KVAK, Daniel. Generování žánrově specifické hudební transkripce Antonína Dvořáka prostřednictvím variačního autoenkodéru (Generating Genre-Specific Musical Transcriptions of Antonín Dvořák through a Variational Autoencoder). Musicologica Brunensia. Brno: Ústav hudební vědy, Filozofická fakulta Masarykovy univerzity, 2021, vol. 56, No 2, p. 49-61. ISSN 1212-0391. Available from: https://dx.doi.org/10.5817/MB2021-2-5.
Other formats:   BibTeX LaTeX RIS
Basic information
Original name Generování žánrově specifické hudební transkripce Antonína Dvořáka prostřednictvím variačního autoenkodéru
Name (in English) Generating Genre-Specific Musical Transcriptions of Antonín Dvořák through a Variational Autoencoder
Authors KVAK, Daniel (203 Czech Republic, guarantor, belonging to the institution).
Edition Musicologica Brunensia, Brno, Ústav hudební vědy, Filozofická fakulta Masarykovy univerzity, 2021, 1212-0391.
Other information
Original language Czech
Type of outcome Article in a journal
Field of Study 60403 Performing arts studies
Country of publisher Czech Republic
Confidentiality degree is not subject to a state or trade secret
WWW Plný text výsledku WoS full record
RIV identification code RIV/00216224:14210/21:00123177
Organization unit Faculty of Arts
Doi http://dx.doi.org/10.5817/MB2021-2-5
UT WoS 000766749800005
Keywords in English algorithmic composition; artificial intelligence; autoencoder; deep learning; generative art; LSTM network; machine learning; recurrent neural network
Tags International impact, Reviewed
Changed by Changed by: Mgr. Michal Petr, učo 65024. Changed: 9/5/2022 11:35.
Abstract
Apart from traditional deep learning tasks such as pattern recognition, stock price prediction, and machine translation, this method also finds practical application within algorithmic composition. This paper explores the use of a generative model based on unsupervised learning of a musical style from a pre-selected corpus and the subsequent prediction of samples from the estimated distribution. The model uses a Long Short-Term Memory neural network whose training data contains genre-specific melodies in symbolic representation.
Abstract (in English)
Apart from traditional deep learning tasks such as pattern recognition, stock price prediction, and machine translation, this method also finds practical application within algorithmic composition. This paper explores the use of a generative model based on unsupervised learning of a musical style from a pre-selected corpus and the subsequent prediction of samples from the estimated distribution. The model uses a Long Short-Term Memory neural network whose training data contains genre-specific melodies in symbolic representation.
Links
MUNI/A/1102/2020, interní kód MUName: Umění – design – média. Výzkum a zprostředkování kreativní produkce v lokálním a mezinárodním kontextu
Investor: Masaryk University
PrintDisplayed: 31/7/2024 04:18