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

Maria Cristina Marinescu, Rafael Ramirez

Producción científica: Capítulo del libroContribución a congreso/conferenciarevisión exhaustiva

1 Cita (Scopus)

Resumen

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 originalInglés
Título de la publicación alojada8th International Conference on Machine Learning and Applications, ICMLA 2009
Páginas577-582
Número de páginas6
DOI
EstadoPublicada - 2009
Publicado de forma externa
Evento8th International Conference on Machine Learning and Applications, ICMLA 2009 - Miami Beach, FL, Estados Unidos
Duración: 13 dic 200915 dic 2009

Serie de la publicación

Nombre8th International Conference on Machine Learning and Applications, ICMLA 2009

Conferencia

Conferencia8th International Conference on Machine Learning and Applications, ICMLA 2009
País/TerritorioEstados Unidos
CiudadMiami Beach, FL
Período13/12/0915/12/09

Huella

Profundice en los temas de investigación de 'A timing-based classification method for human voice in opera recordings'. En conjunto forman una huella única.

Citar esto