• Corpus ID: 245353808

Melody Harmonization with Controllable Harmonic Rhythm

  title={Melody Harmonization with Controllable Harmonic Rhythm},
  author={Shangda Wu and Yue Yang and Zhaowen Wang and Xiaobing Li and Maosong Sun},
Melody harmonization, namely generating a chord progression for a user-given melody, remains a challenging task to this day. Although previous neural network-based systems can effectively generate an appropriate chord progression for a melody, few studies focus on controllable melody harmonization, and none of them can generate flexible harmonic rhythms. To achieve harmonic rhythmcontrollable melody harmonization, we propose AutoHarmonizer, a neural network-based melody harmonization system… 

Figures and Tables from this paper

Chord-Conditioned Melody Choralization with Controllable Harmonicity and Polyphonicity

DeepChoir is proposed, a melody choralization system, which can generate a four-part chorale for a given melody conditioned on a chord progression, and with the improved density sampling, a user can control the extent of harmonicity and polyphonicity for the chorales generated by DeepChoir.

Melodic Skeleton: A Musical Feature for Automatic Melody Harmonization

Inspired from the music theory of counterpoint writing, a novel musical feature called melodic skeleton is introduced, which summarizes the melody movement with strong harmony-related information and a pipeline involving a skeleton analysis model is proposed for melody harmonization task.



Chord Conditioned Melody Generation With Transformer Based Decoders

A chord conditioned melody Transformer is proposed, a K-POP melody generation model, which separately produces rhythm and pitch conditioned on a chord progression, and its capability of generating various melodies in accordance with a given chord progression is revealed.

Melody Harmonization Using Orderless Nade, Chord Balancing, and Blocked Gibbs Sampling

This study applies the concept of orderless NADE, which takes the melody and its partially masked chord sequence as the input of the BiLSTM-based networks to learn the masked ground truth, to the training process and shows the superiority of the proposed model.

Chord Generation from Symbolic Melody Using BLSTM Networks

A novel method of generating chord sequences from a symbolic melody using bidirectional long short-term memory (BLSTM) networks trained on a lead sheet database and it is confirmed that the chord sequences generated by the proposed method are preferred by listeners.

XiaoIce Band: A Melody and Arrangement Generation Framework for Pop Music

An end-to-end melody and arrangement generation framework, called XiaoIce Band, is proposed, which generates a melody track with several accompany tracks played by several types of instruments, and a Chord based Rhythm and Melody Cross-Generation Model (CRMCG) to generate melody with chord progressions.

Automatic melody harmonization with triad chords: A comparative study

A comparative study evaluating the performance of canonical approaches to the task of automatic melody harmonization, including template matching, hidden Markov model, genetic algorithm and deep learning shows that a deep learning method performs the best.

Function- and Rhythm-Aware Melody Harmonization Based on Tree-Structured Parsing and Split-Merge Sampling of Chord Sequences

An automatic harmonization method that, for a given melody, generates a sequence of chord symbols in the style of existing data and outperformed the HMM-based method in terms of predictive abilities is presented.

SurpriseNet: Melody Harmonization Conditioning on User-controlled Surprise Contours

This study proposes a user-controllable framework that uses a conditional variational autoencoder (CVAE) to harmonize the melody based on the given chord surprise indication, and achieves performance comparable to the state-of-the-art melody harmonization model.

Automatic Melodic Harmonization: An Overview, Challenges and Future Directions

The aim of this chapter is to provide an overview of the specific research domain as well as to shed light on the subtasks that have arisen and since evolved, and new trends and future directions are discussed along with the challenges which still remain unsolved.

CLSTMS: A Combination of Two LSTM Models to Generate Chords Accompaniment for Symbolic Melody

Experiments show that after trained on the lead sheet database, CLSTMS can learn certain principles of composing, and the performance is better than traditional HMM from the perspective of repetition rate.

Music SketchNet: Controllable Music Generation via Factorized Representations of Pitch and Rhythm

Music SketchNet, a neural network framework that allows users to specify partial musical ideas guiding automatic music generation, is proposed, and it is demonstrated that the model can successfully incorporate user-specified snippets during the generation process.