Single-channel Speech Enhancement With Deep Complex U-networks And Probabilistic Latent Space Models

Abstract

In this paper, we propose to extend the deep, complex U-Network architecture for speech enhancement by incorporating a probabilistic (i.e., variational) latent space model. The proposed model is evaluated against several ablated versions of itself in order to study the effects of the variational latent space model, complex-value processing, and self-attention. Evaluation on the MS-DNS 2020 and Voicebank+Demand datasets yields consistently high performance. E.g., the proposed model achieves an SI-SDR of up to 20.2 dB, about 0.5 to 1.4 dB higher than its ablated version without probabilistic latent space, 2-2.4 dB higher than WaveUNet, and 6.7 dB above PHASEN. Compared to real-valued magnitude spectrogram processing with a variational U-Net, the complex U-Net achieves an improvement of up to 4.5 dB SI-SDR. Complex spectrum encoding as magnitude and phase yields best performance in anechoic conditions whereas real and imaginary part representation results in better generalization to (nove

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keynustede2023single

Related papers

• Phase-aware Speech Enhancement With Deep Complex U-net (2019)0.00
• Towards Speech Enhancement Using A Variational U-net Architecture (2020)7.81
• Improved Speech Enhancement With The Wave-u-net (2018)0.00
• Dilated U-net Based Approach For Multichannel Speech Enhancement From First-order Ambisonics Recordings (2020)0.00
• A Comparative Evaluation Of Deep Learning Models For Speech Enhancement In Real-world Noisy Environments (2025)0.00
• I-DCCRN-VAE: An Improved Deep Representation Learning Framework For Complex Vae-based Single-channel Speech Enhancement (2025)0.00
• Complex Recurrent Variational Autoencoder With Application To Speech Enhancement (2022)0.00
• Investigation Of Speech And Noise Latent Representations In Single-channel Vae-based Speech Enhancement (2025)0.00