New Baseline in Automatic Speech Recognition for Northern Sámi
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
|Title of host publication||Fourth International Workshop on Computational Linguistics for Uralic Languages|
|Number of pages||11|
|State||Accepted/In press - Dec 2017|
|MoE publication type||A4 Article in a conference publication|
|Event||International Workshop on Computational Linguistics for Uralic Languages - Helsinki, Finland|
Duration: 8 Jan 2018 → 9 Jan 2018
Conference number: 4
|Conference||International Workshop on Computational Linguistics for Uralic Languages|
|Period||08/01/2018 → 09/01/2018|
- Utopia Analytics Oy
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.