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

Documenting languages helps to prevent the extinction of endangered dialects - many of which are otherwise expected to dis-
appear 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.