Semiautomatic Speech Alignment for Under-Resourced Languages

Juho Leinonen, Niko Partanen, Sami Virpioja, Mikko Kurimo

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

2 Lataukset (Pure)

Abstrakti

Cross-language forced alignment is a solution for linguists who create speech corpora for very low-resource languages. However, cross-language is an additional challenge making a complex task, forced alignment, even more difficult. We study how linguists can impart domain expertise to the tasks to increase the performance of automatic forced aligners while keeping the time effort still lower than with manual forced alignment. First, we show that speech recognizers have a clear bias in starting the word later than a human annotator, which results in micro-pauses in the results that do not exist in manual alignments, and study which is the best way to automatically remove these silences. Second, we ask the linguists to simplify the task by splitting long interview audios into shorter lengths by providing some manually aligned segments and evaluating the results of this process. We also study how correlated source language performance is to target language performance, since often it is an easier task to find a better source model than to adapt to the target language.
AlkuperäiskieliEnglanti
OtsikkoProceedings of the Workshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia (EURALI)
KustantajaEuropean Language Resources Association (ELRA)
Sivut17-21
Sivumäärä5
ISBN (painettu)978-2-493814-07-4
TilaJulkaistu - 2022
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaWorkshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia - Marseille, Ranska
Kesto: 20 kesäk. 202220 kesäk. 2022

Workshop

WorkshopWorkshop on Resources and Technologies for Indigenous, Endangered and Lesser-resourced Languages in Eurasia
LyhennettäEURALI
Maa/AlueRanska
KaupunkiMarseille
Ajanjakso20/06/202220/06/2022

Siteeraa tätä