SLPOtherLanguage and speech2022

Comparative Analysis of Majority Language Influence on North Sámi Prosody Using WaveNet-Based modeling.

Katri Hiovain, Antti Suni, Sofoklis Kakouros and 1 others

PMID 33375882

WHAT IT FOUND

A computer model found pitch-pattern differences in North Sámi words spoken by Finnish and Norwegian bilinguals, but the differences were linked to measured pitch only for some word types.

This is a linguistics paper, not clinical evidence for therapy.

Key findings

01The embedding distance between Finnish and Norwegian Sámi word renditions did not correlate significantly with pitch variability or pitch range across the 60 analyzed words.

02When words were grouped by part of speech, the embedding distance correlated significantly with pitch variability for noun-like words and with pitch variability and pitch range for verb-like words.

03The authors state that the majority-language influence interpretation is exploratory and not confirmed.

STILL TO COME

How it was doneWhat they found

Read the rest of this summary

You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.

Already have one?

What it does not show

The model was trained on all the data, so it may describe this corpus rather than generalize to new speech. The speech was read Wikipedia text, not conversation or targeted sentences, so it may not reveal natural intonation differences. Only 21 speakers remained after exclusions, and some word groups had few words, so the reported relationships are fragile. The Finnish and Norwegian groups were not balanced, with nine Finnish and 12 Norwegian speakers. Dialect boundaries did not match country boundaries, so majority language and dialect may be mixed together. The authors state that the majority-language influence hypothesis is not confirmed and needs targeted speech material and perception testing. The study analyzed language variation in bilingual speakers, not a clinical population or treatment outcome.

The easy way to misread this

Do not use this as evidence for speech therapy. It analyzes dialectal prosody in bilingual speakers, not clinical speech problems.

Read it on PubMed →