EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Evaluating the consistency of lenition measures: Neural networks' posterior probability, intensity velocity, and duration

Kevin Tang iD, Ratree Wayland iD, Fenqi Wang iD, Sophia Vellozzi iD, Rahul Sengupta iD

The Journal of the Acoustical Society of America · 01.08.2024 · 156 (2) · 1367-1379

DOI: 10.1121/10.0028299 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, online erschienen am 27.08.2024. Verfasst von Kevin Tang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of English Language and Linguistics, Institute of English and American Studies, Faculty of Arts and Humanities, Heinrich Heine University …. Hauptthemen laut MEDLINE: Neural Networks, Computer, Phonetics, Speech Acoustics. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predictions of gradient degree of lenition of voiceless and voiced stops in a corpus of Argentine Spanish are evaluated using three acoustic measures (minimum and maximum intensity velocity and duration) and two recurrent neural network (Phonet) measures (posterior probabilities of sonorant and continuant phonological features). While mixed and inconsistent predictions were obtained across the acoustic metrics, sonorant and continuant probability values were consistently in the direction predicted by known factors of a stop's lenition with respect to its voicing, place of articulation, and surrounding contexts. The results suggest the effectiveness of Phonet as an additional or alternative method of lenition measurement. Furthermore, this study has enhanced the accessibility of Phonet by releasing the trained Spanish Phonet model used in this study and a pipeline with step-by-step instructions for training and inferencing new models.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerPhoneticsSpeech AcousticsHumansAcousticsProbabilitySpeech Production MeasurementTime Factors

Autor:innen und Institutionen

  • Department of English Language and Linguistics, Institute of English and American Studies, Faculty of Arts and Humanities, Heinrich Heine University Düsseldorf, Düsseldorf, 40225, Germany.
  • Department of Linguistics, University of Florida, Gainesville, Florida, 32611-5454, USA.
  • Department of Linguistics, Simon Fraser University, Burnaby, British Columbia V5A-1S6, Canada.
  • Department of Computer and Information Science and Engineering, University of Florida, 32611-116120, USA.

ORCID-Profile: Kevin Tang, Ratree Wayland, Fenqi Wang, Sophia Vellozzi, Rahul Sengupta

Förderung

  • National Science Foundation

Zitieren

APA

Tang, K., Wayland, R., Wang, F., Vellozzi, S., & Sengupta, R. (2024). Evaluating the consistency of lenition measures: Neural networks' posterior probability, intensity velocity, and duration. The Journal of the Acoustical Society of America, 156(2), 1367-1379. https://doi.org/10.1121/10.0028299

Vancouver

Tang K, Wayland R, Wang F, Vellozzi S, Sengupta R. Evaluating the consistency of lenition measures: Neural networks' posterior probability, intensity velocity, and duration. The Journal of the Acoustical Society of America. 2024;156(2):1367-1379. doi:10.1121/10.0028299

BibTeX
@article{Tang2024,
  author = {Tang, Kevin and Wayland, Ratree and Wang, Fenqi and Vellozzi, Sophia and Sengupta, Rahul},
  title = {Evaluating the consistency of lenition measures: Neural networks' posterior probability, intensity velocity, and duration},
  journal = {The Journal of the Acoustical Society of America},
  year = {2024},
  volume = {156},
  number = {2},
  pages = {1367--1379},
  doi = {10.1121/10.0028299}
}
Kostenlos starten →