Bayesian models for unit discovery on a very low resource language

Abstract : Developing speech technologies for low-resource languages has become a very active research field over the last decade. Among others, Bayesian models have shown some promising results on artificial examples but still lack of in situ experiments. Our work applies state-of-the-art Bayesian models to unsupervised Acoustic Unit Discovery (AUD) in a real low-resource language scenario. We also show that Bayesian models can naturally integrate information from other resourceful languages by means of informative prior leading to more consistent discovered units. Finally, discovered acoustic units are used, either as the 1-best sequence or as a lattice, to perform word segmentation. Word segmentation results show that this Bayesian approach clearly outperforms a Segmental-DTW baseline on the same corpus.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [22 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01709589
Contributor : Laurent Besacier <>
Submitted on : Thursday, February 15, 2018 - 10:24:26 AM
Last modification on : Thursday, April 4, 2019 - 10:18:05 AM
Document(s) archivé(s) le : Monday, May 7, 2018 - 11:37:19 PM

File

main.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01709589, version 1
  • ARXIV : 1802.06053

Citation

Lucas Ondel, Pierre Godard, Laurent Besacier, Elin Larsen, Mark Hasegawa-Johnson, et al.. Bayesian models for unit discovery on a very low resource language. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Feb 2018, Calgary, Alberta, Canada. ⟨hal-01709589⟩

Share

Metrics

Record views

497

Files downloads

59