Home / Publications / E-library page
Only AES members and Institutional Journal Subscribers can download
While challenging, sound source separation is a task that has many practical applications in audio signal processing. In this paper three sound files with two sources in each were separated using the non-negative matrix factorization (NMF) approach, with and without sparseness constraints. The results showed that adding sparseness constraints had no effect when separating drums and bass guitar but had better performances when separating piano and drums, and piano and bass guitar.
Author (s): Geng, Shijia; Leider, Colby N.
Affiliation:
University of Miami, Coral Gables, FL, USA
(See document for exact affiliation information.)
AES Convention: 139
Paper Number:231
Publication Date:
2015-10-06
Import into BibTeX
Permalink: https://aes2.org/publications/elibrary-page/?id=17907
(497KB)
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member Join the AES. If you need to check your member status, login to the Member Portal.
Geng, Shijia; Leider, Colby N.; 2015; Single-Channel Sound Source Separation Using NMF with Sparseness Constraints [PDF]; University of Miami, Coral Gables, FL, USA; Paper 231; Available from: https://aes2.org/publications/elibrary-page/?id=17907
Geng, Shijia; Leider, Colby N.; Single-Channel Sound Source Separation Using NMF with Sparseness Constraints [PDF]; University of Miami, Coral Gables, FL, USA; Paper 231; 2015 Available: https://aes2.org/publications/elibrary-page/?id=17907