Dialect identification in humans and machines: The case of Norwegian prosody
The Journal of the Acoustical Society of America · 01.11.2026 · 160 (5) · 4057-4068
DOI: 10.1121/10.0046103 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, online erschienen am 09.11.2026. Verfasst von Phoebe Parsons und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronic Systems, Norwegian University of Science and Technology, Trondheim, Norway. Hauptthemen laut MEDLINE: Speech Acoustics, Phonetics, Speech Perception, Language. Die Arbeit nennt 55 Literaturangaben. Gefördert von: Norges Forskningsråd.
Abstract (Originalsprache)
Across languages, attempts have been made to determine whether prosodic or phonemic information is more important in human dialect identification (DID). Results suggest that the degree to which prosody is important varies from language to language. We present the first systematic study of this trade-off in Norwegian and examine whether the same balance exists in automatic DID. We report results from two experiments where native Norwegians classified spontaneous Norwegian speech samples. In the first experiment, half of the audio files had been low-pass filtered to isolate prosody. In the second, the pitch was flattened to the average F0 to reduce prosodic information. Results indicate that Norwegians are able to classify dialects on the basis of purely prosodic information, but that prosody is more important for certain dialects than for others. We demonstrate that a machine Norwegian DID model does not pattern with humans, and that in order to classify using prosody alone, the model needs fine-tuning on low-pass filtered data. After such fine-tuning, the model outperforms humans, and for some test sets, it also outperforms the model that uses unmodified audio. Hence, our findings show that prosody is highly relevant to Norwegian dialect classification for both humans and machines.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Electronic Systems, Norwegian University of Science and Technology, Trondheim, Norway.
- Telenor Research, Telenor, Fornebu, Norway.
ORCID-Profile: Phoebe Parsons, Heming Strømholt Bremnes, Knut Kvale, Torbjørn Svendsen, Giampiero Salvi
Förderung
- Norges Forskningsråd
Zitieren
APA
Parsons, P., Bremnes, H. S., Kvale, K., Svendsen, T., & Salvi, G. (2026). Dialect identification in humans and machines: The case of Norwegian prosody. The Journal of the Acoustical Society of America, 160(5), 4057-4068. https://doi.org/10.1121/10.0046103
Vancouver
Parsons P, Bremnes HS, Kvale K, Svendsen T, Salvi G. Dialect identification in humans and machines: The case of Norwegian prosody. The Journal of the Acoustical Society of America. 2026;160(5):4057-4068. doi:10.1121/10.0046103
BibTeX
@article{Parsons2026,
author = {Parsons, Phoebe and Bremnes, Heming Strømholt and Kvale, Knut and Svendsen, Torbjørn and Salvi, Giampiero},
title = {Dialect identification in humans and machines: The case of Norwegian prosody},
journal = {The Journal of the Acoustical Society of America},
year = {2026},
volume = {160},
number = {5},
pages = {4057--4068},
doi = {10.1121/10.0046103}
}
EUVIMED