Corpus ID: 235828829

Towards Automatic Instrumentation by Learning to Separate Parts in Symbolic Multitrack Music

@article{Dong2021TowardsAI,
  title={Towards Automatic Instrumentation by Learning to Separate Parts in Symbolic Multitrack Music},
  author={Hao-Wen Dong and Chris Donahue and Taylor Berg-Kirkpatrick and Julian McAuley},
  journal={ArXiv},
  year={2021},
  volume={abs/2107.05916}
}
Modern keyboards allow a musician to play multiple instruments at the same time by assigning zones—fixed pitch ranges of the keyboard—to different instruments. In this paper, we aim to further extend this idea and examine the feasibility of automatic instrumentation—dynamically assigning instruments to notes in solo music during performance. In addition to the online, real-time-capable setting for performative use cases, automatic instrumentation can also find applications in assistive… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 43 REFERENCES
A Neural Greedy Model for Voice Separation in Symbolic Music
TLDR
A corpus of popular music was manually annotated and used to train a neural network with one hidden layer that is connected to a diverse set of perceptually informed input features, which obtains over 91% F-measure, surpassing a strong baseline based on an iterative application of an envelope extraction function. Expand
Learning Features of Music from Scratch
TLDR
A multi-label classification task to predict notes in musical recordings is defined, along with an evaluation protocol, and several machine learning architectures for this task are benchmarked. Expand
Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs
TLDR
This paper presents a conceptually different approach that explicitly takes into account the type of the tokens, such as note types and metric types, and proposes a new Transformer decoder architecture that uses different feed-forward heads to model tokens of different types. Expand
From Note-Level to Chord-Level Neural Network Models for Voice Separation in Symbolic Music
TLDR
The proposed voice separation task allows for a voice to diverge to multiple voices and also for multiple voices to converge to the same voice, and two models are shown to outperform previous approaches on separating the voices in Bach music. Expand
Pop Music Transformer: Generating Music with Rhythm and Harmony
TLDR
This paper builds a Pop Music Transformer that composes Pop piano music with a more plausible rhythmic structure than prior arts do and introduces a new event set, dubbed "REMI" (REvamped MIDI-derived events), which provides sequence models a metric context for modeling the rhythmic patterns of music. Expand
LakhNES: Improving Multi-instrumental Music Generation with Cross-domain Pre-training
TLDR
To improve the performance of the Transformer architecture, this work proposes a pre-training technique to leverage the information in a large collection of heterogeneous music, namely the Lakh MIDI dataset, and finds that this transfer learning procedure improves both quantitative and qualitative performance for the primary task. Expand
AUTOMATIC ARRANGING MUSICAL SCORE FOR PIANO USING IMPORTANT MUSICAL ELEMENTS
There is a demand for arranging music composed using multiple instruments for a solo piano because there are several pianists who wish to practice playing their favorite songs or music. Generally,Expand
MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment
TLDR
Three models for symbolic multi-track music generation under the framework of generative adversarial networks (GANs) are proposed, referred to as the jamming model, the composer model and the hybrid model, which can generate coherent music of four bars right from scratch. Expand
MMM : Exploring Conditional Multi-Track Music Generation with the Transformer
TLDR
This work creates a time-ordered sequence of musical events for each track and concatenate several tracks into a single sequence, taking advantage of the Transformer's attention-mechanism, which can adeptly handle long-term dependencies. Expand
Improving Automatic Jazz Melody Generation by Transfer Learning Techniques
TLDR
This paper uses a recurrent variational autoencoder as the generative model, and uses a genre-unspecified dataset as the source dataset and a Jazz-only datasets as the target dataset to solve the problem of data insufficiency in Jazz automatic generation. Expand
...
1
2
3
4
5
...