Mridangam stroke dataset

CompMusic

Inici
→
Dades primàries de recerca
→
Departament de Tecnologies de la Informació i les Comunicacions. Dades primàries
→
Visualitza element

dc.contributor.author	CompMusic
dc.date.accessioned	2017-01-19T08:54:15Z
dc.date.available	2017-01-19T08:54:15Z
dc.date.issued	2014-03
dc.identifier.citation	CompMusic.Mridangam stroke dataset [dataset]. Repositori Digital de la UPF: Barcelona; 2014 [citat 19 gener 2017]. Disponible a: http://hdl.handle.net/10230/27936
dc.identifier.uri	http://hdl.handle.net/10230/27936
dc.description	The audio examples were recorded from a professional Carnatic percussionist in a semi-anechoic studio conditions by Akshay Anantapadmanabhan using SM-58 microphones and an H4n ZOOM recorder. The audio was sampled at 44.1 kHz and stored as 16 bit wav files. The dataset can be used for training models for each Mridangam stroke. /n/nA detailed description of the Mridangam and its strokes can be found in the paper below. A part of the dataset was used in the following paper. /nAkshay Anantapadmanabhan, Ashwin Bellur, Hema A. Murthy, "Modal analysis and transcription of strokes of the mridangam using non-negative matrix factorization," in Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013), pp.181-185, May 2013./n/nThe whole dataset is organized by the tonic, into 6 packs in Freesound. The packs can be downloaded from the links below. /n/nB: http://www.freesound.org/people/akshaylaya/packs/14157//n/nC: http://www.freesound.org/people/akshaylaya/packs/14159//n/nC#: http://www.freesound.org/people/akshaylaya/packs/14160//n/nD: http://www.freesound.org/people/akshaylaya/packs/14161//n/nD#: http://www.freesound.org/people/akshaylaya/packs/14163//n/nE: http://www.freesound.org/people/akshaylaya/packs/14164//n/nEach audio file is named as, /n/n<StrokeName>_<Tonic>_<InstanceNumber>.wav/n<Tonic> = {B, C, Csh, D, Dsh, E}/n<StrokeName> = {Bheem, Cha, Dheem, Dhin, Num, Ta, Tha, Tham, Thi, Thom}
dc.description.abstract	The Mridangam Stroke dataset is a collection of 7162 audio examples of individual strokes of the Mridangam in various tonics. The dataset comprises of 10 different strokes played on Mridangams with 6 different tonic values. The dataset can be used for training models for each Mridangam stroke.
dc.language.iso	eng
dc.relation	Publicació relacionada: Anantapadmanabhan A, Bellur A, Murthy HA. Modal analysis and transcription of strokes of the mridangam using non-negative matrix factorization. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing: proceedings; 2013 May 26-31; Vancouver, USA. Piscataway, NJ: IEEE, 2013. p. 181-185. DOI 10.1109/ICASSP.2013.6637633/nhttp://hdl.handle.net/10230/25756
dc.relation.ispartof	Indian art music
dc.relation.isreferencedby	http://hdl.handle.net/10230/25756
dc.relation.uri	http://compmusic.upf.edu/mridangam-stroke-dataset
dc.rights	Aquest document està subjecte a una llicència Creative Commons
dc.rights.uri	http://creativecommons.org/licenses/by/3.0/
dc.title	Mridangam stroke dataset
dc.type	info:eu-repo/semantics/other
dc.type	Dataset
dc.relation.projectID	info:eu-repo/grantAgreement/EC/FP7/267583
dc.rights.accessRights	info:eu-repo/semantics/openAccess