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.
@article{arxiv.2409.09646,
title = {A Simple HMM with Self-Supervised Representations for Phone Segmentation},
author = {Gene-Ping Yang and Hao Tang},
journal= {arXiv preprint arXiv:2409.09646},
year = {2024}
}