Sudowoodo: a Chinese Lyric Imitation System with Source Lyrics

TL;DR

Sudowoodo is a novel Chinese lyrics imitation system that constructs a parallel corpus from source lyrics using a keyword-based model, enabling high-quality lyric generation that mimics style and content.

Contribution

The paper introduces a new framework for lyrics imitation that overcomes the lack of parallel data by constructing a corpus from source lyrics, incorporating audio alignment, and applying post-processing for quality.

Findings

Human evaluation shows improved imitation quality

System effectively incorporates audio and lyrics alignment

Demonstrates practical application with a demo and online system

Abstract

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 \textbf{\textit{Sudowoodo}}, 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 \textit{Sudowoodo} system and demo video of the system is available at \href{https://Sudowoodo.apps-hp.danlu.netease.com/}{Sudowoodo} and \href{https://youtu.be/u5BBT_j1L5M}{https://youtu.be/u5BBT\_j1L5M}.