A Computational Model for Interactive Transcription

Abstract

Transcribing low resource languages can be challenging in the absence of a comprehensive lexicon and proficient transcribers. Accordingly, we seek a way to enable interactive transcription, whereby the machine amplifies human efforts. This paper presents a computational model for interactive transcription, supporting multiple modes of interactivity and increasing the likelihood of finding tasks that stimulate local participation. The approach also supports other applications which are useful in low resource contexts, including spoken document retrieval and language learning.