Semantically Corrected Amharic Automatic Speech Recognition

arXiv:2404.13362v1 Announce Type: cross
Abstract: Automatic Speech Recognition (ASR) can play a crucial role in enhancing the accessibility of spoken languages worldwide. In this paper, we build a set of ASR tools for Amharic, a language spoken by more than 50 million people primarily in eastern Africa. Amharic is written in the Ge'ez script, a sequence of graphemes with spacings denoting word boundaries. This makes computational processing of Amharic challenging since the location of spacings can significantly impact the meaning …

abstract accessibility africa arxiv asr automatic speech recognition build cs.ai cs.cl cs.lg eess.as language languages paper people recognition role set speech speech recognition spoken tools type