Scribd
Upload
214 views

Seminar On Audio Fingerprinting: Presented By: Abdul Jaleel.N Roll No: 01 Gecw

The document discusses audio fingerprinting, which extracts unique features from digital audio recordings to identify them. These fingerprints can be stored in a database and used to identify unknown recordings by comparing their fingerprints. Audio fingerprinting has advantages over hash functions for identification, as fingerprints can match between different formats and minor changes to recordings. It finds applications in areas like content monitoring and music identification. The document outlines the fingerprint extraction and matching process used by some commercial systems.

Uploaded by

arjunrajmp
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
214 views

Seminar On Audio Fingerprinting: Presented By: Abdul Jaleel.N Roll No: 01 Gecw

The document discusses audio fingerprinting, which extracts unique features from digital audio recordings to identify them. These fingerprints can be stored in a database and used to identify unknown recordings by comparing their fingerprints. Audio fingerprinting has advantages over hash functions for identification, as fingerprints can match between different formats and minor changes to recordings. It finds applications in areas like content monitoring and music identification. The document outlines the fingerprint extraction and matching process used by some commercial systems.

Uploaded by

arjunrajmp
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 19

Seminar

on
Audio Fingerprinting

Presented by:
Abdul Jaleel.N
Roll no: 01
GECW
What is Audio Fingerprinting?
• Fingerprints uniquely identify people.

• Every digital recording has unique features just like a


human fingerprint.

• The audio fingerprint of a digital recording must first be


extracted.

• Once extracted, it can be compared with reference


fingerprints stored in a central database to identify the
music.
• The main objective of audio fingerprinting is to
establish a perceptual equality of two audio clips by
comparing their associated fingerprints.
• Good for finding a song you don’t know by
name but know by tune.

What is Audio
Fingerprinting
Advantages of Fingerprinting

• Reduced storage requirements as fingerprints relatively


small

• Efficient comparison as perceptual irrelevancies have been


removed

• Efficient searching as the fingerprint database is also


relatively small
Hash Functions vs.
Fingerprinting

• In Cryptography hash functions allows comparison of two


large digital files by comparing their hash values

• Very efficient way to determine whether or not a particular


digital file is present in a large database
Hash Functions vs.
Fingerprinting

• Hash functions cannot be used in Audio Fingerprinting:

• Changing the audio format will change the digital waveform


(CD to mp3 conversion)

• Changing a few bits would result in a completely different


hash value.
Hash Functions vs.
Fingerprinting

• Fingerprinting does not establish mathematical equality,


but perceptual equality

• Perceptually similar digital recordings will result in similar


but not an identical fingerprint
Fingerprinting Parameters
• Robustness

• Reliability

• Fingerprint size

• Granularity

• Search speed
Applications

• Broadcast monitoring

• Connected Audio

• Database maintenance

• Digital rights management

• Music library organization


Fingerprint Extraction

• Semantic features
• Don't always have a clear meaning
• More difficult to compute
• Not universal (ex: BPM in classical music)
• Non-semantic features
• Spectral flatness measure (Fraunhofer)
• Loudness, bandwidth (Bonn et al)
• Energy at each band (Haitsma/Kalker)
Fingerprint Extraction
(Haitsma)

• Overlapping are used to extract 32-bit sub-fingerprints


every 11.6 ms
• Large overlap is used to smooth short varying differences
in the waveforms
• FFT is used to find the band energy
• A fingerprint block consists of 256 sub-fingerprints about 3
seconds in length
Fingerprint Extraction
Client
. .
.
Client Internet Server

Client
Lookup
Pruning
Feature Extraction
Audio stream identity

Audio stream

Example Architecture
Database Search (Haitsma)

• Brute force method for matching:


• 10,000 song database = 250 million sub-fingerprints
• Searching through every fingerprint would take 20 minutes!
• More efficient methods:
• Look up table is 800,000 times faster!
• Requires 2^32 extra memory .
• Average of 300 comparisons needed.
Database Search (Haitsma)

Table lookup database


Variance
 Compression
 Distortion
 Noise
Efficiency
 GOALS
 Encoding
 Loopkup Robust
Database size
Search algorithm Compact
Music Fast
High dimensionality

Challenges
Commercial Products

• Phillips (Haitsma)
• Audible Magic
• Relatable (Music Brainz)
• Gracenote
Conclusion

• Many practical applications for both industry and


consumers.

• Very accurate and reliable.

• Currently very difficult to effectively convert Audio


Fingerprints.
•Thank you

You might also like