RT Journal Article
T1 Histogram Equalization-Based Features for Speech, Music and Song Discrimination
A1 Gallardo Antolín, Ascensión
A1 Montero, Juan Manuel
AB In this letter, we present a new class of segment-based features for speech, music and song discrimination. These features, called PHEQ (Polynomial-Fit Histogram Equalization), are derived from the nonlinear relationship between the short-term feature distributions computed at segment level and a reference distribution. Results show that PHEQ characteristics outperform short-term features such as Mel Frequency Cepstrum Coefficients (MFCC) and conventional segment-based ones such as MFCC mean and variance. Furthermore, the combination of short-term and PHEQ features significantly improves the performance of the whole system.
PB IEEE
SN 1070-9908
YR 2010
FD 2010-07
LK https://hdl.handle.net/10016/32892
UL https://hdl.handle.net/10016/32892
LA eng
NO This work was supported in part by the regional project Comunidad de Madrid-UC3M CCG08-UC3M/TIC-4457 and the Spanish Government Projects TEC2008-06382 and DPI2007-66846-C02-02.
DS e-Archivo
RD 1 sept. 2024