Deep learning assessment of syllable affiliation of intervocalic consonants
The Journal of the Acoustical Society of America · 2023
DOI: 10.1121/10.0017117 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, 2023. Verfasst von Zirui Liu und 1 weiteren Autor:innen. Beteiligte Einrichtung: Speech, Hearing, and Phonetic Sciences, University College London, London, WC1N 1PJ, United Kingdom. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 103 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
In English, a sentence like “He made out our intentions.” could be misperceived as “He may doubt our intentions.” because the coda /d/ sounds like it has become the onset of the next syllable. The nature and occurrence condition of this resyllabification phenomenon are unclear, however. Previous empirical studies mainly relied on listener judgment, limited acoustic evidence, such as voice onset time, or average formant values to determine the occurrence of resyllabification. This study tested the hypothesis that resyllabification is a coarticulatory reorganisation that realigns the coda consonant with the vowel of the next syllable. Deep learning in conjunction with dynamic time warping (DTW) was used to assess syllable affiliation of intervocalic consonants. The results suggest that convolutional neural network- and recurrent neural network-based models can detect cases of resyllabification using Mel-frequency spectrograms. DTW analysis shows that neural network inferred resyllabified sequences are acoustically more similar to their onset counterparts than their canonical productions. A binary classifier further suggests that, similar to the genuine onsets, the inferred resyllabified coda consonants are coarticulated with the following vowel. These results are interpreted with an account of resyllabification as a speech-rate-dependent coarticulatory reorganisation mechanism in speech.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Speech, Hearing, and Phonetic Sciences, University College London, London, WC1N 1PJ, United Kingdom.
Zitieren
APA
Liu, Z., & Xu, Y. (2023). Deep learning assessment of syllable affiliation of intervocalic consonants. The Journal of the Acoustical Society of America. https://doi.org/10.1121/10.0017117
Vancouver
Liu Z, Xu Y. Deep learning assessment of syllable affiliation of intervocalic consonants. The Journal of the Acoustical Society of America. 2023. doi:10.1121/10.0017117
BibTeX
@article{Liu2023,
author = {Liu, Zirui and Xu, Yi},
title = {Deep learning assessment of syllable affiliation of intervocalic consonants},
journal = {The Journal of the Acoustical Society of America},
year = {2023},
doi = {10.1121/10.0017117}
}
EUVIMED