I-DCCRN-VAE: An Improved Deep Representation Learning Framework for Complex VAE-based Single-channel Speech Enhancement

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Jiatong, Doclo, Simon
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917240134172672
author Li, Jiatong
Doclo, Simon
author_facet Li, Jiatong
Doclo, Simon
contents Recently, a complex variational autoencoder (VAE)-based single-channel speech enhancement system based on the DCCRN architecture has been proposed. In this system, a noise suppression VAE (NSVAE) learns to extract clean speech representations from noisy speech using pretrained clean speech and noise VAEs with skip connections. In this paper, we improve DCCRN-VAE by incorporating three key modifications: 1) removing the skip connections in the pretrained VAEs to encourage more informative speech and noise latent representations; 2) using $β$-VAE in pretraining to better balance reconstruction and latent space regularization; and 3) a NSVAE generating both speech and noise latent representations. Experiments show that the proposed system achieves comparable performance as the DCCRN and DCCRN-VAE baselines on the matched DNS3 dataset but outperforms the baselines on mismatched datasets (WSJ0-QUT, Voicebank-DEMEND), demonstrating improved generalization ability. In addition, an ablation study shows that a similar performance can be achieved with classical fine-tuning instead of adversarial training, resulting in a simpler training pipeline.
format Preprint
id arxiv_https___arxiv_org_abs_2510_12485
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle I-DCCRN-VAE: An Improved Deep Representation Learning Framework for Complex VAE-based Single-channel Speech Enhancement
Li, Jiatong
Doclo, Simon
Audio and Speech Processing
Recently, a complex variational autoencoder (VAE)-based single-channel speech enhancement system based on the DCCRN architecture has been proposed. In this system, a noise suppression VAE (NSVAE) learns to extract clean speech representations from noisy speech using pretrained clean speech and noise VAEs with skip connections. In this paper, we improve DCCRN-VAE by incorporating three key modifications: 1) removing the skip connections in the pretrained VAEs to encourage more informative speech and noise latent representations; 2) using $β$-VAE in pretraining to better balance reconstruction and latent space regularization; and 3) a NSVAE generating both speech and noise latent representations. Experiments show that the proposed system achieves comparable performance as the DCCRN and DCCRN-VAE baselines on the matched DNS3 dataset but outperforms the baselines on mismatched datasets (WSJ0-QUT, Voicebank-DEMEND), demonstrating improved generalization ability. In addition, an ablation study shows that a similar performance can be achieved with classical fine-tuning instead of adversarial training, resulting in a simpler training pipeline.
title I-DCCRN-VAE: An Improved Deep Representation Learning Framework for Complex VAE-based Single-channel Speech Enhancement
topic Audio and Speech Processing
url https://arxiv.org/abs/2510.12485