Assessing agreement level between forced alignment models with data from endangered language documentation corpora

Christian T. DiCanio, Hosung Nam, D. H. Whalen, H. Timothy Bunnell, Jonathan D. Amith, Rey Castillo García

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

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.

Original languageEnglish
Title of host publication13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012
Pages130-133
Number of pages4
Publication statusPublished - 2012 Dec 1
Externally publishedYes
Event13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012 - Portland, OR, United States
Duration: 2012 Sep 92012 Sep 13

Publication series

Name13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012
Volume1

Conference

Conference13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012
CountryUnited States
CityPortland, OR
Period12/9/912/9/13

Fingerprint

documentation
language
Transcription
Labeling
Mexico
efficiency

Keywords

  • Linguistics
  • Phonetics
  • Speech recognition

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Communication

Cite this

DiCanio, C. T., Nam, H., Whalen, D. H., Bunnell, H. T., Amith, J. D., & García, R. C. (2012). Assessing agreement level between forced alignment models with data from endangered language documentation corpora. In 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012 (pp. 130-133). (13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012; Vol. 1).

Assessing agreement level between forced alignment models with data from endangered language documentation corpora. / DiCanio, Christian T.; Nam, Hosung; Whalen, D. H.; Bunnell, H. Timothy; Amith, Jonathan D.; García, Rey Castillo.

13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012. 2012. p. 130-133 (13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012; Vol. 1).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

DiCanio, CT, Nam, H, Whalen, DH, Bunnell, HT, Amith, JD & García, RC 2012, Assessing agreement level between forced alignment models with data from endangered language documentation corpora. in 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012. 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012, vol. 1, pp. 130-133, 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012, Portland, OR, United States, 12/9/9.
DiCanio CT, Nam H, Whalen DH, Bunnell HT, Amith JD, García RC. Assessing agreement level between forced alignment models with data from endangered language documentation corpora. In 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012. 2012. p. 130-133. (13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012).
DiCanio, Christian T. ; Nam, Hosung ; Whalen, D. H. ; Bunnell, H. Timothy ; Amith, Jonathan D. ; García, Rey Castillo. / Assessing agreement level between forced alignment models with data from endangered language documentation corpora. 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012. 2012. pp. 130-133 (13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012).
@inproceedings{4bea6ad764074a98bf3c3d5289423dc9,
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",
month = "12",
day = "1",
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",

}

TY - GEN

T1 - Assessing agreement level between forced alignment models with data from endangered language documentation corpora

AU - DiCanio, Christian T.

AU - Nam, Hosung

AU - Whalen, D. H.

AU - Bunnell, H. Timothy

AU - Amith, Jonathan D.

AU - García, Rey Castillo

PY - 2012/12/1

Y1 - 2012/12/1

N2 - 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.

AB - 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.

KW - Linguistics

KW - Phonetics

KW - Speech recognition

UR - http://www.scopus.com/inward/record.url?scp=84878384249&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878384249&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781622767595

T3 - 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012

SP - 130

EP - 133

BT - 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012

ER -