Linguistic unit discovery from multi-modal inputs in unwritten languages: Summary of the "Speaking Rosetta" JSALT 2017 Workshop

TL;DR

This paper summarizes a workshop focused on computational methods for discovering linguistic units in unwritten languages using multi-modal inputs like images and translated text to replace traditional orthographic transcriptions.

Contribution

It presents a multidisciplinary approach to unsupervised linguistic unit discovery leveraging multi-modal data, advancing methods for unwritten language analysis.

Findings

Exploration of multi-modal data for linguistic unit discovery

Unsupervised methods for subword and word identification

Potential of images and translated text to replace orthography

Abstract

We summarize the accomplishments of a multi-disciplinary workshop exploring the computational and scientific issues surrounding the discovery of linguistic units (subwords and words) in a language without orthography. We study the replacement of orthographic transcriptions by images and/or translated text in a well-resourced language to help unsupervised discovery from raw speech.