Future Directions in Technological Support for Language Documentation

Abstract

To reduce the annotation burden placed on linguistic fieldworkers, freeing up time for deeper linguistic analysis and descriptive work, the language documentation community has been working with machine learning researchers to investigate what assistive role technology can play, with promising early results. This paper describes a number of potential follow-up technical projects that we believe would be worthwhile and straightforward to do. We provide examples of the annotation tasks for computer scientists; descriptions of the technological challenges involved and the estimated level of complexity; and pointers to relevant literature. We hope providing a clear overview of what the needs are and what annotation challenges exist will help facilitate the dialogue and collaboration between computer scientists and fieldwork linguists.

From ‘Snippet-lects’ to Doculects and Dialects: Leveraging Neural Representations of Speech for Placing Audio Signals in a Language Landscape

“…An estimation of closeness between speech signals can have various applications. For computational language documentation [15,16,17,8], there could be benefit in a tool for finding closest neighbours for a newly documented language (with a view to fine-tuning extant models for the newly documented variety, for instance), bypassing the need for explicit phoneme inventories, unlike in [18]. For dialectology, a discipline that traditionally relies on spatial models based on isogloss lines [19], neural representations of audio signals for cognate words allow for calculating a phonetic-phonological distance along a dialect continuum [3]; our work explores whether cross-dialect comparison of audio snippets containing different utterances also allows for significant generalizations.…”

User-Friendly Automatic Transcription of Low-Resource Languages: Plugging ESPnet into Elpis

“…Transcription of speech is an important part of language documentation, and yet speech recognition technology has not been widely harnessed to aid linguists. Despite revolutionary progress in the performance of speech recognition systems in the past decade (Hinton et al, 2012;Hannun et al, 2014;Zeyer et al, 2018;Hadian et al, 2018;Ravanelli et al, 2019;Zhou et al, 2020), including in the application to low-resource languages (Besacier et al, 2014;Blokland et al, 2015;Lim et al, 2018;van Esch et al, 2019;Hjortnaes et al, 2020), these advances are yet to play a common role in language documentation workflows. Speech recognition software often requires effective command line skills and a reasonable understanding of the underlying modeling.…”