Deep Learning for Music

Huang, Allen; Wu, Raymond

doi:10.48550/arxiv.1606.04930

Cited by 15 publications

(19 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many methods use LSTM-style models to construct the pipeline. Huang A, Wu R.'s work [4] provides a simple but effective baseline for end-to-end learning and generative method. Kalingeri V, Grandhe S. [5] further experiment with more variations of LSTM and also adopt convolution layers.…”

Section: Related Workmentioning

confidence: 99%

Dual-track Music Generation using Deep Learning

Lyu,

Zhang,

Song

2020

Preprint

View full text Add to dashboard Cite

Music generation is always interesting in a sense that there is no formalized recipe. In this work, we propose a novel dual-track architecture for generating classical piano music, which is able to model the inter-dependency of left-hand and right-hand piano music. Particularly, we experimented with a lot of different models of neural network as well as different representations of music, and the results show that our proposed model outperforms all other tested methods. Besides, we deployed some special policies for model training and generation, which contributed to the model performance remarkably. Finally, under two evaluation methods, we compared our models with the MuseGAN project and true music.

show abstract

Section: Related Workmentioning

confidence: 99%

Dual-track Music Generation using Deep Learning

Lyu,

Zhang,

Song

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The majority of recent AI advances have arisen due to deep learning [28], a particular machine learning approach that allows for highly complex models [42]. There has been a significant amount of work in applying deep learning to a variety of tasks, including writing [6,48], music composition [8,25], and visual art [7]. However these prior instances almost all involve a use case in which a human user prompts a trained AI agent for output.…”

Section: Ai Co-creationmentioning

confidence: 99%

Friend, Collaborator, Student, Manager

Guzdial

Liao

Chen

et al. 2019

Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Machine learning advances have afforded an increase in algorithms capable of creating art, music, stories, games, and more. However, it is not yet well-understood how machine learning algorithms might best collaborate with people to support creative expression. To investigate how practicing designers perceive the role of AI in the creative process, we developed a game level design tool for Super Mario Bros.style games with a built-in AI level designer. In this paper we discuss our design of the Morai Maker intelligent tool through two mixed-methods studies with a total of over onehundred participants. Our findings are as follows: (1) level designers vary in their desired interactions with, and role of, the AI, (2) the AI prompted the level designers to alter their design practices, and (3) the level designers perceived the AI as having potential value in their design practice, varying based on their desired role for the AI.

show abstract

“…There has been a lot of work where musical features such as notes, chords and notations have been used to generate music using LSTMs [3,4,5]. These works show promising results and demonstrate that LSTMs have the ability to capture enough long-range information required for music generation.…”

Section: Related Workmentioning

confidence: 99%

Music Generation with Deep Learning

Kalingeri¹,

Grandhe²

2016

Preprint

View full text Add to dashboard Cite

The use of deep learning to solve the problems in literary arts has been a recent trend that gained a lot of attention and automated generation of music has been an active area. This project deals with the generation of music using raw audio files in the frequency domain relying on various LSTM architectures. Fully connected and convolutional layers are used along with LSTM's to capture rich features in the frequency domain and increase the quality of music generated. The work is focused on unconstrained music generation and uses no information about musical structure(notes or chords) to aid learning.The music generated from various architectures are compared using blind fold tests. Using the raw audio to train models is the direction to tapping the enormous amount of mp3 files that exist over the internet without requiring the manual effort to make structured MIDI files. Moreover, not all audio files can be represented with MIDI files making the study of these models an interesting prospect to the future of such models.

show abstract

Deep Learning for Music

Cited by 15 publications

References 0 publications

Dual-track Music Generation using Deep Learning

Dual-track Music Generation using Deep Learning

Friend, Collaborator, Student, Manager

Music Generation with Deep Learning

Contact Info

Product

Resources

About