mlsanityData to 7 Oct 2026

Unsupervised Word Discovery: Boundary Detection with Clustering vs. Dynamic Programming

arXiv 2409.14486 ↗First posted 22 Sep 2024eess.AS cs.CL cs.SDcited by 6

Not on the map. Why?

Abstract (arXiv)

We look at the long-standing problem of segmenting unlabeled speech into word-like segments and clustering these into a lexicon. Several previous methods use a scoring model coupled with dynamic programming to find an optimal segmentation. Here we propose a much simpler strategy: we predict word boundaries using the dissimilarity between adjacent self-supervised features, then we cluster the predicted segments to construct a lexicon. For a fair comparison, we update the older ES-KMeans dynamic programming method with better features and boundary constraints. On the five-language ZeroSpeech benchmarks, our simple approach gives similar state-of-the-art results compared to the new ES-KMeans+ method, while being almost five times faster. Project webpage: https://s-malan.github.io/prom-seg-clus.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 19 of its 34 references that are in the map. First posted on arXiv 22 Sep 2024.

Builds on

19 of 34 references.

References · 19

  1. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  2. 2016Cognitive Science in the era of Artificial Intelligence: A roadmap for reverse-engineering the infant language-learnercited by 68
  3. 2024mHuBERT-147: A Compact Multilingual HuBERT Modelcited by 64
  4. 2023What Do Self-Supervised Speech Models Know About Words?cited by 62
  5. 2021A Comparison of Discrete and Soft Speech Units for Improved Voice Conversioncited by 61
  6. 2020The Zero Resource Speech Challenge 2020: Discovering discrete subword and word unitscited by 39
  7. 2022Word Discovery in Visually Grounded, Self-Supervised Speech Modelscited by 37
  8. 2021Segmental Contrastive Predictive Coding for Unsupervised Word Segmentationcited by 32
  9. 2017An embedded segmental K-means model for unsupervised segmentation and clustering of speechcited by 31
  10. 2016A segmental framework for fully-unsupervised large-vocabulary speech recognitioncited by 27
  11. 2022Word Segmentation on Discovered Phone Units with Dynamic Programming and Self-Supervised Scoringcited by 24
  12. 2022Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Speech Modelscited by 21
7 more
  1. 2021Contrastive prediction strategies for unsupervised segmentation and categorization of phonemes and wordscited by 18
  2. 2018Segmental Audio Word2Vec: Representing Utterances as Sequences of Vectors with Applications in Spoken Term Detectioncited by 17
  3. 2022DP-Parse: Finding Word Boundaries from Raw Speech with an Instance Lexiconcited by 12
  4. 2024Spoken-Term Discovery using Discrete Speech Unitscited by 8
  5. 2021Double Articulation Analyzer with Prosody for Unsupervised Word and Phoneme Discoverycited by 7
  6. 2023Unsupervised Word Segmentation Using Temporal Gradient Pseudo-Labelscited by 7
  7. 2024Revisiting speech segmentation and lexicon learning with better featurescited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2026ZeroSyl: Simple Zero-Resource Syllable Tokenization for Spoken Language Modelingcited by 5
  2. 2025Should Top-Down Clustering Affect Boundaries in Unsupervised Word Discovery?cited by 4
  3. 2025Unsupervised lexicon learning from speech is limited by representations rather than clusteringcited by 4
  4. 2026Revisiting Lexicon Evaluation in Unsupervised Word Discoverycited by 1
  5. 2026Recovering the Zipfian Distribution in Unsupervised Term Discoverycited by 0
  6. 2026Do speech foundation models really learn words?cited by 0