Neural Directed Speech Enhancement With Dual Microphone Array In High Noise Scenario

Abstract

In multi-speaker scenarios, leveraging spatial features is essential for enhancing target speech. While with limited microphone arrays, developing a compact multi-channel speech enhancement system remains challenging, especially in extremely low signal-to-noise ratio (SNR) conditions. To tackle this issue, we propose a triple-steering spatial selection method, a flexible framework that uses three steering vectors to guide enhancement and determine the enhancement range. Specifically, we introduce a causal-directed U-Net (CDUNet) model, which takes raw multi-channel speech and the desired enhancement width as inputs. This enables dynamic adjustment of steering vectors based on the target direction and fine-tuning of the enhancement region according to the angular separation between the target and interference signals. Our model with only a dual microphone array, excels in both speech quality and downstream task performance. It operates in real-time with minimal parameters, making it ide

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywen2024neural

Related papers

• Multi-geometry Spatial Acoustic Modeling For Distant Speech Recognition (2019)6.34
• Efficient Multi-channel Speech Enhancement With Spherical Harmonics Injection For Directional Encoding (2023)3.58
• Real-time Stereo Speech Enhancement With Spatial-cue Preservation Based On Dual-path Structure (2024)5.84
• One Model To Enhance Them All: Array Geometry Agnostic Multi-channel Personalized Speech Enhancement (2021)0.00
• Insights Into Deep Non-linear Filters For Improved Multi-channel Speech Enhancement (2022)13.93
• Spatial-dccrn: Dccrn Equipped With Frame-level Angle Feature And Hybrid Filtering For Multi-channel Speech Enhancement (2022)5.84
• Dualsep: A Light-weight Dual-encoder Convolutional Recurrent Network For Real-time In-car Speech Separation (2024)0.00
• 3D Neural Beamforming For Multi-channel Speech Separation Against Location Uncertainty (2023)0.00