A Simple HMM with Self-Supervised Representations for Phone Segmentation
Not on the map. Why?
Abstract (arXiv)
Despite the recent advance in self-supervised representations, unsupervised phonetic segmentation remains challenging. Most approaches focus on improving phonetic representations with self-supervised learning, with the hope that the improvement can transfer to phonetic segmentation. In this paper, contrary to recent approaches, we show that peak detection on Mel spectrograms is a strong baseline, better than many self-supervised approaches. Based on this finding, we propose a simple hidden Markov model that uses self-supervised representations and features at the boundaries for phone segmentation. Our results demonstrate consistent improvements over previous approaches, with a generalized formulation allowing versatile design adaptations.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 15 of its 38 references that are in the map. First posted on arXiv 15 Sep 2024.
Builds on
15 of 38 references.
References · 15
- 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
- 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
- 2021Layer-wise Analysis of a Self-supervised Speech Representation Modelcited by 293
- 2020Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentationcited by 43
- 2017An embedded segmental K-means model for unsupervised segmentation and clustering of speechcited by 31
- 2016A segmental framework for fully-unsupervised large-vocabulary speech recognitioncited by 27
- 2020Towards unsupervised phone and word segmentation using self-supervised vector-quantized neural networkscited by 24
- 2022Word Segmentation on Discovered Phone Units with Dynamic Programming and Self-Supervised Scoringcited by 24
- 2021Contrastive prediction strategies for unsupervised segmentation and categorization of phonemes and wordscited by 18
- 2021Aligned Contrastive Predictive Codingcited by 15
- 2021Unsupervised Speech Segmentation and Variable Rate Representation Learning using Segmental Contrastive Predictive Codingcited by 14
- 2022Phoneme Segmentation Using Self-Supervised Speech Modelscited by 11
3 more
- 2024A predictive learning model can simulate temporal dynamics and context effects found in neural representations of continuous speechcited by 2
- 2022Learning Dependencies of Discrete Speech Representations with Neural Hidden Markov Modelscited by 1
- 2023Towards Matching Phones and Speech Representationscited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.