Contrastive Prediction Strategies for Unsupervised Segmentation and Categorization of Phonemes and Words
Santiago Cuervo, Maciej Grabias, Jan Chorowski, Grzegorz Ciesielski, Adrian Lancucki, Pawel Rychlikowski, Ricard Marxer
Abstract
We identify a performance trade-off between the tasks of phoneme categorization and phoneme and word segmentation in several self-supervised learning algorithms based on Contrastive Predictive Coding (CPC). Our experiments suggest that context building networks, albeit necessary for high performance on categorization tasks, harm segmentation performance by causing a temporal shift on the learned representations. Aiming to tackle this trade-off, we take inspiration from the leading approaches on segmentation and propose multi-level Aligned CPC (mACPC). It builds on Aligned CPC (ACPC), a variant of CPC which exhibits the best performance on categorization tasks, and incorporates multi-level modeling and optimization for detection of spectral changes. Our methods improve in all tested categorization metrics and achieve state-of-the-art performance in word segmentation.
BibTeX
@inproceedings{icassp2022_contrastivepredi,
title = {Contrastive Prediction Strategies for Unsupervised Segmentation and Categorization of Phonemes and Words},
author = {Santiago Cuervo and Maciej Grabias and Jan Chorowski and Grzegorz Ciesielski and Adrian Lancucki and Pawel Rychlikowski and Ricard Marxer},
booktitle = {ICASSP 2022},
year = {2022}
}