Enabling Interactive Transcription in an Indigenous Community

TL;DR

This paper introduces a new transcription workflow that combines spoken term detection and human-in-the-loop methods to bootstrap transcription of endangered languages with minimal initial data.

Contribution

It presents a novel approach for early-stage transcription of endangered languages using minimal resources and a pilot experiment demonstrating its effectiveness.

Findings

Bootstrapping transcription from few isolated words is feasible.

The workflow improves transcription accuracy in low-resource scenarios.

Early-stage transcription can be initiated with minimal initial data.

Abstract

We propose a novel transcription workflow which combines spoken term detection and human-in-the-loop, together with a pilot experiment. This work is grounded in an almost zero-resource scenario where only a few terms have so far been identified, involving two endangered languages. We show that in the early stages of transcription, when the available data is insufficient to train a robust ASR system, it is possible to take advantage of the transcription of a small number of isolated words in order to bootstrap the transcription of a speech collection.