Decoupled Spatial And Temporal Processing For Resource Efficient Multichannel Speech Enhancement

Abstract

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 requirements. The proposed model incorporates explicit spatial and temporal processing within deep neural network (DNN) layers. Inspired by frequency-dependent multichannel filtering, our spatial filtering process applies multiple trainable filters to each hidden unit across the spatial dimension, resulting in a multichannel output. The temporal processing is applied over a single-channel output stream from the spatial processing using a Long Short-Term Memory (LSTM) network. The output from the temporal processing stage is then further integrated into the spatial dimension through elementwise multiplication. This explicit separation of spatial and temporal processing results in a resource-efficient network design. Empirical findings from our experiments show that our proposed model significantly outperforms robust

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypandey2024decoupled

Related papers

• On The Importance Of Neural Wiener Filter For Resource Efficient Multichannel Speech Enhancement (2024)0.00
• On The Role Of Spatial, Spectral, And Temporal Processing For Dnn-based Non-linear Multi-channel Speech Enhancement (2022)7.81
• Insights Into Deep Non-linear Filters For Improved Multi-channel Speech Enhancement (2022)13.93
• Narrow-band Deep Filtering For Multichannel Speech Enhancement (2019)0.00
• Spatialnet: Extensively Learning Spatial Information For Multichannel Joint Speech Separation, Denoising And Dereverberation (2023)13.88
• Lmfca-net: A Lightweight Model For Multi-channel Speech Enhancement With Efficient Narrow-band And Cross-band Attention (2025)3.58
• Multichannel Speech Enhancement Without Beamforming (2021)9.41
• Inter-channel Conv-tasnet For Multichannel Speech Enhancement (2021)0.00