Unsupervised Word Segmentation from Discrete Speech Units in Low-Resource Settings

TL;DR

This paper compares Bayesian and neural unsupervised speech discretization models for word segmentation in low-resource languages, finding Bayesian models more effective for producing useful discrete units for downstream tasks.

Contribution

It provides a comparative analysis of five speech discretization models and demonstrates the effectiveness of Bayesian approaches in low-resource unsupervised word segmentation.

Findings

Neural models are less effective in low-resource settings.

Bayesian models produce higher quality discrete speech units.

Best results achieved with Bayesian models that generate compressed representations.

Abstract

Documenting languages helps to prevent the extinction of endangered dialects, many of which are otherwise expected to disappear by the end of the century. When documenting oral languages, unsupervised word segmentation (UWS) from speech is a useful, yet challenging, task. It consists in producing time-stamps for slicing utterances into smaller segments corresponding to words, being performed from phonetic transcriptions, or in the absence of these, from the output of unsupervised speech discretization models. These discretization models are trained using raw speech only, producing discrete speech units that can be applied for downstream (text-based) tasks. In this paper we compare five of these models: three Bayesian and two neural approaches, with regards to the exploitability of the produced units for UWS. For the UWS task, we experiment with two models, using as our target language the Mboshi (Bantu C25), an unwritten language from Congo-Brazzaville. Additionally, we report results for Finnish, Hungarian, Romanian and Russian in equally low-resource settings, using only 4 hours of speech. Our results suggest that neural models for speech discretization are difficult to exploit in our setting, and that it might be necessary to adapt them to limit sequence length. We obtain our best UWS results by using Bayesian models that produce high quality, yet compressed, discrete representations of the input speech signal.