Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization

This paper presents a statistical method of single-channel speech enhancement that uses a variational autoencoder (VAE) as a prior distribution on clean speech. A standard approach to speech enhancement is to train a deep neural network (DNN) to take noisy speech as input and output clean speech. Al...

Full description

Bibliographic Details

Published in:	2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 716 - 720
Main Authors:	Bando, Yoshiaki, Mimura, Masato, Itoyama, Katsutoshi, Yoshii, Kazuyoshi, Kawahara, Tatsuya
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.04.2018
Subjects:	Bayes methods Bayesian signal processing Data models Gaussian distribution Noise measurement Single-channel speech enhancement Spectrogram Speech enhancement Training variational autoencoder
ISSN:	2379-190X
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!