Youling: an AI-assisted Lyrics Creation System

  title={Youling: an AI-assisted Lyrics Creation System},
  author={Rongsheng Zhang and Xiao-Xi Mao and Le Li and Lin Jiang and Lin Chen and Zhiwei Hu and Yadong Xi and Changjie Fan and Minlie Huang},
Recently, a variety of neural models have been proposed for lyrics generation. However, most previous work completes the generation process in a single pass with little human intervention. We believe that lyrics creation is a creative process with human intelligence centered. AI should play a role as an assistant in the lyrics creation process, where human interactions are crucial for high-quality creation. This paper demonstrates Youling, an AI-assisted lyrics creation system, designed to… 

Figures from this paper

ChipSong: A Controllable Lyric Generation System for Chinese Popular Song
ChipSong is proposed, which is an assisted lyric generation system built based on a Transformer-based autoregressive language model architecture, and generates controlled lyric paragraphs fit for musical short-video display purpose, by designing a novel Begin-Internal-End word-granularity embedding sequence.
QiuNiu: A Chinese Lyrics Generation System with Passage-Level Input
The QiuNiu is demonstrated, a Chinese lyrics generation system which is conditioned on passage-level text rather than a few attributes or keywords, and adopts a two-step process to finetune the model for better alignment between passage- level text and lyrics.
AI-Lyricist: Generating Music and Vocabulary Constrained Lyrics
AI-Lyricist is proposed, a system to generate novel yet meaningful lyrics given a required vocabulary and a MIDI file as inputs, and its superior performance against the state-of-the-art for the proposed tasks is shown.
Lingxi: A Diversity-aware Chinese Modern Poetry Generation System
Lingxi, a diversity-aware Chinese modern poetry generation system, is presented and a semantic-similaritybased rejection sampling algorithm is proposed, which creates longer and more informative context on the basis of the short input poetry title while maintaining high semantic similarity to the title, alleviating the off-topic issue.
KuiLeiXi: a Chinese Open-Ended Text Adventure Game
In KuiLeiXi, players need to interact with the AI until the pre-determined plot goals are reached, and players have a stronger incentive to explore ways to reach plot goals, while the AI’s abilities are not abused to generate harmful contents.


Combining Learned Lyrical Structures and Vocabulary for Improved Lyric Generation
This work proposes a mechanism for combining two separately trained language models into a framework that is able to produce output respecting the desired song structure, while providing a richness and diversity of vocabulary that renders it more creatively appealing.
Generation of Hip-Hop Lyrics with Hierarchical Modeling and Conditional Templates
A simple yet effective mechanism to extract and apply conditional templates from text snippets is developed, and it is shown that these templates significantly improve the quality and realism of the generated snippets.
GhostWriter: Using an LSTM for Automatic Rap Lyric Generation
This paper demonstrates the effectiveness of a Long Short-Term Memory language model in the initial efforts to generate unconstrained rap lyrics, which produces better “ghostwritten” lyrics than a baseline model.
Rigid Formats Controlled Text Generation
A simple and elegant framework named SongNet is proposed to tackle text generation based on the predefined rigid formats of classical Chinese poetry, which generates significantly better results in terms of both automatic metrics and the human evaluation.
A Melody-Conditioned Lyrics Language Model
A novel, data-driven language model that produces entire lyrics for a given input melody conditioned on a featurized melody, and experimental results show that the proposed model generates fluent lyrics while maintaining the compatibility between boundaries of lyrics and melody structures.
A Syllable-Structured, Contextually-Based Conditionally Generation of Chinese Lyrics
This work proposes to interpret lyrics-melody alignments as syllable structural information and use a multi-channel sequence-to-sequence model with considering both phrasal structures and semantics and demonstrates the effectiveness of the proposed lyrics generation model.
Evaluating Creative Language Generation: The Case of Rap Lyric Ghostwriting
A novel evaluation methodology is developed that addresses several complementary aspects of this task, ghostwriting of rap lyrics, and illustrates how such evaluation can be used to meaning fully analyze system performance.
iComposer: An Automatic Songwriting System for Chinese Popular Music
iComposer is an interactive web-based songwriting system designed to assist human creators by greatly simplifying music production by using sequence-to-sequence models to predict melody, rhythm, and lyrics, respectively.
Creative GANs for generating poems, lyrics, and metaphors
This work uses a Generative Adversarial Network framework to alleviate the problem of creative text generation, where multiple outputs are possible and originality and uniqueness are encouraged, and reports better performance of the objective function over other generative models.
A Hierarchical Attention Based Seq2seq Model for Chinese Lyrics Generation
Results of automatic and human evaluations demonstrate that the proposed hierarchical attention based Seq2Seq (Sequence-to-Sequence) model is able to compose complete Chinese lyrics with one united topic constraint.