…
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…
FoVNet: Configurable Field-of-View Speech Enhancement with Low Computation and Distortion for Smart Glasses
Zhongweiyang Xu, Ali Aroudi, Ke Tan +4
This paper presents a novel multi-channel speech enhancement approach, FoVNet, that enables highly efficient speech enhancement within a configurable field of view (FoV) of a smart…
All Neural Low-latency Directional Speech Extraction
Ashutosh Pandey, Sanha Lee, Juan Azcarreta +2
We introduce a novel all neural model for low-latency directional speech extraction. The model uses direction of arrival (DOA) embeddings from a predefined spatial grid, which are…
Speech enhancement deep-learning architecture for efficient edge processing
Monisankha Pal, Arvind Ramanathan, Ted Wada +1
Deep learning has become a de facto method of choice for speech enhancement tasks with significant improvements in speech quality. However, real-time processing with reduced size a…
On the Importance of Neural Wiener Filter for Resource Efficient Multichannel Speech Enhancement
Tsun-An Hsieh, Jacob Donley, Daniel Wong +2
We introduce a time-domain framework for efficient multichannel speech enhancement, emphasizing low latency and computational efficiency. This framework incorporates two compact de…
Decoupled Spatial and Temporal Processing for Resource Efficient Multichannel Speech Enhancement
Ashutosh Pandey, Buye Xu
We present a novel model designed for resource-efficient multichannel speech enhancement in the time domain, with a focus on low latency, lightweight, and low computational require…