@inproceedings{734416a7bcef4d74af2145ddf20f1ef2,
title = "Assessing agreement level between forced alignment models with data from endangered language documentation corpora",
abstract = "Automatic forced alignment between transcriptions has achieved high levels of agreement for languages with large corpora, but the technique holds great promise for work on all languages. Here, we apply two forced alignment programs to data from an endangered Mixtecan language of Mexico. Both yielded a majority of boundaries within 20 ms of hand-labeled ones. Phonemes with fairly steady-state elements (e.g. nasals, fricatives) were more accurately labeled than others. Forced alignment thus may increase efficiency of labeling texts from smaller languages, at least in cases where the phoneme inventories are similar to those of the languages of the training.",
keywords = "Linguistics, Phonetics, Speech recognition",
author = "DiCanio, \{Christian T.\} and Hosung Nam and Whalen, \{D. H.\} and Bunnell, \{H. Timothy\} and Amith, \{Jonathan D.\} and Garc{\'i}a, \{Rey Castillo\}",
year = "2012",
language = "English",
isbn = "9781622767595",
series = "13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012",
pages = "130--133",
booktitle = "13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012",
note = "13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012 ; Conference date: 09-09-2012 Through 13-09-2012",
}