# Sudowoodo: a Chinese Lyric Imitation System with Source Lyrics

arXiv: https://arxiv.org/abs/2308.04665 · HTML: https://mlsanity.com/paper/2308.04665/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 9 Aug 2023.

## Builds on (most cited first, 9 of 9)

- [K-BERT: Enabling Language Representation with Knowledge Graph](https://mlsanity.com/paper/1909.07606/) (2019)
- [Automatic Story Generation: Challenges and Attempts](https://mlsanity.com/paper/2102.12634/) (2021)
- [SongNet: Rigid Formats Controlled Text Generation](https://mlsanity.com/paper/2004.08022/) (2020)
- [ScriptWriter: Narrative-Guided Script Generation](https://mlsanity.com/paper/2005.10331/) (2020)
- [Youling: an AI-Assisted Lyrics Creation System](https://mlsanity.com/paper/2201.06724/) (2022)
- [A Hierarchical Attention Based Seq2seq Model for Chinese Lyrics Generation](https://mlsanity.com/paper/1906.06481/) (2019)
- [Generating Classical Chinese Poems from Vernacular Chinese](https://mlsanity.com/paper/1909.00279/) (2019)
- [Deep Poetry: A Chinese Classical Poetry Generation System](https://mlsanity.com/paper/1911.08212/) (2019)
- [Combining Learned Lyrical Structures and Vocabulary for Improved Lyric Generation](https://mlsanity.com/paper/1811.04651/) (2018)

## Built on by (most cited first, 1 of 1)

- [Train & Constrain: Phonologically Informed Tongue-Twister Generation from Topics and Paraphrases](https://mlsanity.com/paper/2403.13901/) (2024)

## Abstract (arXiv)

Lyrics generation is a well-known application in natural language generation research, with several previous studies focusing on generating accurate lyrics using precise control such as keywords, rhymes, etc. However, lyrics imitation, which involves writing new lyrics by imitating the style and content of the source lyrics, remains a challenging task due to the lack of a parallel corpus. In this paper, we introduce textbftextitSudowoodo, a Chinese lyrics imitation system that can generate new lyrics based on the text of source lyrics. To address the issue of lacking a parallel training corpus for lyrics imitation, we propose a novel framework to construct a parallel corpus based on a keyword-based lyrics model from source lyrics. Then the pairs textit(new lyrics, source lyrics) are used to train the lyrics imitation model. During the inference process, we utilize a post-processing module to filter and rank the generated lyrics, selecting the highest-quality ones. We incorporated audio information and aligned the lyrics with the audio to form the songs as a bonus. The human evaluation results show that our framework can perform better lyric imitation. Meanwhile, the textitSudowoodo system and demo video of the system is available at hrefhttps://Sudowoodo.apps-hp.danlu.netease.com/Sudowoodo and hrefhttps://youtu.be/u5BBTj1L5Mhttps://youtu.be/u5BBTj1L5M.