Planned intervention: On Wednesday April 3rd 05:30 UTC Zenodo will be unavailable for up to 2-10 minutes to perform a storage cluster upgrade.

There is a newer version of the record available.

Published March 20, 2015 | Version v0.1
Software Open

ABXpy v0.1

  • 1. LSCP (ENS/EHESS/CNRS), PSL Research University, Paris, France; SIERRA project-team (ENS/INRIA/CNRS), PSL Research University, Paris, France
  • 2. LSCP (ENS/EHESS/CNRS), PSL Research University, Paris, France

Description

Python library for computing ABX discriminability scores over large datasets.

Files

ABXpy-v0.1.zip

Files (141.0 kB)

Name Size Download all
md5:90f41a88ef9b410fa1982919897b90a0
141.0 kB Preview Download

Additional details

Related works

Funding

BOOTPHON – A computational approach to early language bootstrapping 295810
European Commission

References

  • T. Schatz, V. Peddinti, F. Bach, A. Jansen, H. Hermansky, and E. Dupoux, “Evaluating speech features with the Minimal-Pair ABX task (I): Analysis of the classical MFC/PLP pipeline,” in proceedings of INTERSPEECH, 2013.
  • T. Schatz, V. Peddinti, X.-N. Cao, F. Bach, H. Hermansky, and E. Dupoux, “Evaluating speech features with the Minimal-Pair ABX task (II): Resistance to noise,” in proceedings of INTERSPEECH, 2014.