Zur Hauptnavigation wechseln Zur Suche wechseln Zum Hauptinhalt wechseln

On the Reduction of False Positives in Singing Voice Detection

  • B. Lehner (Vortragende*r)

Aktivität: Vortrag oder PräsentationPosterpräsentationunbekannt

Beschreibung

Motivated by the observation that one of the biggest problems in automatic singing voice detection is the confusion of vocals with other pitch-continuous and pitch-varying instruments, we propose a set of three new audio features designed to reduce the amount of false vocal detections. This is borne out in comparative experiments with three different musical corpora. The resulting singing voice detector appears to be at least on par with more complex state-of-the-art methods. New features and classifier are very light-weight and in principle suitable for on-line use.
Zeitraum06 Mai 2014
Ereignistitel9th International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
VeranstaltungstypKonferenz
OrtItalienAuf Karte anzeigen

Wissenschaftszweige

  • 202002 Audiovisuelle Medien
  • 102 Informatik
  • 102001 Artificial Intelligence
  • 102015 Informationssysteme
  • 102003 Bildverarbeitung

JKU-Schwerpunkte

  • Computation in Informatics and Mathematics
  • TNF Allgemein