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

• URL: http://arxiv.org/abs/2510.09225v1
• Date: Fri, 10 Oct 2025 10:12:11 GMT
• Title: Unsupervised lexicon learning from speech is limited by representations rather than clustering
• Abstract summary: Zero-resource word segmentation and clustering systems aim to tokenise speech into word-like units without access to text labels.<n>We ask whether performance is limited by the representation of word segments, or by the clustering methods that group them into word-like types.<n>We combine a range of self-supervised speech features with different clustering methods (K-means, hierarchical, graph-based) on English and Mandarin data.
• Score: 15.386356718833555
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 -- rather than clustering -- is the primary factor limiting performance.

Related papers

• Cluster-Aware Prompt Ensemble Learning for Few-Shot Vision-Language Model Adaptation [40.60703048681749]
  Vision-language models (VLMs) such as CLIP achieve zero-shot transfer across various tasks by pre-training on numerous image-text pairs.<n>Despite being effective, conventional prompt ensembling that averages textual features of context prompts often yields suboptimal results.<n>We propose the Cluster-Aware Prompt Ensemble Learning framework, which preserves the cluster nature of context prompts.
  arXiv  Detail & Related papers  (2025-10-10T20:58:43Z)
• Should Top-Down Clustering Affect Boundaries in Unsupervised Word Discovery? [22.044042563954378]
  We investigate the problem of segmenting unlabeled speech into word-like units and clustering these to create a lexicon.<n>Top-down methods incorporate information from the clustered words to inform boundary selection.<n>We show that the top-down influence of ES-KMeans can be beneficial, but in many cases the simple bottom-up method performs just as well.
  arXiv  Detail & Related papers  (2025-07-25T12:19:16Z)
• Moving Past Single Metrics: Exploring Short-Text Clustering Across Multiple Resolutions [0.0]
  The study focuses on short-text clustering, involving 30,000 political Twitter bios.<n>A metric of proportional stability is introduced to uncover the stability of specific clusters between cluster resolutions.<n>The results are visualised using Sankey diagrams to provide an interrogative tool for understanding the nature of the dataset.
  arXiv  Detail & Related papers  (2025-02-24T10:17:09Z)
• Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment [53.2701026843921]
  Large-scale pre-trained Vision Language Models (VLMs) have proven effective for zero-shot classification. In this paper, we aim at a more challenging setting, Realistic Zero-Shot Classification, which assumes no annotation but instead a broad vocabulary. We propose the Self Structural Semantic Alignment (S3A) framework, which extracts structural semantic information from unlabeled data while simultaneously self-learning.
  arXiv  Detail & Related papers  (2023-08-24T17:56:46Z)
• Reinforcement Graph Clustering with Unknown Cluster Number [91.4861135742095]
  We propose a new deep graph clustering method termed Reinforcement Graph Clustering. In our proposed method, cluster number determination and unsupervised representation learning are unified into a uniform framework. In order to conduct feedback actions, the clustering-oriented reward function is proposed to enhance the cohesion of the same clusters and separate the different clusters.
  arXiv  Detail & Related papers  (2023-08-13T18:12:28Z)
• Self-supervised Contrastive Attributed Graph Clustering [110.52694943592974]
  We propose a novel attributed graph clustering network, namely Self-supervised Contrastive Attributed Graph Clustering (SCAGC) In SCAGC, by leveraging inaccurate clustering labels, a self-supervised contrastive loss, are designed for node representation learning. For the OOS nodes, SCAGC can directly calculate their clustering labels.
  arXiv  Detail & Related papers  (2021-10-15T03:25:28Z)
• Unsupervised Visual Representation Learning by Online Constrained K-Means [44.38989920488318]
  Cluster discrimination is an effective pretext task for unsupervised representation learning. We propose a novel clustering-based pretext task with online textbfConstrained textbfK-mtextbfeans (textbfCoKe) Our online assignment method has a theoretical guarantee to approach the global optimum.
  arXiv  Detail & Related papers  (2021-05-24T20:38:32Z)
• Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation [96.67525775629444]
  Action segmentation refers to inferring boundaries of semantically consistent visual concepts in videos. We present a fully automatic and unsupervised approach for segmenting actions in a video that does not require any training. Our proposal is an effective temporally-weighted hierarchical clustering algorithm that can group semantically consistent frames of the video.
  arXiv  Detail & Related papers  (2021-03-20T23:30:01Z)
• Predictive K-means with local models [0.028675177318965035]
  Predictive clustering seeks to obtain the best of the two worlds. We present two new algorithms using this technique and show on a variety of data sets that they are competitive for prediction performance.
  arXiv  Detail & Related papers  (2020-12-16T10:49:36Z)
• Text Information Aggregation with Centrality Attention [86.91922440508576]
  We propose a new way of obtaining aggregation weights, called eigen-centrality self-attention. We build a fully-connected graph for all the words in a sentence, then compute the eigen-centrality as the attention score of each word.
  arXiv  Detail & Related papers  (2020-11-16T13:08:48Z)
• Structured Graph Learning for Clustering and Semi-supervised Classification [74.35376212789132]
  We propose a graph learning framework to preserve both the local and global structure of data. Our method uses the self-expressiveness of samples to capture the global structure and adaptive neighbor approach to respect the local structure. Our model is equivalent to a combination of kernel k-means and k-means methods under certain condition.
  arXiv  Detail & Related papers  (2020-08-31T08:41:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.