07-06-2012, 04:18 PM
SEMINAR ON AUDIO FINGERPRINTING SYSTEM
FINGERPRINTING SYSTEM[.doc (Size: 384.5 KB / Downloads: 2)
INTRODUCTION
Fingerprint systems are over one hundred years old. In 1893 Sir Francis Galton was the first to “prove” that no two fingerprints of human beings were alike. Approximately 10 years later Scotland Yard accepted a system designed by Sir Edward Henry for identifying fingerprints of people. This fingerprinting system however existed longer than a century. It is important to note that a human fingerprint differs from a textual summary in that it does not allow the reconstruction of other aspects of the original. For example, a human fingerprint does not convey any information about the color of the person’s hair or eyes.
Audio fingerprinting is best known for its ability to page link unlabeled audio to corresponding metadata (e.g. Artist and song name), regardless of the audio format. There are more applications to audio fingerprinting, such us: Content-based integrity verification or watermarking support. Audio fingerprinting or Content-based audio identification (CBID) systems extract a perceptual digest of a piece of audio content, i.e. the fingerprint and store it in a database. When presented with unlabeled audio, its fingerprint is calculated and matched against those stored in the database. Using fingerprints and matching algorithms, distorted versions of a recording can be identified as the same audio content.
AUDIO FINGERPRINTING CONCEPTS
Audio Fingerprint Definition
Recall that an audio fingerprint can be seen as a short summary of an audio object. Therefore a fingerprint function F should map an audio object X, consisting of a large number of bits, to a fingerprint of only a limited number of bits.
Here we can draw an analogy with so-called hash functions1, which are well known in cryptography. A cryptographic hash function H maps an (usually large) object X to a (usually small) hash value (a.k.a. message digest). A cryptographic hash function allows comparison of two large objects X and Y, by just comparing their respective hash values H(X) and H(Y). Strict mathematical equality of the latter pair implies equality of the former, with only a very low probability of error. For a properly designed cryptographic function this probability is 2 where n equals the number of bits of the hash value. Using cryptographic hash functions, an efficient method exists to check whether or not a particular data item X is contained in a given and large data set Y={Yi}. Instead of storing and comparing with all of the data in Y,
it is sufficient to store the set of hash values {hi = H(Yi)}, and to compare H(X) with this set of hash values.
GENERAL FRAMEWORK
There are two fundamental processes: the fingerprint extraction and the matching algorithm. The fingerprint extraction derives a set of relevant perceptual characteristics of a recording in a concise and robust form.