# Music Sentiment Transfer

arXiv: https://arxiv.org/abs/2110.05765 · HTML: https://mlsanity.com/paper/2110.05765/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 18 references that are in the map.
- First posted on arXiv 12 Oct 2021.

## Builds on (most cited first, 14 of 14)

- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [A Neural Algorithm of Artistic Style](https://mlsanity.com/paper/1508.06576/) (2015)
- [Universal Style Transfer via Feature Transforms](https://mlsanity.com/paper/1705.08086/) (2017)
- [Neural Style Transfer: A Review](https://mlsanity.com/paper/1705.04058/) (2017)
- [StarGAN-VC2: Rethinking Conditional Methods for StarGAN-Based Voice Conversion](https://mlsanity.com/paper/1907.12279/) (2019)
- [Learning to Generate Music With Sentiment](https://mlsanity.com/paper/2103.06125/) (2021)
- [Symbolic Music Genre Transfer with CycleGAN](https://mlsanity.com/paper/1809.07575/) (2018)
- [CycleGAN-VC3: Examining and Improving CycleGAN-VCs for Mel-spectrogram Conversion](https://mlsanity.com/paper/2010.11672/) (2020)
- [MaskCycleGAN-VC: Learning Non-parallel Voice Conversion with Filling in Frames](https://mlsanity.com/paper/2102.12841/) (2021)
- [MelGAN-VC: Voice Conversion and Audio Style Transfer on arbitrarily long samples using Spectrograms](https://mlsanity.com/paper/1910.03713/) (2019)
- [Image Sentiment Transfer](https://mlsanity.com/paper/2006.11337/) (2020)
- [Many-to-Many Voice Conversion using Conditional Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/2002.06328/) (2020)
- [Global Image Sentiment Transfer](https://mlsanity.com/paper/2006.11989/) (2020)
- [Generating Music using an LSTM Network](https://mlsanity.com/paper/1804.07300/) (2018)

## Built on by (most cited first, 1 of 1)

- [Revisiting Your Memory: Reconstruction of Affect-Contextualized Memory via EEG-guided Audiovisual Generation](https://mlsanity.com/paper/2412.05296/) (2024)

## Abstract (arXiv)

Music sentiment transfer is a completely novel task. Sentiment transfer is a natural evolution of the heavily-studied style transfer task, as sentiment transfer is rooted in applying the sentiment of a source to be the new sentiment for a target piece of media; yet compared to style transfer, sentiment transfer has been only scantily studied on images. Music sentiment transfer attempts to apply the high level objective of sentiment transfer to the domain of music. We propose CycleGAN to bridge disparate domains. In order to use the network, we choose to use symbolic, MIDI, data as the music format. Through the use of a cycle consistency loss, we are able to create one-to-one mappings that preserve the content and realism of the source data. Results and literature suggest that the task of music sentiment transfer is more difficult than image sentiment transfer because of the temporal characteristics of music and lack of existing datasets.