Unsupervised Lexicon Learning From Speech Is Limited By Representations Rather Than Clustering

Abstract

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 --

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyslabbert2025unsupervised

Related papers

• Unsupervised Word Discovery: Boundary Detection With Clustering Vs. Dynamic Programming (2024)3.58
• An Embedded Segmental K-means Model For Unsupervised Segmentation And Clustering Of Speech (2017)0.00
• Unsupervised Word Segmentation And Lexicon Discovery Using Acoustic Word Embeddings (2016)12.10
• Multilingual And Unsupervised Subword Modeling For Zero-resource Languages (2018)7.81
• Representation Learning With Hidden Unit Clustering For Low Resource Speech Applications (2023)0.00
• Improving Unsupervised Subword Modeling Via Disentangled Speech Representation Learning And Transformation (2019)5.24
• Unsupervised Neural And Bayesian Models For Zero-resource Speech Processing (2017)0.00
• Self-supervised Language Learning From Raw Audio: Lessons From The Zero Resource Speech Challenge (2022)10.07