RT Journal Article
T1 Design of an efficient music-speech discriminator
A1 Tardón-García, Lorenzo José
A1 Sammartino, Simone
A1 Barbancho-Pérez, Isabel
K1 Archivos audiovisuales
AB In this paper, the problem of the design of a simple and efficient music-speech discriminator forlarge audio data sets in which advanced music playing techniques are taught and voice and musicare intrinsically interleaved is addressed. In the process, a number of features used in speech-musicdiscrimination are defined and evaluated over the available data set. Specifically, the data setcontains pieces of classical music played with different and unspecified instruments  or even lyricsand the voice of a teacher  a top music performer or even the overlapped voice of the translator andother persons. After an initial test of the performance of the features implemented, a selectionprocess is started, which takes into account the type of classifier selected beforehand, to achievegood discrimination performance and computational efficiency, as shown in the experiments. Thediscrimination application has been defined and tested on a large data set supplied by FundaciónAlbéniz, containing a large variety of classical music pieces played with different instrument, whichinclude comments and speeches of famous performers.
PB Acoustical Society of America
YR 2010
FD 2010-01
LK https://hdl.handle.net/10630/33434
UL https://hdl.handle.net/10630/33434
LA eng
NO Tardón, L. J., Sammartino, S., & Barbancho, I. (2010). Design of an efficient music-speech discriminator. In The Journal of the Acoustical Society of America (Vol. 127, Issue 1, pp. 271–279). Acoustical Society of America (ASA). https://doi.org/10.1121/1.3257204
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 20 ene 2026