Home / Publications / E-library page
Only AES members and Institutional Journal Subscribers can download
The authors introduce the idea of performing it Intelligent ICA to focus on and separate a specific instrument, voice or sound source of interest. This is achieved by incorporating high-level probabilistic priors in the ICA model that characterise each instrument or voice. For instrument modelling, we experimented with various feature sets previously used for instrument or speaker recognition. Prior training of a Gaussian Mixture Model for each instrument was performed. The order of the feature vector, the number of gaussian mixtures and the training audio data length were kept to reasonably minimum levels.
Author (s): Mitianoudis, Nikolaos; Davies, Mike
Affiliation:
DSP Lab, Queen Mary College, University of London, London, UK
(See document for exact affiliation information.)
AES Convention: 112
Paper Number:5529
Publication Date:
2002-04-06
Import into BibTeX
Session subject:
Musical Acoustics
Permalink: https://aes2.org/publications/elibrary-page/?id=11326
(1306KB)
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.
Mitianoudis, Nikolaos; Davies, Mike; 2002; Intelligent Audio Source Separation using Independent Component Analysis [PDF]; DSP Lab, Queen Mary College, University of London, London, UK; Paper 5529; Available from: https://aes2.org/publications/elibrary-page/?id=11326
Mitianoudis, Nikolaos; Davies, Mike; Intelligent Audio Source Separation using Independent Component Analysis [PDF]; DSP Lab, Queen Mary College, University of London, London, UK; Paper 5529; 2002 Available: https://aes2.org/publications/elibrary-page/?id=11326