New Baseline in Automatic Speech Recognition for Northern Sámi
Juho Leinonen, Peter Smit, Sámi Virpioja, Mikko Kurimo · 2018
Automatic speech recognition has gone through many changes in recent years.Advances both in computer hardware and machine learning have made it possible to develop systems far more capable and complex than the previous state-of-theart.However, almost all of these improvements have been tested in major wellresourced languages.In this paper, we show that these techniques are capable of yielding improvements even in a small data scenario.We experiment with different deep neural network architectures for acoustic modeling for Northern Sámi and report up to 50% relative error rate reductions.We also run experiments to compare the performance of subwords as language modeling units in Northern Sámi. TiivistelmäAutomaattinen puheentunnistus on kehittynyt viime vuosina merkittävästi.Uudet innovaatiot sekä laitteistossa että koneoppimisessa ovat mahdollistaneet entistä paljon tehokkaammat ja monimutkaisemmat järjestelmät.