9 citations · 21 across the 14 of their papers we have counts for
6 papers · 1 filter
Speech Recognition for Endangered and Extinct Samoyedic languages
Niko Partanen, Mika Hämäläinen, Tiina Klooster
Our study presents a series of experiments on speech recognition with endangered and extinct Samoyedic languages, spoken in Northern and Southern Siberia. To best of our knowledge,…
Normalization of Different Swedish Dialects Spoken in Finland
Mika Hämäläinen, Niko Partanen, Khalid Alnajjar
Our study presents a dialect normalization method for different Finland Swedish dialects covering six regions. We tested 5 different models, and the best model improved the word er…
Ve'rdd. Narrowing the Gap between Paper Dictionaries, Low-Resource NLP and Community Involvement
Khalid Alnajjar, Mika Hämäläinen, Jack Rueter +1
We present an open-source online dictionary editing system, Ve'rdd, that offers a chance to re-evaluate and edit grassroots dictionaries that have been exposed to multiple amateur…
Automated Prediction of Medieval Arabic Diacritics
Khalid Alnajjar, Mika Hämäläinen, Niko Partanen +1
This study uses a character level neural machine translation approach trained on a long short-term memory-based bi-directional recurrent neural network architecture for diacritizat…
Automatic Dialect Adaptation in Finnish and its Effect on Perceived Creativity
Mika Hämäläinen, Niko Partanen, Khalid Alnajjar +2
We present a novel approach for adapting text written in standard Finnish to different dialects. We experiment with character level NMT models both by using a multi-dialectal and t…
Uralic Language Identification (ULI) 2020 shared task dataset and the Wanca 2017 corpus
Tommi Jauhiainen, Heidi Jauhiainen, Niko Partanen +1
This article introduces the Wanca 2017 corpus of texts crawled from the internet from which the sentences in rare Uralic languages for the use of the Uralic Language Identification…