Metric Learning for Temporal Sequence Alignment

Authors: Damien Garreau, Rémi Lajugie, Sylvain Arlot, Francis Bach

NeurIPS 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 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.
Researcher Affiliation Academia Damien Garreau ENS damien.garreau@ens.fr Remi Lajugie INRIA remi.lajugie@inria.fr Sylvain Arlot CNRS sylvain.arlot@ens.fr Francis Bach INRIA francis.bach@inria.fr
Pseudocode Yes This algorithm is described in Alg. 1 of the supplementary material.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets Yes First, we applied our method on the dataset of Kirchhoff and Lerch [14]. In this dataset, pairs of aligned examples (Ai, Bi) are artificially created by stretching an original audio signal. That way, the groundtruth alignment Y i is known and thus the data falls into our setting A more precise description of the dataset can be found in [14]. The Bach 10 dataset3 consists in ten J. S. Bach s Chorales (small quadriphonic pieces). http://music.cs.northwestern.edu/data/Bach10.html.
Dataset Splits No The paper mentions 'n pairs of training instances' but does not specify exact dataset split percentages, sample counts, or cross-validation setup for reproduction.
Hardware Specification No The paper does not provide specific hardware details (like exact GPU/CPU models or memory amounts) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup No The paper does not contain specific experimental setup details such as concrete hyperparameter values or comprehensive training configurations.