Julien Karadayi
2022
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
Transactions of the Association for Computational Linguistics, Volume 10
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
Search
Co-authors
- Robin Algayres 1
- Tristan Ricoul 1
- Hugo Laurençon 1
- Salah Zaiem 1
- Abdelrahman Mohamed 1
- show all...
Venues
- tacl1