DP-Parse: Finding Word Boundaries from Raw Speech with an Instance Lexicon

Robin Algayres, Tristan Ricoul, Julien Karadayi, Hugo Laurençon, Salah Zaiem, Abdelrahman Mohamed, Benoît Sagot, Emmanuel Dupoux


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 (Goldwater et al., 2006, 2009) 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. 1
Anthology ID:
2022.tacl-1.61
Volume:
Transactions of the Association for Computational Linguistics, Volume 10
Month:
Year:
2022
Address:
Cambridge, MA
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
1051–1065
Language:
URL:
https://aclanthology.org/2022.tacl-1.61
DOI:
10.1162/tacl_a_00505
Bibkey:
Cite (ACL):
Robin Algayres, Tristan Ricoul, Julien Karadayi, Hugo Laurençon, Salah Zaiem, Abdelrahman Mohamed, Benoît Sagot, and Emmanuel Dupoux. 2022. DP-Parse: Finding Word Boundaries from Raw Speech with an Instance Lexicon. Transactions of the Association for Computational Linguistics, 10:1051–1065.
Cite (Informal):
DP-Parse: Finding Word Boundaries from Raw Speech with an Instance Lexicon (Algayres et al., TACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/paclic-22-ingestion/2022.tacl-1.61.pdf