Fast-ULCNet: A fast and ultra low complexity network for single-channel speech enhancement

📅 2026-01-21
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This work addresses the demand for low-latency, low-complexity single-channel speech enhancement on resource-constrained embedded devices by proposing an improved architecture. Specifically, the original GRU in ULCNet is replaced with a lightweight FastGRNN, and a novel trainable complementary filter is introduced to mitigate state drift during long-duration audio inference. The proposed method achieves speech enhancement performance comparable to the original ULCNet while reducing model size by over 50% and decreasing average inference latency by 34%. These improvements significantly enhance deployment efficiency and practical applicability on edge hardware without compromising perceptual quality or intelligibility.

Technology Category

Application Category

📝 Abstract
Single-channel speech enhancement algorithms are often used in resource-constrained embedded devices, where low latency and low complexity designs gain more importance. In recent years, researchers have proposed a wide variety of novel solutions to this problem. In particular, a recent deep learning model named ULCNet is among the state-of-the-art approaches in this domain. This paper proposes an adaptation of ULCNet, by replacing its GRU layers with FastGRNNs, to reduce both computational latency and complexity. Furthermore, this paper shows empirical evidence on the performance decay of FastGRNNs in long audio signals during inference due to internal state drifting, and proposes a novel approach based on a trainable complementary filter to mitigate it. The resulting model, Fast-ULCNet, performs on par with the state-of-the-art original ULCNet architecture on a speech enhancement task, while reducing its model size by more than half and decreasing its latency by 34% on average.
Problem

Research questions and friction points this paper is trying to address.

speech enhancement
low complexity
single-channel
latency
state drift
Innovation

Methods, ideas, or system contributions that make the work stand out.

FastGRNN
state drifting mitigation
trainable complementary filter
ultra-low complexity
speech enhancement
🔎 Similar Papers
No similar papers found.
N
Nicolás Arrieta Larraza
Bang & Olufsen, Allé 1, 7600 Struer, Denmark
N
Niels de Koeijer
Bang & Olufsen, Allé 1, 7600 Struer, Denmark