Chroma binary similarity and local alignment applied to cover song identification
We present a new technique for audio signal comparison based on tonal subsequence alignment and its application to detect cover versions (i.e., different performances of the same underlying musical piece). Cover song identification is a task whose popularity has increased in the Music Information Re...
| Autores: | , , , |
|---|---|
| Formato: | artículo |
| Estado: | Versión aceptada para publicación |
| Fecha de publicación: | 2008 |
| País: | España |
| Recursos: | Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya) |
| Repositorio: | Recercat. Dipósit de la Recerca de Catalunya |
| OAI Identifier: | oai:recercat.cat:10230/16277 |
| Acesso em linha: | http://hdl.handle.net/10230/16277 http://dx.doi.org/10.1109/TASL.2008.924595 |
| Access Level: | acceso abierto |
| Palavra-chave: | Tonalitat (Música) Música So -- Enregistrament i reproducció -- Tècniques digitals Acoustic signal analysis Dynamic programming Information retrieval Multidimensional sequences Music |
| Resumo: | We present a new technique for audio signal comparison based on tonal subsequence alignment and its application to detect cover versions (i.e., different performances of the same underlying musical piece). Cover song identification is a task whose popularity has increased in the Music Information Retrieval (MIR) community along in the past, as it provides a direct and objective way to evaluate music similarity algorithms./nThis article first presents a series of experiments carried out/nwith two state-of-the-art methods for cover song identification./nWe have studied several components of these (such as chroma resolution and similarity, transposition, beat tracking or Dynamic Time Warping constraints), in order to discover which characteristics would be desirable for a competitive cover song identifier. After analyzing many cross-validated results, the importance of these characteristics is discussed, and the best-performing ones are finally applied to the newly proposed method. Multiple/nevaluations of this one confirm a large increase in identification/naccuracy when comparing it with alternative state-of-the-art/napproaches. |
|---|