Construction and evaluation of a robust multifeature speech/music discriminator

Author

Scheirer, Eric ; Slaney, Malcoh

Author_Institution

Interval Res. Corp., Palo Alto, CA, USA

Volume

2

fYear

1997

fDate

21-24 Apr 1997

Firstpage

1331

Abstract

We report on the construction of a real-time computer system capable of distinguishing speech signals from music signals over a wide range of digital audio input. We have examined 13 features intended to measure conceptually distinct properties of speech and/or music signals, and combined them in several multidimensional classification frameworks. We provide extensive data on system performance and the cross-validated training/test setup used to evaluate the system. For the datasets currently in use, the best classifier classifies with 5.8% error on a frame-by-frame basis, and 1.4% error when integrating long (2.4 second) segments of sound

Keywords

audio signals; digital communication; feature extraction; music; real-time systems; speech processing; cross validated training/test setup; digital audio input; features; multidimensional classification; music signals; real-time computer system; robust multifeature speech/music discriminator; sound segments; speech signals; system performance; Automatic speech recognition; Band pass filters; Energy measurement; Milling machines; Multimedia systems; Multiple signal classification; Real time systems; Robustness; Speech analysis; System performance;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1997. ICASSP-97., 1997 IEEE International Conference on

Conference_Location

Munich

ISSN

1520-6149

Print_ISBN

0-8186-7919-0

Type

conf

DOI

10.1109/ICASSP.1997.596192

Filename

596192