Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Comparative Study
. 2013 Sep;134(3):2235-46.
doi: 10.1121/1.4816491.

Using automatic alignment to analyze endangered language data: testing the viability of untrained alignment

Christian DiCanio  1 , Hosung Nam, Douglas H Whalen, H Timothy Bunnell, Jonathan D Amith, Rey Castillo García
Affiliations
Comparative Study

Using automatic alignment to analyze endangered language data: testing the viability of untrained alignment

Christian DiCanio et al. J Acoust Soc Am. 2013 Sep.

Abstract

While efforts to document endangered languages have steadily increased, the phonetic analysis of endangered language data remains a challenge. The transcription of large documentation corpora is, by itself, a tremendous feat. Yet, the process of segmentation remains a bottleneck for research with data of this kind. This paper examines whether a speech processing tool, forced alignment, can facilitate the segmentation task for small data sets, even when the target language differs from the training language. The authors also examined whether a phone set with contextualization outperforms a more general one. The accuracy of two forced aligners trained on English (hmalign and p2fa) was assessed using corpus data from Yoloxóchitl Mixtec. Overall, agreement performance was relatively good, with accuracy at 70.9% within 30 ms for hmalign and 65.7% within 30 ms for p2fa. Segmental and tonal categories influenced accuracy as well. For instance, additional stop allophones in hmalign's phone set aided alignment accuracy. Agreement differences between aligners also corresponded closely with the types of data on which the aligners were trained. Overall, using existing alignment systems was found to have potential for making phonetic analysis of small corpora more efficient, with more allophonic phone sets providing better agreement than general ones.

PubMed Disclaimer

Figures

FIG. 1.
FIG. 1.
Agreement for consonants and vowels across aligners.
FIG. 2.
FIG. 2.
Agreement for consonant classes across aligners.
FIG. 3.
FIG. 3.
Agreement for vowel qualities across aligners.
FIG. 4.
FIG. 4.
Agreement for vowel nasalization across aligners.
FIG. 5.
FIG. 5.
Agreement for stops across aligners.
FIG. 6.
FIG. 6.
Agreement for glottal stops across aligners.
See this image and copyright information in PMC

References

    1. Adda-Decker, M., and Snoeren, N. D. (2011). “ Quantifying temporal speech reduction in French using forced speech alignment,” J. Phonetics 39, 261–270. 10.1016/j.wocn.2010.11.011 - DOI
    1. Baayen, R. H. (2008). Analyzing Linguistic Data: A Practical Introduction to Statistics Using R (Cambridge University Press, Cambridge, UK: ).
    1. Badenhorst, J., van Heerden, C., Davel, M., and Barnard, E. (2011). “ Collecting and evaluating speech recognition corpora for 11 South African languages,” Lang. Res. Eval. 45(3 ), 289–309. 10.1007/s10579-011-9152-1 - DOI
    1. Bates, D. M. (2005). “ Fitting linear mixed models in R,” R News 5, 27–30.
    1. Beddor, P. S. , and Krakow, R. A. (1999). “ Perception of coarticulatory nasalization by speakers of English and Thai: Evidence for partial compensation,” J. Acoust. Soc. Am. 106(5 ), 2868–2887. 10.1121/1.428111 - DOI - PubMed

Publication types

LinkOut - more resources