mlsanityData to 14 Oct 2026

Unsupervised Speech Recognition with N-Skipgram and Positional Unigram Matching

arXiv 2310.02382 ↗First posted 3 Oct 2023cs.CL cs.SD eess.AScited by 5

Not on the map. Why?

Abstract (arXiv)

Training unsupervised speech recognition systems presents challenges due to GAN-associated instability, misalignment between speech and text, and significant memory demands. To tackle these challenges, we introduce a novel ASR system, ESPUM. This system harnesses the power of lower-order N-skipgrams (up to N=3) combined with positional unigram statistics gathered from a small batch of samples. Evaluated on the TIMIT benchmark, our model showcases competitive performance in ASR and phoneme segmentation tasks. Access our publicly available code at https://github.com/lwang114/GraphUnsupASR.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 17 of its 21 references that are in the map. First posted on arXiv 3 Oct 2023.

Builds on

17 of 21 references.

References · 17

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  3. 2019Libri-Light: A Benchmark for ASR with Limited or No Supervisioncited by 467
  4. 2021Unsupervised Speech Recognitioncited by 148
  5. 2022Towards End-to-end Unsupervised Speech Recognitioncited by 45
  6. 2020Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentationcited by 43
  7. 2021Segmental Contrastive Predictive Coding for Unsupervised Word Segmentationcited by 32
  8. 2018Completely Unsupervised Phoneme Recognition by Adversarially Learning Mapping Relationships from Audio Embeddingscited by 22
  9. 2018Unsupervised Speech Recognition via Segmental Empirical Output Distribution Matchingcited by 20
  10. 2022Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognitioncited by 14
  11. 2022Simple and Effective Unsupervised Speech Synthesiscited by 12
  12. 2022Simple and Effective Unsupervised Speech Translationcited by 12
5 more
  1. 2021Analyzing the Robustness of Unsupervised Speech Recognitioncited by 11
  2. 2022Phoneme Segmentation Using Self-Supervised Speech Modelscited by 11
  3. 2017Gate Activation Signal Analysis for Gated Recurrent Neural Networks and Its Correlation with Phoneme Boundariescited by 9
  4. 2023Improving Cascaded Unsupervised Speech Translation with Denoising Back-translationcited by 5
  5. 2023A Theory of Unsupervised Speech Recognitioncited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 1; 2026: 1.

5 papers.

  1. 2024Whistle: Data-Efficient Multilingual and Crosslingual Speech Recognition via Weakly Phonetic Supervisioncited by 17
  2. 2024REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASRcited by 4
  3. 2025Towards Unsupervised Speech Recognition at the Syllable-Levelcited by 2
  4. 2024Towards Unsupervised Speech Recognition Without Pronunciation Modelscited by 1
  5. 2026Sequence-Level Unsupervised Training in Speech Recognition: A Theoretical Studycited by 0