Authors
Phoebe Parsons, Heming Strømholt Bremnes, Knut Kvale, Torbjørn Svendsen, Giampiero Salvi
Published in
The Journal of the Acoustical Society of America. Volume 160. Issue 5. Pages 4057-4068. Nov 01, 2026.
Abstract
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.
PMID:
43002469
Bibliographic data and abstract were imported from PubMed on 10 Nov 2026.
Read full publication at:
Please sign in
to see all details.
Advertisement
Stats
- Recommendations n/a n/a positive of 0 vote(s)
- Views 14
- Comments 0