@inproceedings{80cf09cb78f3420798855ff16eccb6da,
title = "Automatic transcription of drum sequences using audiovisual features",
abstract = "The transcription of a music performance from the audio signal is often problematic, either because it requires the separation of complex sources, or simply because some important high-level music information cannot be directly extracted from the audio signal. In this paper, we propose a novel multimodal approach for the transcription of drum sequences using audiovisual features. The transcription is performed by Support Vector Machines (SVM) classifiers, and three different information fusion strategies are evaluated. A correct recognition rate of 85.8\% can be achieved for a detailed taxonomy and a fully automated transcription.",
author = "Olivier Gillet and Ga{\"e}l Richard",
year = "2005",
month = jan,
day = "1",
doi = "10.1109/ICASSP.2005.1415682",
language = "English",
isbn = "0780388747",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "III205--III208",
booktitle = "2005 IEEE International Conference on Acoustics, Speech, and Signal Processing,ICASSP '05 - Proceedings - Audio and ElectroacousticsSignal Processing for Communication",
note = "2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05 ; Conference date: 18-03-2005 Through 23-03-2005",
}