A Computational Evaluation Framework for Singable Lyric Translation

TL;DR

This paper introduces a computational framework with four metrics to evaluate the quality of singable lyric translation, considering musical, linguistic, and cultural factors, supported by a multilingual dataset.

Contribution

It presents a novel, integrated evaluation framework for singable lyric translation, combining multiple dimensions and providing a dataset for validation.

Findings

The framework effectively measures syllable, phoneme, musical, and semantic similarities.

Singable lyrics show distinct patterns compared to non-singable lyrics.

The dataset enables detailed comparative analysis of multilingual lyrics.

Abstract

Lyric translation plays a pivotal role in amplifying the global resonance of music, bridging cultural divides, and fostering universal connections. Translating lyrics, unlike conventional translation tasks, requires a delicate balance between singability and semantics. In this paper, we present a computational framework for the quantitative evaluation of singable lyric translation, which seamlessly integrates musical, linguistic, and cultural dimensions of lyrics. Our comprehensive framework consists of four metrics that measure syllable count distance, phoneme repetition similarity, musical structure distance, and semantic similarity. To substantiate the efficacy of our framework, we collected a singable lyrics dataset, which precisely aligns English, Japanese, and Korean lyrics on a line-by-line and section-by-section basis, and conducted a comparative analysis between singable and non-singable lyrics. Our multidisciplinary approach provides insights into the key components that underlie the art of lyric translation and establishes a solid groundwork for the future of computational lyric translation assessment.