# Bridging Music and Text with Crowdsourced Music Comments: A Sequence-to-Sequence Framework for Thematic Music Comments Generation

arXiv: https://arxiv.org/abs/2209.01996 · HTML: https://mlsanity.com/paper/2209.01996/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 32 references that are in the map.
- First posted on arXiv 5 Sep 2022.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient](https://mlsanity.com/paper/1609.05473/) (2016)
- [Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis](https://mlsanity.com/paper/1806.04558/) (2018)
- [Music Transformer](https://mlsanity.com/paper/1809.04281/) (2018)
- [A Hierarchical Approach for Generating Descriptive Image Paragraphs](https://mlsanity.com/paper/1611.06607/) (2016)
- [Long Text Generation via Adversarial Training with Leaked Information](https://mlsanity.com/paper/1709.08624/) (2017)
- [MaskGAN: Better Text Generation via Filling in the______](https://mlsanity.com/paper/1801.07736/) (2018)
- [Relational recurrent neural networks](https://mlsanity.com/paper/1806.01822/) (2018)
- [Towards Diverse and Natural Image Descriptions via a Conditional GAN](https://mlsanity.com/paper/1703.06029/) (2017)
- [Adversarial Feature Matching for Text Generation](https://mlsanity.com/paper/1706.03850/) (2017)
- [Deep Learning Techniques for Music Generation -- A Survey](https://mlsanity.com/paper/1709.01620/) (2017)
- [GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution](https://mlsanity.com/paper/1611.04051/) (2016)
- [DopeLearning: A Computational Approach to Rap Lyrics Generation](https://mlsanity.com/paper/1505.04771/) (2015)

## Abstract (arXiv)

We consider a novel task of automatically generating text descriptions of music. Compared with other well-established text generation tasks such as image caption, the scarcity of well-paired music and text datasets makes it a much more challenging task. In this paper, we exploit the crowd-sourced music comments to construct a new dataset and propose a sequence-to-sequence model to generate text descriptions of music. More concretely, we use the dilated convolutional layer as the basic component of the encoder and a memory based recurrent neural network as the decoder. To enhance the authenticity and thematicity of generated texts, we further propose to fine-tune the model with a discriminator as well as a novel topic evaluator. To measure the quality of generated texts, we also propose two new evaluation metrics, which are more aligned with human evaluation than traditional metrics such as BLEU. Experimental results verify that our model is capable of generating fluent and meaningful comments while containing thematic and content information of the original music.