https://github.com/dschwertfeger/cbar

A Python package for content-based audio retrieval with text queries.
https://github.com/dschwertfeger/cbar

audio content-based gradient-descent machine-learning retrieval riemann

Last synced: about 1 year ago
JSON representation

A Python package for content-based audio retrieval with text queries.

• Host: GitHub
• URL: https://github.com/dschwertfeger/cbar
• Owner: dschwertfeger
• License: mit
• Created: 2017-02-02T16:28:38.000Z (over 9 years ago)
• Default Branch: master
• Last Pushed: 2017-03-27T14:12:20.000Z (about 9 years ago)
• Last Synced: 2025-03-20T21:03:53.111Z (over 1 year ago)
• Topics: audio, content-based, gradient-descent, machine-learning, retrieval, riemann
• Language: Python
• Homepage:
• Size: 857 KB
• Stars: 5
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.rst
  • License: LICENSE.txt

Awesome Lists containing this project

README

          
CBAR: Content-Based Audio Retrieval in Python

=============================================

CBAR is a Python package for content-based audio retrieval with text queries.

It contains two retrieval methods. The Passive-Aggressive Model for Image Retrieval (PAMIR) was initially

developed in the context of an image retrieval application [1]_ but has been

proven to work equally well for audio retrieval applications [2]_.

The second approach combines on a Low-Rank Retraction Algorithm (LORETA) [3]_

and the Weighted Approximate-Rank Pairwise loss (WARP loss) [4]_ to efficiently

infer the model parameters. A similar algorithm, constrained to the context

of finding similar items of the same kind (similarity search), has been shown to

work well on image and audio datasets [5]_.

Getting started

---------------

Jump straight to the :doc:`CAL500 quickstart ` guide

if you are impatient.

Installation

------------

The latest release of CBAR can be installed from PyPI using ``pip``.

.. code:: bash

    pip install cbar

Dependencies

------------

CBAR is tested on Python 2.7 and depends on NumPy, SciPy, Pandas, NLTK, and

scikit-learn. See ``setup.py`` for version information.

Documentation

-------------

https://dschwertfeger.github.io/cbar

On GitHub

---------

https://github.com/dschwertfeger/cbar

References

----------

.. [1] Grangier, D. and Bengio, S., 2008. `A discriminative kernel-based

        approach to rank images from text queries.

        `_

        IEEE transactions on pattern analysis and machine intelligence, 30(8),

        pp.1371-1384.

.. [2] Chechik, G., Ie, E., Rehn, M., Bengio, S. and Lyon, D., 2008,

        October. `Large-scale content-based audio retrieval from text queries.

        `_

        In Proceedings of the 1st ACM international conference on Multimedia

        information retrieval (pp. 105-112). ACM.

.. [3] Shalit, U., Weinshall, D. and Chechik, G., 2012. `Online learning in

        the embedded manifold of low-rank matrices.

        `_

        Journal of Machine Learning Research, 13(Feb), pp.429-458.

.. [4] Weston, J., Bengio, S. and Usunier, N., 2010. `Large scale image

        annotation: learning to rank with joint word-image embeddings.

        `_

        Machine learning, 81(1), pp.21-35.

.. [5] Lim, D. and Lanckriet, G., 2014. `Efficient Learning of Mahalanobis

        Metrics for Ranking.

        `_

        In Proceedings of The 31st International Conference on Machine Learning

        (pp. 1980-1988).