A Syllable-structured, Contextually-based Conditionally Generation Of Chinese Lyrics

Abstract

This paper presents a novel, syllable-structured Chinese lyrics generation model given a piece of original melody. Most previously reported lyrics generation models fail to include the relationship between lyrics and melody. In this work, we propose 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. Two different RNN encoders are applied, one of which is for encoding syllable structures while the other for semantic encoding with contextual sentences or input keywords. Moreover, a large Chinese lyrics corpus for model training is leveraged. With automatic and human evaluations, results demonstrate the effectiveness of our proposed lyrics generation model. To the best of our knowledge, there is few previous reports on lyrics generation considering both music and linguistic perspectives.

Stats

• citations8
• S2 citations—
• github stars0
• HF likes0
• heat score7.16
• arxiv keylu2019a

Related papers

• Diverse Melody Generation From Chinese Lyrics Via Mutual Information Maximization (2020)0.00
• Neural Melody Composition From Lyrics (2018)9.59
• Modeling The Rhythm From Lyrics For Melody Generation Of Pop Song (2023)0.00
• Unsupervised Melody-to-lyric Generation (2023)0.00
• Melody-conditioned Lyrics Generation With Seqgans (2020)7.50
• Conditional LSTM-GAN For Melody Generation From Lyrics (2019)14.69
• Songglm: Lyric-to-melody Generation With 2D Alignment Encoding And Multi-task Pre-training (2024)3.58
• Joint Learning Of Wording And Formatting For Singable Melody-to-lyric Generation (2023)0.00