EXEMPLAR-BASED ASSIGNMENT OF LARGE MISSING AUDIO PARTS USING STRING MATCHING ON TONAL FEATURES

We propose a new approach for assigning audio data in large missing audio parts (from 1 to 16 seconds). Inspired by im-age inpainting approaches, the proposed method uses the repetitive aspect of music pieces on musical features to re-cover missing segments via an exemplar-based reconstruc-tion. Tonal features combined with a string matching tech-nique allows locating repeated segments accurately. The evaluation consists in performing on both musician and non-musician subjects listening tests of randomly reconstructed audio excerpts, and experiments highlight good results in assigning musically relevant parts. The contribution of this paper is twofold: bringing musical features to solve a sig-nal processing problem in the case of large missing audio parts, and successfully applying exemplar-based techniques on musical signals while keeping a musical consistency on audio pieces. 1