Deep Supervised Contrastive Learning of Pitch Contours for Robust Pitch Accent Classification in Seoul Korean

TL;DR

This paper introduces Dual-Glob, a deep contrastive learning framework that improves classification of pitch accents in Seoul Korean by capturing holistic $F_0$ contour shapes, supported by a new large-scale annotated dataset.

Contribution

It presents the first large-scale benchmark dataset and a novel deep contrastive learning method for robust pitch accent classification in Seoul Korean.

Findings

Dual-Glob achieves 77.75% accuracy and 51.54% F1-score, outperforming baseline models.

The approach effectively captures structural features of $F_0$ contours.

The dataset contains 10,093 manually annotated Accentual Phrases.

Abstract

The intonational structure of Seoul Korean has been defined with discrete tonal categories within the Autosegmental-Metrical model of intonational phonology. However, it is challenging to map continuous $F_0$ contours to these invariant categories due to variable $F_0$ realizations in real-world speech. Our paper proposes Dual-Glob, a deep supervised contrastive learning framework to robustly classify fine-grained pitch accent patterns in Seoul Korean. Unlike conventional local predictive models, our approach captures holistic $F_0$ contour shapes by enforcing structural consistency between clean and augmented views in a shared latent space. To this aim, we introduce the first large-scale benchmark dataset, consisting of manually annotated 10,093 Accentual Phrases in Seoul Korean. Experimental results show that our Dual-Glob significantly outperforms strong baseline models with state-of-the-art accuracy (77.75%) and F1-score (51.54%). Therefore, our work supports AM-based intonational phonology using data-driven methodology, showing that deep contrastive learning effectively captures holistic structural features of continuous $F_0$ contours.