A Simple HMM with Self-Supervised Representations for Phone Segmentation

View a PDF of the paper titled A Simple HMM with Self-Supervised Representations for Phone Segmentation, by Gene-Ping Yang and Hao Tang

View PDF
HTML (experimental)

Abstract: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.