DP-Parse: Finding Word Boundaries from Raw Speech with an Instance Lexicon - Inria - Institut national de recherche en sciences et technologies du numérique
Journal Articles Transactions of the Association for Computational Linguistics Year : 2022

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 (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-theart 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
Fichier principal
Vignette du fichier
2206.11332.pdf (575.77 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03831873 , version 1 (27-10-2022)

Identifiers

Cite

Robin Algayres, Tristan Ricoul, Julien Karadayi, Hugo Laurençon, Salah Zaiem, et al.. DP-Parse: Finding Word Boundaries from Raw Speech with an Instance Lexicon. Transactions of the Association for Computational Linguistics, 2022, 10, pp.1051-1065. ⟨10.1162/tacl_a_00505⟩. ⟨hal-03831873⟩
69 View
58 Download

Altmetric

Share

More