Sub-fingerprint masking for a robust audio fingerprinting system in a real-noise environment for portable consumer devices

The robustness of audio fingerprinting system in a noisy environment is a principal challenge in the area of content-based audio retrieval, especially for use in portable consumer devices. Our new audio fingerprint method using sub-fingerprint masking based on the predominant pitch extraction increa...

Full description

Saved in:
Bibliographic Details
Published in2010 Digest of Technical Papers International Conference on Consumer Electronics (ICCE) pp. 409 - 410
Main Authors Wooram Son, Hyun-Tae Cho, Kyoungro Yoon
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.01.2010
Subjects
Acoustic noise
Audio databases
Computer science
Content based retrieval
Filtering
Fingerprint recognition
Frequency conversion
Frequency domain analysis
Noise robustness
Working environment noise
Online AccessGet full text

Cover

More Information
Summary:The robustness of audio fingerprinting system in a noisy environment is a principal challenge in the area of content-based audio retrieval, especially for use in portable consumer devices. Our new audio fingerprint method using sub-fingerprint masking based on the predominant pitch extraction increases the accuracy of the audio fingerprinting system in a noisy environment dramatically, while requiring much less computing power compared to the expanded hash table lookup method, where the searching complexity increases by the factor of 33 times the degree of expansion.
ISBN:9781424443147
1424443148
ISSN:2158-3994
2158-4001
DOI:10.1109/ICCE.2010.5418912