Emotion-conditioned Melody Harmonization With Hierarchical Variational Autoencoder
2023 · Shulei Ji, Xinyu Yang
Abstract
Existing melody harmonization models have made great progress in improving the quality of generated harmonies, but most of them ignored the emotions beneath the music. Meanwhile, the variability of harmonies generated by previous methods is insufficient. To solve these problems, we propose a novel LSTM-based Hierarchical Variational Auto-Encoder (LHVAE) to investigate the influence of emotional conditions on melody harmonization, while improving the quality of generated harmonies and capturing the abundant variability of chord progressions. Specifically, LHVAE incorporates latent variables and emotional conditions at different levels (piece- and bar-level) to model the global and local music properties. Additionally, we introduce an attention-based melody context vector at each step to better learn the correspondence between melodies and harmonies. Objective experimental results show that our proposed model outperforms other LSTM-based models. Through subjective evaluation, we conclude
Authors
(none)
Tags
Stats
Related papers
- Automatic Melody Harmonization With Triad Chords: A Comparative Study (2020)11.49
- Melody Harmonization Using Orderless NADE, Chord Balancing, And Blocked Gibbs Sampling (2020)8.35
- Conditional Variational Autoencoder To Improve Neural Audio Synthesis For Polyphonic Music Sound (2022)0.00
- Towards Improving Harmonic Sensitivity And Prediction Stability For Singing Melody Extraction (2023)0.00
- A Melody-unsupervision Model For Singing Voice Synthesis (2021)5.84
- Interpretable Timbre Synthesis Using Variational Autoencoders Regularized On Timbre Descriptors (2023)0.00
- Midi-sandwich: Multi-model Multi-task Hierarchical Conditional VAE-GAN Networks For Symbolic Single-track Music Generation (2019)0.00
- Multi-view Midivae: Fusing Track- And Bar-view Representations For Long Multi-track Symbolic Music Generation (2024)0.00