Chord Conditioned Melody Generation With Transformer Based Decoders

Choi, Kyoyun; Park, Jonggwon; Heo, Wan; Jeon, Sungwook; Park, Jonghun

doi:10.1109/access.2021.3065831

Cited by 26 publications

(16 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Once again the MT-CP model's results are significant worse than ours, which indicates that using a BiLSTM encoder instead of self-attention layers improves the overall performance. This has been confirmed in similar tasks, such us chord-conditioned melody generation [7].…”

Section: Objective Evaluationsupporting

confidence: 59%

Conditional Drums Generation using Compound Word Representations

Makris¹,

Guo²,

Καλιακάτσος-Παπακώστας³

et al. 2022

Preprint

View full text Add to dashboard Cite

The field of automatic music composition has seen great progress in recent years, specifically with the invention of transformerbased architectures. When using any deep learning model which considers music as a sequence of events with multiple complex dependencies, the selection of a proper data representation is crucial. In this paper, we tackle the task of conditional drums generation using a novel data encoding scheme inspired by the Compound Word representation, a tokenization process of sequential data. Therefore, we present a sequence-to-sequence architecture where a Bidirectional Long short-term memory (BiLSTM) Encoder receives information about the conditioning parameters (i.e., accompanying tracks and musical attributes), while a Transformer-based Decoder with relative global attention produces the generated drum sequences. We conducted experiments to thoroughly compare the effectiveness of our method to several baselines. Quantitative evaluation shows that our model is able to generate drums sequences that have similar statistical distributions and characteristics to the training corpus. These features include syncopation, compression ratio, and symmetry among others. We also verified, through a listening test, that generated drum sequences sound pleasant, natural and coherent while they "groove" with the given accompaniment.

show abstract

Section: Objective Evaluationsupporting

confidence: 59%

Conditional Drums Generation using Compound Word Representations

Makris¹,

Guo²,

Καλιακάτσος-Παπακώστας³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…We find that some melody generation models [9,32] use similar representations. However, they differ from our representation in that: 1) they represent each chord as a single multi-hot vector, whereas we treat it as four one-hot vectors to predict pitch information more accurately, 2) the rhythm sequence in this paper encodes the rhythm of the chord (i.e.…”

Section: Encoding Methodmentioning

confidence: 81%

Melody Harmonization with Controllable Harmonic Rhythm

Wu¹,

Yang²,

Wang³

et al. 2021

Preprint

View full text Add to dashboard Cite

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 that can generate denser or sparser chord progressions with the use of a new sampling method for controllable generation proposed in this paper. This system mainly consists of two parts: a harmonic rhythm model provides coarse-grained chord onset information, while a chord model generates specific pitches for chords based on the given melody and the corresponding harmonic rhythm sequence previously generated. To evaluate the performance of AutoHarmonizer, we use nine metrics to compare the chord progressions from humans, the system proposed in this paper and the baseline. Experimental results show that AutoHarmonizer not only generates harmonic rhythms comparable to the human level, but generates chords with overall better quality than baseline at different settings. In addition, we use AutoHarmonizer to harmonize the Session Dataset (which were originally chordless), and ended with 40,925 traditional Irish folk songs with harmonies, named the Session Lead Sheet Dataset, which is the largest lead sheet dataset to date.

show abstract

“…Jazz Transformer adapted REMI to jazz music to create long-term coherent jazz lead sheets [38]. More recently, chord conditioned melody transformer (CMT) leveraged Transformer decoders to generate a gridbased melody given a chord progression [18]. This work attempted to create a melody with proper rhythms that were well aligned with the given chords.…”

Section: B Transformer-based Music Generationmentioning

confidence: 99%

“…Using eventbased representations differs from how humans perceive a rendered or score-written melody for harmonization [16]. Instead, a grid-based melody representation can be more intuitive for modeling melodic patterns synchronized with chord labels [4], [17], [18]. In our work, we convert a melody into a more intuitive note-based representation, where each frame represents one note.…”

Section: Introductionmentioning

confidence: 99%

Translating Melody to Chord: Structured and Flexible Harmonization of Melody With Transformer

et al. 2022

View full text Add to dashboard Cite

Recent deep learning approaches for melody harmonization have achieved remarkable performance by overcoming the uneven chord distributions of music data. However, most of these approaches have not attempted to capture an original melodic structure and generate structured chord sequences with appropriate rhythms. Hence, we use a Transformer-based architecture that directly maps lower-level melody notes into a semantic higher-level chord sequence. In particular, we encode the binary piano roll of a melody into a note-based representation. Furthermore, we address the flexible generation of various chords with Transformer expanded with a VAE framework. We propose three Transformer-based melody harmonization models: 1) the standard Transformer-based model for the neural translation of a melody to chords (STHarm), 2) the variational Transformer model for learning the global representation of complete music (VTHarm), and 3) the regularized variational Transformer model for the controllable generation of chords (rVTHarm). Experimental results demonstrate that the proposed models generate more structured, diverse chord sequences than LSTM-based models.

show abstract

Chord Conditioned Melody Generation With Transformer Based Decoders

Cited by 26 publications

References 23 publications

Conditional Drums Generation using Compound Word Representations

Conditional Drums Generation using Compound Word Representations

Melody Harmonization with Controllable Harmonic Rhythm

Translating Melody to Chord: Structured and Flexible Harmonization of Melody With Transformer

Contact Info

Product

Resources

About