Robust Audio Identification for Commercial Applications

1
Robust Audio Identification for Commercial
Applications

• Matthias Gruhne
• ghe_at_emt.iis.fhg.de
• Fraunhofer IIS, AEMT, D-98693 Ilmenau, Germany

2
Overview

• What is AudioID?
• Requirements
• System Architecture
• MPEG 7
• Recognition Performance
• Applications
• Conclusions
• Demonstration

3
What is AudioID?
4
What is AudioID?

• Identify audio material (artist, song, etc.) by
  analysis of the signal itself
• Content-Based Identification
• No associated information required (headers, ID3
  tags)
• No embedded signals (e.g. watermark), are
  required
• Some knowledge available about music to be
  identified (reference database)

Purpose
Conditions
5
Requirements

• High recognition rates (gt 95), even with
  distorted signals
• Robust against various distortions
• volume change, equalization, noise addition,
  audio coding (e.g. MP3), ...
• analog artifacts (e.g. D/A, A/D)
• Small signature size
• Extensibility of database (gt 106 items) while
  keeping processing time low(few ms/item)

Recognition rate
Robustness
Compactness
Scalability
6
System Architecture - Overview
7
System Architecture

• Signal preprocessing
• Extract the essence of audio signal
• Increase discriminance efficiency
• Temporal grouping of features (super vector)
• Statistics calculation (mean, variance, etc.)

FeatureExtractor
FeatureProcessor
8
System Architecture

• Clustering of processed feature vectors
• further reduce the amount of data
• enhance robustness (overfitting)
• Add class with associated metadata to database
• Compare feature vectors against classes in
  database by means of some metric
• Find class yielding the best approximation
• Retrieve associated metadata

Class generator
Classification
9
MPEG-7 - Elements for Robust Audio Matching

• AudioSpectrumFlatness LLD
• Derived fromSpectral Flatness Measure (SFM)
• Describes un/flatness of spectrum in frequency
  bands (tonal ? noise)
• AudioSignature Description Scheme
• Statistical data summarization of
  AudioSpectrumFlatness LLD
• Textual description in XML syntax

Low leveldata
Fingerprint
10
MPEG-7 - Benefits

• Standardized Feature Format? guarantees
  worldwide interoperability
• Published, open format? descriptive data can be
  produced easily
• Large MPEG-7 compliant databases expected to be
  available in near future (incl. fingerprints)
• Long term format stability/ life time

11
Recognition Performance- Conditions
Conditions

• Training and test sets (mostly rock / pop)
• 15,000 items
• 90,000 items
• Spectral Flatness Measure (SFM)
• Number of correctly identified items (both
  single best and within top 10)

Considered feature
Classificationperformance
12
Recognition Performance - 15k items
Feature SFM
Cropping 100.0 / 100.0
MP3 _at_ 96kbps 99.6 / 99.8
Loudsp./Mic. 98.0 / 99.0

• 16 bands
• Advanced matching with temporal tracking

13
Recognition Performance - 90k items
!
!

• 16 bands
• Advanced matching with temporal tracking

14
Applications

• Retrieve associated metadata by identifying audio
  content
• Automated search of audio content on the Internet
• Broadcast monitoring by protocoling the
  transmission of audio material
• Feature based indexing of audio databases
  (similarity search)
• ...

15
Conclusions

• High recognition rates (gt99 tested with 90,000
  items)
• Robust to real world signal distortions
• Fast and reliable extraction and classification
• Underlying feature specified in MPEG-7
  standard? ensures worldwide interoperability and
  licensing available for everyone

16
Real Time Demonstration

• Demo running on laptop(Pentium III _at_ 500 MHz)
• Local database with 15,000 items(Rock / Pop
  genre)
• Acoustic transmission mp3 -gt D/A -gt Speakers -gt
  Noisy Environment -gt Microphone -gt A/D -gt
  AudioID

17
Thanks for your Attention !