no code implementations • LREC 2020 • Yonas Woldemariam, Adam Dahlgren
We present an ASR based pipeline for Amharic that orchestrates NLP components within a cross media analysis framework (CMAF).
no code implementations • LREC 2020 • Yonas Woldemariam
In this paper, we investigate a model adaptation method, namely transfer learning for a less-resourced Semitic language i. e., Amharic, to solve resource scarcity problems in speech recognition development and improve the Amharic ASR model.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • LREC 2020 • Yonas Woldemariam
In our experiments, extracting answers from systematically selected users followed by linguistic features annotation and models building.