A Simple HMM with Self-Supervised Representations for Phone Segmentation

Autor:	Yang, Gene-Ping, Tang, Hao
Rok vydání:	2024
Předmět:	Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	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. Comment: Accepted to SLT 2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2409.09646 Zobrazit plný text záznamu View this record from Arxiv