EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Gradient boundaries through confidence intervals for forced alignment estimates using model ensembles

Matthew C Kelley iD

Phonetica · 24.06.2026 · 83 (3) · 285-305

DOI: 10.1515/phon-2025-0039 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Phonetica, online erschienen am 06.05.2026. Verfasst von Matthew C Kelley. Beteiligte Einrichtung: Linguistics Program, Department of English, George Mason University, Fairfax, VA, 22030, USA. Hauptthemen laut MEDLINE: Neural Networks, Computer, Phonetics. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Forced alignment is a common tool to align audio with orthographic and phonetic transcriptions. Most forced alignment tools provide only point-estimates of boundaries. The present project introduces a method of producing gradient boundaries by deriving confidence intervals using neural network ensembles. Ten different segment classifier neural networks were previously trained, and the alignment process is repeated with each classifier. The ensemble is then used to place the point-estimate of a boundary at the median of the boundaries in the ensemble, and the gradient range is placed using a 97.85 % confidence interval around the median constructed using order statistics. Gradient boundaries are taken here as a more realistic representation of how segments transition into each other. Moreover, the range indicates the model uncertainty in the boundary placement, facilitating tasks like finding boundaries that should be reviewed. As a bonus, on the Buckeye and TIMIT corpora, the ensemble boundaries show a slight overall improvement over using just a single model. The gradient boundaries can be emitted during alignment as JSON files and a main table for programmatic and statistical analysis. For familiarity, they are also output as Praat TextGrids using a point tier to represent the edges of the boundary regions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerPhoneticsHumansAlgorithms

Stichwörter der Autor:innen

acoustic modelingautomatic speech recognitionforced alignmentphoneticsspeech segmentation

Autor:innen und Institutionen

  • Linguistics Program, Department of English, George Mason University, Fairfax, VA, 22030, USA.

ORCID-Profile: Matthew C Kelley

Zitieren

APA

Kelley, M. C. (2026). Gradient boundaries through confidence intervals for forced alignment estimates using model ensembles. Phonetica, 83(3), 285-305. https://doi.org/10.1515/phon-2025-0039

Vancouver

Kelley MC. Gradient boundaries through confidence intervals for forced alignment estimates using model ensembles. Phonetica. 2026;83(3):285-305. doi:10.1515/phon-2025-0039

BibTeX
@article{Kelley2026,
  author = {Kelley, Matthew C},
  title = {Gradient boundaries through confidence intervals for forced alignment estimates using model ensembles},
  journal = {Phonetica},
  year = {2026},
  volume = {83},
  number = {3},
  pages = {285--305},
  doi = {10.1515/phon-2025-0039}
}
Kostenlos starten →