Conditional neural sequence learners for generating drums’ rhythms

Makris, Dimos; Καλιακάτσος-Παπακώστας, Μάξιμος; Karydis, Ioannis; Kermanidis, Katia Lida

doi:10.1007/s00521-018-3708-6

Cited by 15 publications

(15 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have five distinct symbols: two indicating the first two bars of a phrase, two for the last two bars and one more descriptor for the rest bars. These indicators allow the model to learn the initial and final events of a phrase, an approach that has been successfully used in the task of melodic harmonisation [33] and drums generation [20].…”

Section: A Encoder Representation -Controllable By the Usermentioning

confidence: 99%

“…We use the calculated valence as a high-level conditioning feature, along with others (e.g., time signature and grouping indicators inspired by [20]), in our proposed generative lead sheet system based on sequence-to-sequence architectures (LSTM [21] and Transformer [22]). Another novel aspect of our approach is a unique strategy to include the high-level user conditions as the encoder input, whereas the musical events of the lead sheet are predicted in the decoder.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Generating Lead Sheets with Affect: A Novel Conditional seq2seq Framework

Makris¹,

Agres²,

Herremans³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

The field of automatic music composition has seen great progress in the last few years, much of which can be attributed to advances in deep neural networks. There are numerous studies that present different strategies for generating sheet music from scratch. The inclusion of high-level musical characteristics (e.g., perceived emotional qualities), however, as conditions for controlling the generation output remains a challenge. In this paper, we present a novel approach for calculating the valence (the positivity or negativity of the perceived emotion) of a chord progression within a lead sheet, using pre-defined mood tags proposed by music experts. Based on this approach, we propose a novel strategy for conditional lead sheet generation that allows us to steer the music generation in terms of valence, phrasing, and time signature. Our approach is similar to a Neural Machine Translation (NMT) problem, as we include high-level conditions in the encoder part of the sequence-to-sequence architectures used (i.e., long-short term memory networks, and a Transformer network). We conducted experiments to thoroughly analyze these two architectures. The results show that the proposed strategy is able to generate lead sheets in a controllable manner, resulting in distributions of musical attributes similar to those of the training dataset. We also verified through a subjective listening test that our approach is effective in controlling the valence of a generated chord progression.

show abstract

Section: A Encoder Representation -Controllable By the Usermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Generating Lead Sheets with Affect: A Novel Conditional seq2seq Framework

Makris¹,

Agres²,

Herremans³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In sequential systems (e.g. as the one presented by Makris et al (2019) ), the decision for each note depends only on previous notes, with additional potential constraints. In non-sequential systems (e.g., as Deep Bach; Hadjeres et al (2017) ), new notes are inserted by sampling, forming “dynamic” constraints for notes that are inserted later on, regardless of time precedence – i.e.…”

Section: Motivation Research Questions and Contributionmentioning

confidence: 99%

On the Adaptability of Recurrent Neural Networks for Real-Time Jazz Improvisation Accompaniment

Kritsis

Kylafi

Καλιακάτσος-Παπακώστας

et al. 2021

Front. Artif. Intell.

Self Cite

View full text Add to dashboard Cite

Jazz improvisation on a given lead sheet with chords is an interesting scenario for studying the behaviour of artificial agents when they collaborate with humans. Specifically in jazz improvisation, the role of the accompanist is crucial for reflecting the harmonic and metric characteristics of a jazz standard, while identifying in real-time the intentions of the soloist and adapt the accompanying performance parameters accordingly. This paper presents a study on a basic implementation of an artificial jazz accompanist, which provides accompanying chord voicings to a human soloist that is conditioned by the soloing input and the harmonic and metric information provided in a lead sheet chart. The model of the artificial agent includes a separate model for predicting the intentions of the human soloist, towards providing proper accompaniment to the human performer in real-time. Simple implementations of Recurrent Neural Networks are employed both for modeling the predictions of the artificial agent and for modeling the expectations of human intention. A publicly available dataset is modified with a probabilistic refinement process for including all the necessary information for the task at hand and test-case compositions on two jazz standards show the ability of the system to comply with the harmonic constraints within the chart. Furthermore, the system is indicated to be able to provide varying output with different soloing conditions, while there is no significant sacrifice of “musicality” in generated music, as shown in subjective evaluations. Some important limitations that need to be addressed for obtaining more informative results on the potential of the examined approach are also discussed.

show abstract

“…In [9], Markris et al proposed an architecture with stacked LSTM layers conditioned with a Feedforward layer to generate rhythm patterns. The Feedforward layer takes information on accompanying bass lines and the position within a bar.…”

Section: Related Work 21 Rhythm Generationmentioning

confidence: 99%

“…Gillick et al also provide Ableton Live plugin 9 2 based on the method, which allows users to generate new rhythms within the Ableton Live DAW environment. However, users cannot train their own models, and users' control over generated patterns is limited.…”

Section: Related Work 21 Rhythm Generationmentioning

confidence: 99%

Towards democratizing music production with AI-Design of Variational Autoencoder-based Rhythm Generator as a DAW plugin

Tokui

2020

Preprint

View full text Add to dashboard Cite

There has been significant progress in the music generation technique utilizing deep learning. However, it is still hard for musicians and artists to use these techniques in their daily music-making practice.This paper proposes a Variational Autoencoder[8](VAE)based rhythm generation system, in which musicians can train a deep learning model only by selecting target MIDI files, then generate various rhythms with the model. The author has implemented the system as a plugin software for a DAW (Digital Audio Workstation), namely a Max for Live device for Ableton Live.Selected professional/semi-professional musicians and music producers have used the plugin, and they proved that the plugin is a useful tool for making music creatively.The plugin, source code, and demo videos are available online 1 .

show abstract

Conditional neural sequence learners for generating drums’ rhythms

Cited by 15 publications

References 21 publications

Generating Lead Sheets with Affect: A Novel Conditional seq2seq Framework

Generating Lead Sheets with Affect: A Novel Conditional seq2seq Framework

On the Adaptability of Recurrent Neural Networks for Real-Time Jazz Improvisation Accompaniment

Towards democratizing music production with AI-Design of Variational Autoencoder-based Rhythm Generator as a DAW plugin

Contact Info

Product

Resources

About