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.

翻译：零资源分词与聚类系统旨在无需文本标注的情况下将语音切分为类词单元。尽管已有进展，但诱导出的词汇表仍远非完美。在具有黄金词边界的理想化设置中，我们探究性能受限的主要因素是词片段的表征方式，还是将其聚类为类词类型的聚类方法。我们在英语和普通话数据上，结合多种自监督语音特征（连续/离散、帧级/词级）与不同聚类方法（K均值、层次聚类、基于图的聚类）。最佳系统采用基于动态时间规整的连续特征图聚类。更快速的替代方案则使用基于平均连续特征余弦距离的图聚类，或基于离散单元序列编辑距离的图聚类。通过隔离表征或聚类方法的对照实验，我们证明同一词类型片段间的表征变异性——而非聚类方法——是限制性能的主要因素。