Composing Multi-Instrumental Music with Recurrent Neural Networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10408039" target="_blank" >RIV/00216208:11320/19:10408039 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/IJCNN.2019.8852430" target="_blank" >https://doi.org/10.1109/IJCNN.2019.8852430</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/IJCNN.2019.8852430" target="_blank" >10.1109/IJCNN.2019.8852430</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Composing Multi-Instrumental Music with Recurrent Neural Networks

Popis výsledku v původním jazyce

We propose a generative model for artificial composition of both classical and popular music with the goal of producing music as well as humans do. The problem is that music is based on a highly sophisticated hierarchical structure and it is hard to measure its quality automatically. Contrary to other&apos;s work, we try to generate a symbolic representation of music with multiple different instruments playing simultaneously to cover a broader musical space. We train three modules based on LSTM networks to generate the music; a lot of effort is put into reducing the high complexity of multi-instrumental music representation by a thorough musical analysis. We believe that the proposed preprocessing techniques and symbolic representation constitute a useful resource for future research in this field

Název v anglickém jazyce

Composing Multi-Instrumental Music with Recurrent Neural Networks

Popis výsledku anglicky

We propose a generative model for artificial composition of both classical and popular music with the goal of producing music as well as humans do. The problem is that music is based on a highly sophisticated hierarchical structure and it is hard to measure its quality automatically. Contrary to other&apos;s work, we try to generate a symbolic representation of music with multiple different instruments playing simultaneously to cover a broader musical space. We train three modules based on LSTM networks to generate the music; a lot of effort is put into reducing the high complexity of multi-instrumental music representation by a thorough musical analysis. We believe that the proposed preprocessing techniques and symbolic representation constitute a useful resource for future research in this field

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GJ17-10090Y" target="_blank" >GJ17-10090Y: Optimalizace sítí</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2019 International Joint Conference on Neural Networks (IJCNN)

ISBN

978-1-72811-985-4

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

1-8

Název nakladatele

IEEE

Místo vydání

Neuveden

Místo konání akce

Budapešť, Maďarsko

Datum konání akce

14. 7. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—