@inproceedings{df302c5b09d64a9ab940dc5ea4ddd5ae,
title = "A multimodal approach for percussion music transcription from audio and video",
abstract = "A multimodal approach for percussion music transcription from audio and video recordings is proposed in this work. It is part of an ongoing research effort for the development of tools for computeraided analysis of Candombe drumming, a popular afro-rooted rhythm from Uruguay. Several signal processing techniques are applied to automatically extract meaningful information from each source. This involves detecting certain relevant objects in the scene from the video stream. The location of events is obtained from the audio signal and this information is used to drive the processing of both modalities. Then, the detected events are classified by combining the information from each source in a feature-level fusion scheme. The experiments conducted yield promising results that show the advantages of the proposed method.",
keywords = "Machine learning applications, Multimodal signal processing, Music transcription, Percussion music, Sound classification",
author = "Bernardo Marenco and Magdalena Fuentes and Florencia Lanzaro and Mart{\'i}n Rocamora and Alvaro G{\'o}mez",
note = "Funding Information: This work was supported by funding agencies CSIC and ANII from Uruguay. Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2015.; 20th Iberoamerican Congress on on Pattern Recognition, CIARP 2015 ; Conference date: 09-11-2015 Through 12-11-2015",
year = "2015",
doi = "10.1007/978-3-319-25751-8_12",
language = "English (US)",
isbn = "9783319257501",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "92--99",
editor = "Alvaro Pardo and Josef Kittler",
booktitle = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
}