mlsanityData to 7 Oct 2026

Automatic Song Translation for Tonal Languages

arXiv 2203.13420 ↗First posted 25 Mar 2022cs.CL cs.AI cs.SDcited by 12

Not on the map. Why?

Abstract (arXiv)

This paper develops automatic song translation (AST) for tonal languages and addresses the unique challenge of aligning words' tones with melody of a song in addition to conveying the original meaning. We propose three criteria for effective AST -- preserving meaning, singability and intelligibility -- and design metrics for these criteria. We develop a new benchmark for English--Mandarin song translation and develop an unsupervised AST system, Guided AliGnment for Automatic Song Translation (GagaST), which combines pre-training with three decoding constraints. Both automatic and human evaluations show GagaST successfully balances semantics and singability.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 21 of its 59 references that are in the map. First posted on arXiv 25 Mar 2022.

Builds on

21 of 59 references.

References · 21

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  4. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  5. 2015A Neural Attention Model for Abstractive Sentence Summarizationcited by 394
  6. 2017A Deep Reinforced Model for Abstractive Summarizationcited by 364
  7. 2017Lexically Constrained Decoding for Sequence Generation Using Grid Beam Searchcited by 234
  8. 2016A Persona-Based Neural Conversation Modelcited by 221
  9. 2018Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translationcited by 181
  10. 2015Neural Responding Machine for Short-Text Conversationcited by 124
  11. 2018Achieving Human Parity on Automatic Chinese to English News Translationcited by 119
  12. 2020SongMASS: Automatic Song Writing with Pre-training and Alignment Constraintcited by 41
9 more
  1. 2019Controlling the Output Length of Neural Machine Translationcited by 36
  2. 2021Controllable Generation from Pre-trained Language Models via Inverse Promptingcited by 29
  3. 2020SongNet: Rigid Formats Controlled Text Generationcited by 25
  4. 2021DeepRapper: Neural Rap Generation with Rhyme and Rhythm Modelingcited by 24
  5. 2015DopeLearning: A Computational Approach to Rap Lyrics Generationcited by 17
  6. 2020Melody-Conditioned Lyrics Generation with SeqGANscited by 14
  7. 2021Task-Oriented Dialogue System as Natural Language Generationcited by 14
  8. 2018Neural Melody Composition from Lyricscited by 10
  9. 2016Chinese Song Iambics Generation with Neural Attention-based Modelcited by 9

Built on by

Cited by year

Citing papers per year: 2023: 7; 2024: 3; 2025: 2.

12 papers.

  1. 2023Songs Across Borders: Singable and Controllable Neural Lyric Translationcited by 11
  2. 2023Unsupervised Melody-to-Lyric Generationcited by 7
  3. 2023Translate the Beauty in Songs: Jointly Learning to Align Melody and Translate Lyricscited by 6
  4. 2023A Computational Evaluation Framework for Singable Lyric Translationcited by 4
  5. 2023K-pop Lyric Translation: Dataset, Analysis, and Neural-Modellingcited by 4
  6. 2024REFFLY: Melody-Constrained Lyrics Editing Modelcited by 2
  7. 2024Sing it, Narrate it: Quality Musical Lyrics Translationcited by 2
  8. 2023Joint Learning of Wording and Formatting for Singable Melody-to-Lyric Generationcited by 1
  9. 2024Song Form-aware Full-Song Text-to-Lyrics Generation with Multi-Level Granularity Syllable Count Controlcited by 1
  10. 2025LyriCAR: A Difficulty-Aware Curriculum Reinforcement Learning Framework For Controllable Lyric Translationcited by 1
  11. 2023Unsupervised Melody-Guided Lyrics Generationcited by 0
  12. 2025MAVL: A Multilingual Audio-Video Lyrics Dataset for Animated Song Translationcited by 0