DeepAI AI Chat
Log In Sign Up

SongMASS: Automatic Song Writing with Pre-training and Alignment Constraint

by   Zhonghao Sheng, et al.
Nanjing University
Zhejiang University
Peking University

Automatic song writing aims to compose a song (lyric and/or melody) by machine, which is an interesting topic in both academia and industry. In automatic song writing, lyric-to-melody generation and melody-to-lyric generation are two important tasks, both of which usually suffer from the following challenges: 1) the paired lyric and melody data are limited, which affects the generation quality of the two tasks, considering a lot of paired training data are needed due to the weak correlation between lyric and melody; 2) Strict alignments are required between lyric and melody, which relies on specific alignment modeling. In this paper, we propose SongMASS to address the above challenges, which leverages masked sequence to sequence (MASS) pre-training and attention based alignment modeling for lyric-to-melody and melody-to-lyric generation. Specifically, 1) we extend the original sentence-level MASS pre-training to song level to better capture long contextual information in music, and use a separate encoder and decoder for each modality (lyric or melody); 2) we leverage sentence-level attention mask and token-level attention constraint during training to enhance the alignment between lyric and melody. During inference, we use a dynamic programming strategy to obtain the alignment between each word/syllable in lyric and note in melody. We pre-train SongMASS on unpaired lyric and melody datasets, and both objective and subjective evaluations demonstrate that SongMASS generates lyric and melody with significantly better quality than the baseline method without pre-training or alignment constraint.


page 1

page 2

page 3

page 4


MASS: Masked Sequence to Sequence Pre-training for Language Generation

Pre-training and fine-tuning, e.g., BERT, have achieved great success in...

ERNIE-GEN: An Enhanced Multi-Flow Pre-training and Fine-tuning Framework for Natural Language Generation

Current pre-training works in natural language generation pay little att...

Unsupervised pre-traing for sequence to sequence speech recognition

This paper proposes a novel approach to pre-train encoder-decoder sequen...

A Hierarchical Attention Based Seq2seq Model for Chinese Lyrics Generation

In this paper, we comprehensively study on context-aware generation of C...

JASS: Japanese-specific Sequence to Sequence Pre-training for Neural Machine Translation

Neural machine translation (NMT) needs large parallel corpora for state-...

Code-switching pre-training for neural machine translation

This paper proposes a new pre-training method, called Code-Switching Pre...