Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

A Dynamic Latent Variable Model for Source Separation

Abstract: 

We propose a novel latent variable model for learning latent bases for time-varying non-negative data. Our model uses a mixture multinomial as the likelihood function and proposes a Dirichlet distribution with dynamic parameters as a prior, which we call the dynamic Dirichlet prior. An expectation maximization (EM) algorithm is developed for estimating the parameters of the proposed model. Furthermore, we connect our proposed dynamic Dirichlet latent variable model (dynamic DLVM) to the two popular latent basis learning methods - probabilistic latent component analysis (PLCA) and non-negative matrix factorization (NMF). We show that (i) PLCA is a special case of the dynamic DLVM, and (ii) dynamic DLVM can be interpreted as a dynamic version of NMF. The effectiveness of the proposed model is demonstrated through extensive experiments on speaker source separation, and speech-noise separation. In both cases, our method performs better than relevant and competitive baselines. For speaker separation, dynamic DLVM shows 1:38 dB improvement in terms of source to interference ratio, and 1 dB improvement in source to artifact ratio

up
0 users have voted:

Paper Details

Authors:
Anurendra Kumar, Tanaya Guha, Prasanta Ghosh
Submitted On:
19 April 2018 - 2:17pm
Short Link:
Type:
Poster
Event:
Presenter's Name:
Pavan Karjol
Paper Code:
2166
Document Year:
2018
Cite

Document Files

ICASSP_18.pdf

(172)

Subscribe

[1] Anurendra Kumar, Tanaya Guha, Prasanta Ghosh, "A Dynamic Latent Variable Model for Source Separation", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/2990. Accessed: Aug. 10, 2020.
@article{2990-18,
url = {http://sigport.org/2990},
author = {Anurendra Kumar; Tanaya Guha; Prasanta Ghosh },
publisher = {IEEE SigPort},
title = {A Dynamic Latent Variable Model for Source Separation},
year = {2018} }
TY - EJOUR
T1 - A Dynamic Latent Variable Model for Source Separation
AU - Anurendra Kumar; Tanaya Guha; Prasanta Ghosh
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/2990
ER -
Anurendra Kumar, Tanaya Guha, Prasanta Ghosh. (2018). A Dynamic Latent Variable Model for Source Separation. IEEE SigPort. http://sigport.org/2990
Anurendra Kumar, Tanaya Guha, Prasanta Ghosh, 2018. A Dynamic Latent Variable Model for Source Separation. Available at: http://sigport.org/2990.
Anurendra Kumar, Tanaya Guha, Prasanta Ghosh. (2018). "A Dynamic Latent Variable Model for Source Separation." Web.
1. Anurendra Kumar, Tanaya Guha, Prasanta Ghosh. A Dynamic Latent Variable Model for Source Separation [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/2990