Supplementary material for the publication N. Kroher, A. Pikrakis and J.-M. Díaz-Báñez (2017): “Image-based singer identificaiton in flamenco videos” In Proceedings of the 7th International Workshop of Folk Music Analysis, Málaga, Spain.
Description & download
CANTE is a software for the automatic transcription of flamenco singing from a cappella and accompanied music recordings. Given the absence of scores in flamenco, automatic transcriptions are essential to a number of related Music Information Retrieval (MIR) tasks. CANTE extracts a note-level transcription of the singing voice melody, where each sung note is characterised by its onset time, duration and pitch value.
corpusCOFLA is a research corpus containing meta-data for more than 1800 songs as well as several annotated test sets for specific music information retrieval tasks.
TONAS: A dataset of flamenco a cappella sung melodies with corresponding manual transcriptions. This dataset contains a music collection of 72 sung excerpts representative of three a cappella singing styles (Deblas, two variants of Martinete). The collection was built in the context of a study on similarity and style classification of flamenco a cappella singing styles (Tonas) by the flamenco expert Dr. Joaquin Mora, Universidad de Sevilla.
FlaBase (Flamenco Knowledge Base) is the acronym of a new knowledge base of flamenco music. Its ultimate aim is to gather all available online editorial, biographical and musicological information related to flamenco music. A first version is just being released. Its content is the result of the curation and extraction processes. FlaBase is stored in JSON format, and it is freely available for download. This first release of FlaBase contains information about 1,102 artists, 74 palos (flamenco genres), 2,860 albums, 13,311 tracks, and 771 Andalusian locations.