The paper discusses an Amharic speaker independent continuous speech recognizer based on an HMM/ANN hybrid approach. The model was constructed at a context dependent phone part subword level with the help of the CSLU Toolkit. A promising result of 74.28% word and 39.70% sentence recognition rate was achieved. These are the best figures reported so far for speech recognition for the Amharic language.
Cite as: Seid, H., Gambäck, B. (2005) A speaker independent continuous speech recognizer for Amharic. Proc. Interspeech 2005, 3349-3352, doi: 10.21437/Interspeech.2005-860
@inproceedings{seid05_interspeech,
author={Hussien Seid and Björn Gambäck},
title={{A speaker independent continuous speech recognizer for Amharic}},
year=2005,
booktitle={Proc. Interspeech 2005},
pages={3349--3352},
doi={10.21437/Interspeech.2005-860}
}