# Sing it, Narrate it: Quality Musical Lyrics Translation

arXiv: https://arxiv.org/abs/2410.22066 · HTML: https://mlsanity.com/paper/2410.22066/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 27 references that are in the map.
- First posted on arXiv 29 Oct 2024.

## Builds on (most cited first, 10 of 10)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca](https://mlsanity.com/paper/2304.08177/) (2023)
- [Extrapolating Large Language Models to Non-English by Aligning Languages](https://mlsanity.com/paper/2308.04948/) (2023)
- [BigTranslate: Augmenting Large Language Models with Multilingual Translation Capability over 100 Languages](https://mlsanity.com/paper/2305.18098/) (2023)
- [TIM: Teaching Large Language Models to Translate with Comparison](https://mlsanity.com/paper/2307.04408/) (2023)
- [Improving Translation Faithfulness of Large Language Models via Augmenting Instructions](https://mlsanity.com/paper/2308.12674/) (2023)
- [Automatic Song Translation for Tonal Languages](https://mlsanity.com/paper/2203.13420/) (2022)
- [Songs Across Borders: Singable and Controllable Neural Lyric Translation](https://mlsanity.com/paper/2305.16816/) (2023)
- [Translate the Beauty in Songs: Jointly Learning to Align Melody and Translate Lyrics](https://mlsanity.com/paper/2303.15705/) (2023)

## Built on by (most cited first, 2 of 2)

- [LyriCAR: A Difficulty-Aware Curriculum Reinforcement Learning Framework For Controllable Lyric Translation](https://mlsanity.com/paper/2510.19967/) (2025)
- [MAVL: A Multilingual Audio-Video Lyrics Dataset for Animated Song Translation](https://mlsanity.com/paper/2505.18614/) (2025)

## Abstract (arXiv)

Translating lyrics for musicals presents unique challenges due to the need to ensure high translation quality while adhering to singability requirements such as length and rhyme. Existing song translation approaches often prioritize these singability constraints at the expense of translation quality, which is crucial for musicals. This paper aims to enhance translation quality while maintaining key singability features. Our method consists of three main components. First, we create a dataset to train reward models for the automatic evaluation of translation quality. Second, to enhance both singability and translation quality, we implement a two-stage training process with filtering techniques. Finally, we introduce an inference-time optimization framework for translating entire songs. Extensive experiments, including both automatic and human evaluations, demonstrate significant improvements over baseline methods and validate the effectiveness of each component in our approach.