一种结合自监督表示的简单隐马尔可夫模型用于音素分割
A Simple HMM with Self-Supervised Representations for Phone Segmentation
AI总结：
本文提出一种结合自监督表示和边界特征的简单隐马尔可夫模型用于音素分割，以梅尔频谱图峰值检测为强基线，在先前方法上取得一致改进。
摘要：
尽管自监督表示近期取得了进展，无监督音素分割仍然具有挑战性。大多数方法侧重于通过自监督学习改进音素表示，希望这种改进能够迁移到音素分割任务。与近期方法相反，本文表明基于梅尔频谱图的峰值检测是一个强基线，优于许多自监督方法。基于这一发现，我们提出了一种简单的隐马尔可夫模型，该模型利用自监督表示和边界特征进行音素分割。我们的结果在先前方法上取得了一致的改进，并通过泛化公式实现了灵活的设计适配。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
