TY - GEN
T1 - A system for automatically annotating traditional Irish music field recordings
AU - Duggan, Bryan
AU - O'Shea, Brendan
AU - Cunningham, Pádraig
PY - 2008
Y1 - 2008
N2 - This paper presents MATT2 (Machine Annotation of Traditional Tunes). MATT2 is a novel system which can automatically annotate field recordings of traditional Irish music with useful metadata such as tune name, key signature, time signature, composer and discography. MATT2 works by using a number of algorithms to automatically transcribe digital audio to be annotated to the ABC music notation language. It then compares these transcriptions against a corpus of 860 human made transcriptions in ABC using a variation of the edit distance algorithm. Results using MATT2 to annotate fifty recordings of flute and fiddle tunes demonstrate a high success rate at annotating recordings made by different musicians. Additionally, several of the recordings successfully annotated in testing MATT2 were recorded in imperfect conditions, with badly degraded audio.
AB - This paper presents MATT2 (Machine Annotation of Traditional Tunes). MATT2 is a novel system which can automatically annotate field recordings of traditional Irish music with useful metadata such as tune name, key signature, time signature, composer and discography. MATT2 works by using a number of algorithms to automatically transcribe digital audio to be annotated to the ABC music notation language. It then compares these transcriptions against a corpus of 860 human made transcriptions in ABC using a variation of the edit distance algorithm. Results using MATT2 to annotate fifty recordings of flute and fiddle tunes demonstrate a high success rate at annotating recordings made by different musicians. Additionally, several of the recordings successfully annotated in testing MATT2 were recorded in imperfect conditions, with badly degraded audio.
UR - https://www.scopus.com/pages/publications/51849151965
U2 - 10.1109/CBMI.2008.4564923
DO - 10.1109/CBMI.2008.4564923
M3 - Conference contribution
AN - SCOPUS:51849151965
SN - 9781424420445
T3 - 2008 International Workshop on Content-Based Multimedia Indexing, CBMI 2008, Conference Proceedings
SP - 25
EP - 32
BT - 2008 International Workshop on Content-Based Multimedia Indexing, CBMI 2008, Conference Proceedings
T2 - 2008 International Workshop on Content-Based Multimedia Indexing, CBMI 2008
Y2 - 18 June 2008 through 20 June 2008
ER -