N. Mitianoudis and M. Davies, “Intelligent Audio Source Separation using Independent Component Analysis,” in Proc. AES Convention 112, Apr. 2002, pp. 5529:1-5. [Online]. Available: https://aes.org/publications/elibrary-page/?id=11326
Mitianoudis N, Davies M. Intelligent Audio Source Separation using Independent Component Analysis. In: AES Convention 112. Audio Engineering Society; 2002.pp. 5529:1-5. Available from: https://aes.org/publications/elibrary-page/?id=11326
@inproceedings{Mitianoudis2002_11326,
author = {Mitianoudis, Nikolaos and Davies, Mike},
title = {{Intelligent Audio Source Separation using Independent Component Analysis}},
booktitle = {AES Convention 112},
pages = {5529:1-5},
url = {https://aes.org/publications/elibrary-page/?id=11326},
year = {2002},
month = apr,
publisher = {Audio Engineering Society},
address = {Munich Germany}
}
TY - CPAPER
TI - Intelligent Audio Source Separation using Independent Component Analysis
AU - Mitianoudis, Nikolaos
AU - Davies, Mike
T2 - AES Convention 112
SP - 1
EP - 5
M1 - Paper 5529
PY - 2002
DA - 2002/04/06
UR - https://aes.org/publications/elibrary-page/?id=11326
PB - Audio Engineering Society
CY - Munich Germany
LA - en
AB - 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.
ER -