Self-supervised contrastive learning for unsupervised phoneme segmentation

Felix Kreuk*, Joseph Keshet, Yossi Adi

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

36 Scopus citations


We propose a self-supervised representation learning model for the task of unsupervised phoneme boundary detection. The model is a convolutional neural network that operates directly on the raw waveform. It is optimized to identify spectral changes in the signal using the Noise-Contrastive Estimation principle. At test time, a peak detection algorithm is applied over the model outputs to produce the final boundaries. As such, the proposed model is trained in a fully unsupervised manner with no manual annotations in the form of target boundaries nor phonetic transcriptions. We compare the proposed approach to several unsupervised baselines using both TIMIT and Buckeye corpora. Results suggest that our approach surpasses the baseline models and reaches state-of-the-art performance on both data sets. Furthermore, we experimented with expanding the training set with additional examples from the Librispeech corpus. We evaluated the resulting model on distributions and languages that were not seen during the training phase (English, Hebrew and German) and showed that utilizing additional untranscribed data is beneficial for model performance. Our implementation is available at:

Original languageAmerican English
Pages (from-to)3700-3704
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
StatePublished - 2020
Externally publishedYes
Event21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020 - Shanghai, China
Duration: 25 Oct 202029 Oct 2020

Bibliographical note

Publisher Copyright:
© 2020 ISCA


  • Contrastive Noise Estimation
  • Self-Supervised Learning
  • Unsupervised Phoneme Segmentation


Dive into the research topics of 'Self-supervised contrastive learning for unsupervised phoneme segmentation'. Together they form a unique fingerprint.

Cite this