DP-Parse: Finding Word Boundaries from Raw Speech with an Instance Lexicon
Abstract
Finding word boundaries in continuous speech is challenging as there is little or no equivalent of a 'space' delimiter between words. Popular Bayesian non-parametric models for text segmentation use a Dirichlet process to jointly segment sentences and build a lexicon of word types. We introduce DP-Parse, which uses similar principles but only relies on an instance lexicon of word tokens, avoiding the clustering errors that arise with a lexicon of word types. On the Zero Resource Speech Benchmark 2017, our model sets a new speech segmentation state-of-the-art in 5 languages. The algorithm monotonically improves with better input representations, achieving yet higher scores when fed with weakly supervised inputs. Despite lacking a type lexicon, DP-Parse can be pipelined to a language model and learn semantic and syntactic representations as assessed by a new spoken word embedding benchmark.
Cite
@article{arxiv.2206.11332,
title = {DP-Parse: Finding Word Boundaries from Raw Speech with an Instance Lexicon},
author = {Robin Algayres and Tristan Ricoul and Julien Karadayi and Hugo Laurençon and Salah Zaiem and Abdelrahman Mohamed and Benoît Sagot and Emmanuel Dupoux},
journal= {arXiv preprint arXiv:2206.11332},
year = {2022}
}