Redirecting to original paper in 30 seconds...

Click below to go immediately or wait for automatic redirect

arxiv_ai 90% Match Research Paper Speech processing researchers,Audio engineers,ML engineers in audio 1 week ago

Online neural fusion of distortionless differential beamformers for robust speech enhancement

speech-audio › speech-recognition
📄 Abstract

Abstract: Fixed beamforming is widely used in practice since it does not depend on the estimation of noise statistics and provides relatively stable performance. However, a single beamformer cannot adapt to varying acoustic conditions, which limits its interference suppression capability. To address this, adaptive convex combination (ACC) algorithms have been introduced, where the outputs of multiple fixed beamformers are linearly combined to improve robustness. Nevertheless, ACC often fails in highly non-stationary scenarios, such as rapidly moving interference, since its adaptive updates cannot reliably track rapid changes. To overcome this limitation, we propose a frame-online neural fusion framework for multiple distortionless differential beamformers, which estimates the combination weights through a neural network. Compared with conventional ACC, the proposed method adapts more effectively to dynamic acoustic environments, achieving stronger interference suppression while maintaining the distortionless constraint.
Authors (7)
Yuanhang Qian
Kunlong Zhao
Jilu Jin
Xueqin Luo
Gongping Huang
Jingdong Chen
+1 more
Submitted
October 28, 2025
arXiv Category
cs.SD
arXiv PDF

Key Contributions

Proposes a frame-online neural fusion framework for multiple distortionless differential beamformers. This method estimates combination weights via a neural network, enabling more effective adaptation to dynamic acoustic environments and stronger interference suppression compared to conventional ACC algorithms.

Business Value

Improved clarity and intelligibility of speech in noisy or dynamic environments, leading to better user experiences in voice assistants, teleconferencing, and hearing aids.