Complex Recurrent Variational Autoencoder with Application to Speech Enhancement

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xie, Yuying, Arildsen, Thomas, Tan, Zheng-Hua
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914990179483648
author Xie, Yuying
Arildsen, Thomas
Tan, Zheng-Hua
author_facet Xie, Yuying
Arildsen, Thomas
Tan, Zheng-Hua
contents As an extension of variational autoencoder (VAE), complex VAE uses complex Gaussian distributions to model latent variables and data. This work proposes a complex recurrent VAE framework, specifically in which complex-valued recurrent neural network and L1 reconstruction loss are used. Firstly, to account for the temporal property of speech signals, this work introduces complex-valued recurrent neural network in the complex VAE framework. Besides, L1 loss is used as the reconstruction loss in this framework. To exemplify the use of the complex generative model in speech processing, we choose speech enhancement as the specific application in this paper. Experiments are based on the TIMIT dataset. The results show that the proposed method offers improvements on objective metrics in speech intelligibility and signal quality.
format Preprint
id arxiv_https___arxiv_org_abs_2204_02195
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Complex Recurrent Variational Autoencoder with Application to Speech Enhancement
Xie, Yuying
Arildsen, Thomas
Tan, Zheng-Hua
Audio and Speech Processing
As an extension of variational autoencoder (VAE), complex VAE uses complex Gaussian distributions to model latent variables and data. This work proposes a complex recurrent VAE framework, specifically in which complex-valued recurrent neural network and L1 reconstruction loss are used. Firstly, to account for the temporal property of speech signals, this work introduces complex-valued recurrent neural network in the complex VAE framework. Besides, L1 loss is used as the reconstruction loss in this framework. To exemplify the use of the complex generative model in speech processing, we choose speech enhancement as the specific application in this paper. Experiments are based on the TIMIT dataset. The results show that the proposed method offers improvements on objective metrics in speech intelligibility and signal quality.
title Complex Recurrent Variational Autoencoder with Application to Speech Enhancement
topic Audio and Speech Processing
url https://arxiv.org/abs/2204.02195