Please use this identifier to cite or link to this item: http://hdl.handle.net/10125/24869

Evaluating cross-linguistic forced alignment of conversational data in north Australian Kriol, an under-resourced language

File Size Format  
jones et al.pdf 1.33 MB Adobe PDF View/Open

Item Summary

Title:Evaluating cross-linguistic forced alignment of conversational data in north Australian Kriol, an under-resourced language
Authors:Jones, Caroline
Li, Weicong
Almeida, Andre
German, Amit
Keywords:Australian Kriol
forced alignment
Creoles
language documentation
speech technology
Date Issued:Jun 2019
Publisher:University of Hawaii Press
Citation:Jones, Caroline, Weicong Li, Andre Almeida, & Amit German. 2019. Evaluating cross-linguistic forced alignment of conversational data in north Australian Kriol, an under-resourced language. Language Documentation & Conservation 13: 281-299.
Abstract:Speech technology is transforming language documentation; acoustic models trained on “small” languages are now technically feasible. At the same time, forced alignment built for major world languages has matured and now offers ease of use through web interfaces requiring low technical expertise. This paper provides an updated and detailed evaluation of cross-linguistic forced alignment, the approach of using forced aligners untrained on the target language. We compare two options within MAUS (Munich Automatic Segmentation System): language-independent mode vs major world language system (here, Italian) on the one dataset, a comparison that has not previously been reported. The dataset comes from a corpus of adult conversational speech in Kriol, an English-based creole of northern Australia. The results of using MAUS Italian were better than those of using the language-independent mode and those in previous studies: the agreement rate at 20 ms was 72.1% at vowel onset and 57.2% at vowel offset. With completely misaligned tokens excluded, the overall agreement rate rose to 69.2% at 20 ms and over 90% at 50 ms. Most errors in the output SAMPA (Speech Assessment Methods Phonetic Alphabet) labels were resolvable with simple text replacements. These results offer updated benchmark data for an untrained, late-model forced alignment system.
Pages/Duration:19 pages
URI:http://hdl.handle.net/10125/24869
ISSN:1934-5275
Rights:Creative Commons Attribution-NonCommercial 4.0 International
Attribution-NonCommercial 3.0 United States
http://creativecommons.org/licenses/by-nc/3.0/us/
Journal:Language Documentation & Conservation
Volume:13
Appears in Collections: Volume 13 : Language Documentation & Conservation


Please email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.

This item is licensed under a Creative Commons License Creative Commons