Metric Learning for Temporal Sequence Alignment - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

Metric Learning for Temporal Sequence Alignment


In this paper, we propose to learn a Mahalanobis distance to perform alignment of multivariate time series. The learning examples for this task are time series for which the true alignment is known. We cast the alignment problem as a structured prediction task, and propose realistic losses between alignments for which the optimization is tractable. We provide experiments on real data in the audio to audio context, where we show that the learning of a similarity measure leads to improvements in the performance of the alignment task. We also propose to use this metric learning framework to perform feature selection and, from basic audio features, build a combination of these with better performance for the alignment.
Fichier principal
Vignette du fichier
HAL.pdf (780.66 Ko) Télécharger le fichier
alignmentMatrixTrue.pdf (492.33 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Other

Dates and versions

hal-01062130 , version 1 (10-09-2014)



Damien Garreau, Rémi Lajugie, Sylvain Arlot, Francis Bach. Metric Learning for Temporal Sequence Alignment. Advances in Neural Information Processing Systems 27 (NIPS 2014), Dec 2014, Montréal, Canada. ⟨hal-01062130⟩
779 View
261 Download



Gmail Facebook X LinkedIn More