Unsupervised lexicon learning from speech is limited by representations rather than clustering

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Slabbert, Danel, Malan, Simon, Kamper, Herman
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914282546921472
author Slabbert, Danel
Malan, Simon
Kamper, Herman
author_facet Slabbert, Danel
Malan, Simon
Kamper, Herman
contents Zero-resource word segmentation and clustering systems aim to tokenise speech into word-like units without access to text labels. Despite progress, the induced lexicons are still far from perfect. In an idealised setting with gold word boundaries, we ask whether performance is limited by the representation of word segments, or by the clustering methods that group them into word-like types. We combine a range of self-supervised speech features (continuous/discrete, frame/word-level) with different clustering methods (K-means, hierarchical, graph-based) on English and Mandarin data. The best system uses graph clustering with dynamic time warping on continuous features. Faster alternatives use graph clustering with cosine distance on averaged continuous features or edit distance on discrete unit sequences. Through controlled experiments that isolate either the representations or the clustering method, we demonstrate that representation variability across segments of the same word type -- rather than clustering -- is the primary factor limiting performance.
format Preprint
id arxiv_https___arxiv_org_abs_2510_09225
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Unsupervised lexicon learning from speech is limited by representations rather than clustering
Slabbert, Danel
Malan, Simon
Kamper, Herman
Audio and Speech Processing
Computation and Language
Sound
Zero-resource word segmentation and clustering systems aim to tokenise speech into word-like units without access to text labels. Despite progress, the induced lexicons are still far from perfect. In an idealised setting with gold word boundaries, we ask whether performance is limited by the representation of word segments, or by the clustering methods that group them into word-like types. We combine a range of self-supervised speech features (continuous/discrete, frame/word-level) with different clustering methods (K-means, hierarchical, graph-based) on English and Mandarin data. The best system uses graph clustering with dynamic time warping on continuous features. Faster alternatives use graph clustering with cosine distance on averaged continuous features or edit distance on discrete unit sequences. Through controlled experiments that isolate either the representations or the clustering method, we demonstrate that representation variability across segments of the same word type -- rather than clustering -- is the primary factor limiting performance.
title Unsupervised lexicon learning from speech is limited by representations rather than clustering
topic Audio and Speech Processing
Computation and Language
Sound
url https://arxiv.org/abs/2510.09225