Unsupervised Word Segmentation From Discrete Speech Units In Low-resource Settings
2021 · Marcely Zanon Boito, Bolaji Yusuf, Lucas Ondel, et al.
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
Authors
(none)
Tags
Stats
Related papers
- Unsupervised Word Segmentation And Lexicon Discovery Using Acoustic Word Embeddings (2016)12.10
- Unsupervised Acoustic Unit Discovery By Leveraging A Language-independent Subword Discriminative Feature Representation (2021)5.84
- An Embedded Segmental K-means Model For Unsupervised Segmentation And Clustering Of Speech (2017)0.00
- Multilingual And Unsupervised Subword Modeling For Zero-resource Languages (2018)7.81
- Unsupervised Speech Segmentation: A General Approach Using Speech Language Models (2025)2.60
- The Zero Resource Speech Challenge 2020: Discovering Discrete Subword And Word Units (2020)11.58
- Word Segmentation On Discovered Phone Units With Dynamic Programming And Self-supervised Scoring (2022)9.23
- Exploiting Cross-lingual Speaker And Phonetic Diversity For Unsupervised Subword Modeling (2019)6.77