mlsanityData to 14 Oct 2026

DP-Parse: Finding Word Boundaries from Raw Speech with an Instance Lexicon

arXiv 2206.11332 ↗First posted 22 Jun 2022cs.CLcited by 12

Not on the map. Why?

Abstract (arXiv)

Finding word boundaries in continuous speech is challenging as there is little or no equivalent of a 'space' delimiter between words. Popular Bayesian non-parametric models for text segmentation use a Dirichlet process to jointly segment sentences and build a lexicon of word types. We introduce DP-Parse, which uses similar principles but only relies on an instance lexicon of word tokens, avoiding the clustering errors that arise with a lexicon of word types. On the Zero Resource Speech Benchmark 2017, our model sets a new speech segmentation state-of-the-art in 5 languages. The algorithm monotonically improves with better input representations, achieving yet higher scores when fed with weakly supervised inputs. Despite lacking a type lexicon, DP-Parse can be pipelined to a language model and learn semantic and syntactic representations as assessed by a new spoken word embedding benchmark.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 27 of its 57 references that are in the map. First posted on arXiv 22 Jun 2022.

Builds on

27 of 57 references.

References · 27

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  3. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  4. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  5. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  6. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  7. 2021Generative Spoken Language Modeling from Raw Audiocited by 340
  8. 2019pyannote.audio: neural building blocks for speaker diarizationcited by 181
  9. 2020The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modelingcited by 101
  10. 2018Speech2Vec: A Sequence-to-Sequence Framework for Learning Word Embeddings from Speechcited by 52
  11. 2017The Zero Resource Speech Challenge 2017cited by 45
  12. 2020The Zero Resource Speech Challenge 2020: Discovering discrete subword and word unitscited by 39
15 more
  1. 2021Segmental Contrastive Predictive Coding for Unsupervised Word Segmentationcited by 32
  2. 2017An embedded segmental K-means model for unsupervised segmentation and clustering of speechcited by 31
  3. 2018Truly unsupervised acoustic word embeddings using weak top-down constraints in encoder-decoder modelscited by 29
  4. 2016A segmental framework for fully-unsupervised large-vocabulary speech recognitioncited by 27
  5. 2016Discriminative Acoustic Word Embeddings: Recurrent Neural Network-Based Approachescited by 25
  6. 2020Towards unsupervised phone and word segmentation using self-supervised vector-quantized neural networkscited by 24
  7. 2022Word Segmentation on Discovered Phone Units with Dynamic Programming and Self-Supervised Scoringcited by 24
  8. 2020Evaluating the reliability of acoustic speech embeddingscited by 21
  9. 2021Acoustic word embeddings for zero-resource languages using self-supervised contrastive learning and multilingual adaptationcited by 19
  10. 2021Contrastive prediction strategies for unsupervised segmentation and categorization of phonemes and wordscited by 18
  11. 2020Multilingual Jointly Trained Acoustic and Written Word Embeddingscited by 16
  12. 2020Self-Expressing Autoencoders for Unsupervised Spoken Term Discoverycited by 12
  13. 2020Acoustic span embeddings for multilingual query-by-example searchcited by 7
  14. 2022Speech Sequence Embeddings using Nearest Neighbors Contrastive Learningcited by 7
  15. 2018Sampling strategies in Siamese Networks for unsupervised speech representation learningcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 4; 2025: 3; 2026: 2.

12 papers.

  1. 2023What Do Self-Supervised Speech Models Know About Words?cited by 64
  2. 2023Syllable Discovery and Cross-Lingual Generalization in a Visually Grounded, Self-Supervised Speech Modelcited by 11
  3. 2024From Babble to Words: Pre-Training Language Models on Continuous Streams of Phonemescited by 11
  4. 2024Unsupervised Word Discovery: Boundary Detection with Clustering vs. Dynamic Programmingcited by 7
  5. 2025Should Top-Down Clustering Affect Boundaries in Unsupervised Word Discovery?cited by 4
  6. 2025Unsupervised lexicon learning from speech is limited by representations rather than clusteringcited by 4
  7. 2024Revisiting speech segmentation and lexicon learning with better featurescited by 3
  8. 2023XLS-R fine-tuning on noisy word boundaries for unsupervised speech segmentation into wordscited by 1
  9. 2024Towards Unsupervised Speech Recognition Without Pronunciation Modelscited by 1
  10. 2026Tracking the emergence of linguistic structure in self-supervised models learning from speechcited by 1
  11. 2025Discriminating Form and Meaning in Multilingual Models with Minimal-Pair ABX Taskscited by 0
  12. 2026Recovering the Zipfian Distribution in Unsupervised Term Discoverycited by 0