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

Result code in 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>

Result on the web

<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

—

Result language

angličtina

Original language name

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

Original language description

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.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

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

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2022

Confidentiality

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

Article name in the collection

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

—

Number of pages

9

Pages from-to

1-9

Publisher name

European Language Resources Association

Place of publication

Marseile

Event location

Marseile

Event date

Jun 20, 2022

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—