Published June 27, 2017 | Version v1

UPS-IRIT system #1 for track1

  • 1. Université de Toulouse ; IRIT

Description

We run a k-means (k=100 clusters, L2 norm) on the baseline MFCCs (static, first and second derivative, 39-d) that are ZCA whitened on a per-file basis. The feature representations correspond to the distances between the data points and the cluster centroids.

Files

Files (10.7 GB)

Name Size
md5:4996b08277b02c0f8c48b855be7a651a
10.7 GB Download