New Baseline in Automatic Speech Recognition for Northern Sámi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Details

Original languageEnglish
Title of host publicationFourth International Workshop on Computational Linguistics for Uralic Languages
PublisherACL
Pages89-99
Number of pages11
StateAccepted/In press - Dec 2017
MoE publication typeA4 Article in a conference publication
EventInternational Workshop on Computational Linguistics for Uralic Languages - Helsinki, Finland
Duration: 8 Jan 20189 Jan 2018
Conference number: 4

Conference

ConferenceInternational Workshop on Computational Linguistics for Uralic Languages
Abbreviated titleIWCLUL
CountryFinland
CityHelsinki
Period08/01/201809/01/2018

Researchers

Research units

  • Utopia Analytics Oy

Abstract

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-the-art. However, almost all of these improvements have been tested in major well-resourced 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 different subwords as language modeling units in Northern Sámi.

Download statistics

No data available

ID: 16394324