Description: These routines implement a landmark-based audio fingerprinting system that is very well suited to identifying small, noisy excerpts a large number of items. It is based on the ideas used in the Shazam music matching service, which can identify seemingly any commercial music tracks short snippets recorded via cellphones even in very noisy conditions. I don t know if my algorithm is as good as theirs, but the approach, as described in the paper below, certainly seems to work:
Avery Wang An Industrial-Strength Audio Search Algorithm , Proc. 2003 ISMIR International Symposium on Music Information Retri , Baltimore, MD, Oct. 2003. http://www.ee.columbia.edu/~dpwe/papers/Wang03-shazam.pdf
To Search:
File list (Check if you may need any files):
fingerprint\fingerprint\addprefixsuffix.m
...........\...........\add_tracks.m
...........\...........\clear_hashtable.m
...........\...........\demo_fingerprint.m
...........\...........\demo_fingerprint.png
...........\...........\demo_fingerprint_01.png
...........\...........\eval_fprint.m
...........\...........\find_landmarks.m
...........\...........\finger_thumb.png
...........\...........\gen_random_queries.m
...........\...........\get_hash_hits.m
...........\...........\hash2landmark.m
...........\...........\illustrate_match.m
...........\...........\index.html
...........\...........\landmark2hash.m
...........\...........\match_query.m
...........\...........\myls.m
...........\...........\Q-full-circle.mp3
...........\...........\readaudio.m
...........\...........\record_hashes.m
...........\...........\show_landmarks.m
...........\...........\windows-notes.txt
...........\fingerprint
fingerprint
Download