Software Open Access

UPS-IRIT system #1 for track1

Pellegrini, Thomas; Manenti, Céline; Pinquier, Julien

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 (10.7 GB)
Name Size
zrsc17-track1-IRIT-UPS.tar.gz
md5:4996b08277b02c0f8c48b855be7a651a
10.7 GB Download

Share

Cite as