Towards the First Dictation System for Latvian Language
Askars Salimbajevs · Frontiers in artificial intelligence and applications · 2016
In this paper, we introduce the first dictation system for the Latvian language. We present its main features, the details of the automatic speech recognition (ASR) system used in this service, software architecture, and an evaluation of recognition quality. The service will provide Latvian-speaking people with the opportunity to dictate text in Latvian into their computers. The presented system achieved a word error rate (WER) of 23.86% in evaluation of dictation scenario, which is a good result for a system in the beta stage.