Unsupervised Word Segmentation from Discrete Speech Units in Low-Resource Settings

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F22%3APU150717" target="_blank" >RIV/00216305:26230/22:PU150717 - isvavai.cz</a>

Výsledek na webu

<a href="https://aclanthology.org/2022.sigul-1.1.pdf" target="_blank" >https://aclanthology.org/2022.sigul-1.1.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Unsupervised Word Segmentation from Discrete Speech Units in Low-Resource Settings

Popis výsledku v původním jazyce

Documenting languages helps to prevent the extinction of endangered dialects - many of which are otherwise expected to dis- appear by the end of the century. When documenting oral languages, unsupervised word segmentation (UWS) from speech is a useful, yet challenging, task. It consists in producing time-stamps for slicing utterances into smaller segments corresponding to words, being performed from phonetic transcriptions, or in the absence of these, from the output of unsupervised speech discretization models. These discretization models are trained using raw speech only, producing discrete speech units that can be applied for downstream (text-based) tasks. In this paper we compare five of these models: three Bayesian and two neural approaches, with regards to the exploitability of the produced units for UWS. For the UWS task, we experiment with two models, using as our target language the Mboshi (Bantu C25), an unwritten language from Congo-Brazzaville. Additionally, we report results for Finnish, Hungarian, Romanian and Russian in equally low-resource settings, using only 4 hours of speech. Our results suggest that neural models for speech discretization are difficult to exploit in our setting, and that it might be necessary to adapt them to limit sequence length. We obtain our best UWS results by using Bayesian models that produce high quality, yet compressed, discrete representations of the input speech signal.

Název v anglickém jazyce

Unsupervised Word Segmentation from Discrete Speech Units in Low-Resource Settings

Popis výsledku anglicky

Documenting languages helps to prevent the extinction of endangered dialects - many of which are otherwise expected to dis- appear by the end of the century. When documenting oral languages, unsupervised word segmentation (UWS) from speech is a useful, yet challenging, task. It consists in producing time-stamps for slicing utterances into smaller segments corresponding to words, being performed from phonetic transcriptions, or in the absence of these, from the output of unsupervised speech discretization models. These discretization models are trained using raw speech only, producing discrete speech units that can be applied for downstream (text-based) tasks. In this paper we compare five of these models: three Bayesian and two neural approaches, with regards to the exploitability of the produced units for UWS. For the UWS task, we experiment with two models, using as our target language the Mboshi (Bantu C25), an unwritten language from Congo-Brazzaville. Additionally, we report results for Finnish, Hungarian, Romanian and Russian in equally low-resource settings, using only 4 hours of speech. Our results suggest that neural models for speech discretization are difficult to exploit in our setting, and that it might be necessary to adapt them to limit sequence length. We obtain our best UWS results by using Bayesian models that produce high quality, yet compressed, discrete representations of the input speech signal.

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

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2022

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the the 1st Annual Meeting of the ELRA/ISCA Special Interest Group on Under-Resourced Languages

ISBN

979-10-95546-91-7

ISSN

—

e-ISSN

—

Počet stran výsledku

9

Strana od-do

1-9

Název nakladatele

European Language Resources Association

Místo vydání

Marseile

Místo konání akce

Marseile

Datum konání akce

20. 6. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—