Pairwise Boosted Audio Fingerprint

@article{Jang2009PairwiseBA,
  title={Pairwise Boosted Audio Fingerprint},
  author={Dalwon Jang and Chang Dong Yoo and Sunil Lee and Sungwoong Kim and Ton Kalker},
  journal={IEEE Transactions on Information Forensics and Security},
  year={2009},
  volume={4},
  pages={995-1004}
}
  • Dalwon Jang, C. Yoo, T. Kalker
  • Published 1 December 2009
  • Computer Science
  • IEEE Transactions on Information Forensics and Security
A novel binary audio fingerprint obtained by filtering and then quantizing the spectral centroids is proposed. [] Key Method The PB algorithm selects the filters and quantizers which lead to accurate classification of matching and nonmatching audio pairs: a matching pair is an audio pair that should be classified as being identical, and a nonmatching pair is a pair that should be classified as being different.
Audio Fingerprint Binarization by Minimizing Hinge-Loss Function
TLDR
Experiments over thousands of songs demonstrate that the identification performance of binary fingerprinting can be improved by minimizing the proposed hinge loss function.
A Power Mask based audio fingerprint
  • Bob Coover, Jinyu Han
  • Computer Science
    2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2014
TLDR
This paper shows the Philips fingerprint is noise resistant, and is capable of recognizing music that is corrupted by noise at a -4 to -7 dB signal to noise ratio.
Audio Fingerprint Based on Combining Binary Fingerprints
This paper proposes the method to extract a binary audio fingerprint by combining several base binary fingerprints. Based on majority voting of base fingerprints, which are designed by mimicking the
Robust Image Hash Function Based on Polar Harmonic Transforms and Feature Selection
  • Y. N. Li
  • Computer Science
    2012 Eighth International Conference on Computational Intelligence and Security
  • 2012
TLDR
Experimental results reveal that the proposed work is both distortion-resistent and discriminative, and it can achieve higher content identification accuracy than the comparative algorithm.
An efficient audio fingerprint design for MP3 music
TLDR
An indexing scheme which is composed of the PCA technique and the QUC-tree structure is applied to efficiently search for an unknown MP3 fingerprint in the high dimensional feature space.
Regularized Adaboost Learning for Identification of Time-Varying Content
  • Honghai Yu, P. Moulin
  • Computer Science
    IEEE Transactions on Information Forensics and Security
  • 2014
TLDR
A regularized Adaboost algorithm to learn and extract binary fingerprints of time-varying content by filtering and quantizing perceptually significant features and demonstrates significant performance gains over SPB for both audio and video content identification systems.
Aligning meeting recordings via adaptive fingerprinting
TLDR
An adaptive audio fingerprint which is learned on-the-fly in a completely unsupervised manner to adapt to the characteristics of a given set of unaligned recordings, formulated as a series of optimization problems which can be solved very efficiently using eigenvector routines.
Regularized Adaboost for content identification
  • Honghai Yu, P. Moulin
  • Computer Science
    2013 IEEE International Conference on Acoustics, Speech and Signal Processing
  • 2013
TLDR
A regularized Adaboost learning algorithm to extract binary fingerprints by filtering and quantizing perceptually significant features by taking feature sequence correlation into account is proposed.
Fingerprint information maximization for content identification
  • R. Naini, P. Moulin
  • Computer Science
    2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2014
This paper presents a novel design of content fingerprints based on maximization of the mutual information across the distortion channel. We use the information bottleneck method to optimize the
Robust and Efficient Multiple Alignment of Unsynchronized Meeting Recordings
  • T. Tsai, A. Stolcke
  • Computer Science
    IEEE/ACM Transactions on Audio, Speech, and Language Processing
  • 2016
TLDR
This paper proposes a way to generate a single high-quality audio recording of a meeting using no equipment other than participants' personal devices using an adaptive audio fingerprint based on spectrotemporal eigenfilters, where the fingerprint design is learned on-the-fly in a totally unsupervised way to perform well on the data at hand.
...
...

References

SHOWING 1-10 OF 16 REFERENCES
Boosted Binary Audio Fingerprint Based on Spectral Subband Moments
  • Sungwoong Kim, C. Yoo
  • Computer Science
    2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07
  • 2007
TLDR
The experimental results showed that the proposed binary audio fingerprint obtained by boosting the spectral subband moments outperformed some of the state-of-the-art binary audio fingerprints in the context of both robustness and pair-wise independence (reliability).
Audio fingerprinting based on normalized spectral subband moments
TLDR
This letter presents a new audio-fingerprinting method based on the normalized spectral subband moments, which shows the best performance for fingerprinting among the considered subband features.
Content-based Identification of Audio Material Using MPEG-7 Low Level Description
TLDR
A system for reliable, fast and robust identification of audio material which can be run on the resources provided by today's standard computing platforms, based on a general pattern recognition paradigm and exploits low level signal features standardized within the MPEG-7 framework, thus enabling interoperability on a world-wide scale.
Known-Audio Detection using Waveprint: Spectrogram Fingerprinting by Wavelet Hashing
  • Michele Covell, S. Baluja
  • Computer Science
    2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07
  • 2007
TLDR
The resulting system has excellent detection capabilities for small snippets of audio that have been degraded in a variety of manners, including competing noise, poor recording quality, and cell-phone playback.
A Highly Robust Audio Fingerprinting System With an Efficient Search Strategy
TLDR
An audio fingerprinting system that uses the fingerprint of an unknown audio clip as a query on a fingerprint database, which contains the fingerprints of a large library of songs, the audio clip can be identified.
A Highly Robust Audio Fingerprinting System
TLDR
An audio fingerprinting system that uses the fingerprint of an unknown audio clip as a query on a fingerprint database, which contains the fingerprints of a large library of songs, the audio clip can be identified.
Issues with digital watermarking and perceptual hashing
TLDR
It is argued that not only in the context of content recognition, but also for other applications, a benefit is to be expected from the combination of robust feature recognition and digital watermarking.
Rapid object detection using a boosted cascade of simple features
  • Paul A. Viola, Michael J. Jones
  • Computer Science
    Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001
  • 2001
TLDR
A machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates and the introduction of a new image representation called the "integral image" which allows the features used by the detector to be computed very quickly.
Improved Boosting Algorithms Using Confidence-rated Predictions
We describe several improvements to Freund and Schapire's AdaBoost boosting algorithm, particularly in a setting in which hypotheses may assign confidences to each of their predictions. We give a
A Survey of Combinatorial Gray Codes
TLDR
The area of combinatorial Gray codes is surveyed, recent results, variations, and trends are described, and some open problems are highlighted.
...
...