Saved in:
Bibliographic Details
Main Authors: Yang, Gene-Ping, Tang, Hao
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.09646
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917780131938304
author Yang, Gene-Ping
Tang, Hao
author_facet Yang, Gene-Ping
Tang, Hao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2409_09646
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Simple HMM with Self-Supervised Representations for Phone Segmentation
Yang, Gene-Ping
Tang, Hao
Computation and Language
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.
title A Simple HMM with Self-Supervised Representations for Phone Segmentation
topic Computation and Language
url https://arxiv.org/abs/2409.09646