TY - GEN
T1 - Belief propagation algorithm for automatic chord estimation
AU - Martin, Vincent P.
AU - Reynal, Sylvain
AU - Basaran, Dogac
AU - Crayencour, Hélène Camille
N1 - Publisher Copyright:
Copyright: © 2019 Vincent P. Martin et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 Unported License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
PY - 2019/5/20
Y1 - 2019/5/20
N2 - This work aims at bridging the gap between two completely distinct research fields: digital communications and Music Information Retrieval. While works in the MIR community have long used algorithms borrowed from speech signal processing, text recognition or image processing, to our knowledge very scarce work based on digital communications algorithms has been produced. This paper specifically targets the use of the Belief Propagation algorithm for the task of Automatic Chord Estimation. This algorithm is of widespread use in iterative decoders for error correcting codes and we show that it offers improved performances in ACE by genuinely incorporating the ability to take constraints between distant parts of the song into account. It certainly represents a promising alternative to traditional MIR graphical models approaches, in particular Hidden Markov Models.
AB - This work aims at bridging the gap between two completely distinct research fields: digital communications and Music Information Retrieval. While works in the MIR community have long used algorithms borrowed from speech signal processing, text recognition or image processing, to our knowledge very scarce work based on digital communications algorithms has been produced. This paper specifically targets the use of the Belief Propagation algorithm for the task of Automatic Chord Estimation. This algorithm is of widespread use in iterative decoders for error correcting codes and we show that it offers improved performances in ACE by genuinely incorporating the ability to take constraints between distant parts of the song into account. It certainly represents a promising alternative to traditional MIR graphical models approaches, in particular Hidden Markov Models.
UR - http://www.scopus.com/inward/record.url?scp=85084398142&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85084398142
T3 - Proceedings of the Sound and Music Computing Conferences
SP - 537
EP - 544
BT - Proceedings of the 16th Sound and Music Computing Conference, SMC 2019
A2 - Barbancho, Isabel
A2 - Tardon, Lorenzo J.
A2 - Peinado, Alberto
A2 - Barbancho, Ana M.
PB - CERN
T2 - 16th Sound and Music Computing Conference, SMC 2019
Y2 - 28 May 2019 through 31 May 2019
ER -