Audio Fingerprint Identification by Approximate String Matching

Jerome Lebossé (1) , Luc Brun (2)

1 FT R&D - France Télécom Recherche & Développement
2 Equipe Image - Laboratoire GREYC - UMR6072

An audio fingerprint is a small digest of an audio file which allows to identify it among a database of candidates. This paper first presents a fingerprint extraction algorithm. The identification task is performed by a new identification scheme which combines string matching algorithms and q-grams filtration.

Domaines: Traitement des images [eess.IV]

Jerome Lebossé, Luc Brun. Audio Fingerprint Identification by Approximate String Matching. Proceedings of ISMIR 2007, Sep 2007, Vienna, Austria. pp.143-144. ⟨hal-00824741⟩