A timing-based classification method for human voice in opera recordings

Maria Cristina Marinescu, Rafael Ramirez

Producció científica: Capítol de llibreContribució a congrés/conferènciaAvaluat per experts

1 Citació (Scopus)

Resum

The goal of this work is to identify famous tenors from commercial recordings. Our approach is based on training expressive singer-specific models and using them to classify new musical fragments interpreted by singers that perform arias from the training set. In this paper we focus on expressive timing variations and build the models by applying machine learning techniques to a body of data consisting of high-level descriptors extracted from audio recordings. The experimental results show evidence that performers can be automatically identified at a rate significantly better than random choice.

Idioma originalAnglès
Títol de la publicació8th International Conference on Machine Learning and Applications, ICMLA 2009
Pàgines577-582
Nombre de pàgines6
DOIs
Estat de la publicacióPublicada - 2009
Publicat externament
Esdeveniment8th International Conference on Machine Learning and Applications, ICMLA 2009 - Miami Beach, FL, United States
Durada: 13 de des. 200915 de des. 2009

Sèrie de publicacions

Nom8th International Conference on Machine Learning and Applications, ICMLA 2009

Conferència

Conferència8th International Conference on Machine Learning and Applications, ICMLA 2009
País/TerritoriUnited States
CiutatMiami Beach, FL
Període13/12/0915/12/09

Fingerprint

Navegar pels temes de recerca de 'A timing-based classification method for human voice in opera recordings'. Junts formen un fingerprint únic.

Com citar-ho