Skip to content
conftrace_
2026 EMNLP EMNLP 2026

IPA-Verified Singable Lyrics Translation with LLM Agents

AbstractTranslating song lyrics while preserving singability requires satisfying musical constraints, including syllable counts, rhyme schemes, and syllable patterns, that standard machine translation ignores. We present a framework that exposes IPA-based phonetic analysis as a suite of composable Agent Skills, each defined by a natural-language description plus deterministic verification scripts that the orchestrating LLM invokes on demand. The agent extracts constraints from source lyrics, then translates through a multi-phase process, calling skills to verify syllable counts and rhyme and iteratively refine syllable-count mismatches. We formalize the three musical constraints, describe the IPA skill suite and agent architecture, and propose three evaluation metrics: Syllable Error Rate (SER), Syllable Count Relative Error (SCRE), and Adjusted Rand Index (ARI). Experiments across three frontier orchestrators, with component ablations, confirm that tool-verified translation dramatically improves constraint satisfaction and preserves rhyme structure substantially better than a supervised baseline, while requiring no task-specific training and no parallel corpora, and transferring to Spanish and Japanese targets with only a small language-specific syllabification adapter.

More from EMNLP 2026

All EMNLP 2026 papers →