Bayesian Models for Unit Discovery on a Very Low Resource Language

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F18%3APU130733" target="_blank" >RIV/00216305:26230/18:PU130733 - isvavai.cz</a>

Výsledek na webu

<a href="http://www.fit.vutbr.cz/research/pubs/all.php?id=11719" target="_blank" >http://www.fit.vutbr.cz/research/pubs/all.php?id=11719</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICASSP.2018.8461545" target="_blank" >10.1109/ICASSP.2018.8461545</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Bayesian Models for Unit Discovery on a Very Low Resource Language

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

Bayesian Models for Unit Discovery on a Very Low Resource Language

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/LQ1602" target="_blank" >LQ1602: IT4Innovations excellence in science</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2018

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of ICASSP 2018

ISBN

978-1-5386-4658-8

ISSN

—

e-ISSN

—

Počet stran výsledku

5

Strana od-do

5939-5943

Název nakladatele

IEEE Signal Processing Society

Místo vydání

Calgary

Místo konání akce

Calgary

Datum konání akce

15. 4. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000446384606020