3 papers
cs.CL2026
ZeroSyl: Simple Zero-Resource Syllable Tokenization for Spoken Language Modeling
Nicol Visser, Simon Malan, Danel Slabbert +1
Pure speech language models aim to learn language directly from raw audio without textual resources. A key challenge is that discrete tokens from self-supervised speech encoders re…
eess.AS2026
Recovering the Zipfian Distribution in Unsupervised Term Discovery
Danel Slabbert, Simon Malan, Herman Kamper
Unsupervised term discovery involves segmenting unlabelled speech into word- or syllable-like units and clustering these into a lexicon of candidate types. True lexicons follow a Z…
eess.AS2026
Revisiting Lexicon Evaluation in Unsupervised Word Discovery
Simon Malan, Danel Slabbert, Herman Kamper
Building a lexicon from discovered word-like units is a central goal in zero-resource speech processing. But do our evaluations provide a trustworthy indication of lexicon quality?…