Software and Data

This is a list of software I co-authored and data I compiled during my research. For code or data especific of a paper, please refer to the list of publications.

Software

Miscellaneous

• ircor: Correlation Coefficients for Information Retrieval.
  CRAN package, Latest version.

Information Retrieval Evaluation

• simIReff: Stochastic Simulation for IR Evaluation Research: Effectiveness Scores.
  CRAN package, Latest version.
• Allcea: A Library for Low-Cost Evaluation in Audio music similarity.
  Currently under development.
• gt4ireval: Generalizability Theory for Information Retrieval Evaluation.
  CRAN package, Vignette, Latest version.
• nFire: A framework for Information Retrieval Evaluation in .net.
  Latest version.

Music Information Retrieval

• MelodyShape: A library and tool for Symbolic Melodic Similarity based on shape similarity.
  Latest version, User manual.
• essentia-robustness: Scripts to evaluate the robustness of descriptors to different encodings and analysis parameters.
  Latest version.

Crowdsourcing

• GetAnotherLabel.net: A C# port of the original quality control code for estimating the quality of the workers in crowdsourcing environments.
  Latest version.

Data

Music Information Retrieval

• AcousticBrainz dataset: a large-scale collection of hierarchical multi-label genre annotations from different metadata sources.

Text Information Retrieval

• EIREX test collections: a set of small Web test collections to use in graduate Information Retrieval courses.