Memory of sound (Smetana–Dvořák–Janáček). To the method of processing audio recordings using the MemoVision tool; [PAMĚŤ ZVUKU (SMETANA–DVOŘÁK–JANÁČEK). K METODĚ ZPRACOVÁNÍ ZVUKOVÝCH NAHRÁVEK POMOCÍ NÁSTROJE MEMOVISION]
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3AENSR6CGN" target="_blank" >RIV/00216208:11320/25:ENSR6CGN - isvavai.cz</a>
Result on the web
<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85183626777&doi=10.54759%2fMUSICOLOGY-2023-0403&partnerID=40&md5=24c784124b4f40bd924da28480bd818c" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85183626777&doi=10.54759%2fMUSICOLOGY-2023-0403&partnerID=40&md5=24c784124b4f40bd924da28480bd818c</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.54759/MUSICOLOGY-2023-0403" target="_blank" >10.54759/MUSICOLOGY-2023-0403</a>
Alternative languages
Result language
angličtina
Original language name
Memory of sound (Smetana–Dvořák–Janáček). To the method of processing audio recordings using the MemoVision tool; [PAMĚŤ ZVUKU (SMETANA–DVOŘÁK–JANÁČEK). K METODĚ ZPRACOVÁNÍ ZVUKOVÝCH NAHRÁVEK POMOCÍ NÁSTROJE MEMOVISION]
Original language description
This study presents the results of the project ""Memories of Sound: The Evolution of the Interpretative Tradition Based on the Works of Antonín Dvořák and Bedřich Smetana"" (The Technology Agency of the Czech Republic). The project aims to create analytical tools for music performance practice. It explores the use of computational methods, machine learning, and artificial intelligence to capture the interpretive evolution of piano works by Bedřich Smetana and Antonín Dvořák. The authors prepared the open-source software ""MemoVision"" to address the musicological goals of the project. This software combines a user-friendly interface with state-of-the-art methods. It aims to utilize the methods of music information retrieval for the goals of music performance analysis and focus primarily on a comparative analysis–computing and analyzing differences between multiple versions of the same musical piece. Users can upload audio recordings, metadata, ground-truth measurement annotations, and binary labels. Then, the software extracts features and information from all recordings and provides useful cues based on selected features and labels. Users can play back a specific range of measures, create their own areas of interest, or visualize performance data and differences between individual recordings or groups of recordings. The MemoVision tool combines methods of synchronization and feature selection to provide insight into performance data together with further visualization options. The software's potential is demonstrated on several interpretations of Antonín Dvořák's String Quartet No. 13 in G major, Op. 106 and Leoš Janáček's String Quartet No. 2 “Intimate Letters” in the section “The String Quartets: Dvořák–Janáček”. The following section, ""Excursus: The Czech Dances of Bedřich Smetana"", utilizes an extensive musical database of Smetana's Czech Dances. Although the number of international pianists (recordings) is lower, they do constitute a representative group allowing the authors to capture the differences between selected binary classes (in this case, Czech and international performers). The aim of the analysis was to find the bars or sections in which the interpretation of the two defined groups differed the most. © 2023, Institute of Art History of the Academy of Sciences of the Czech Republic. All rights reserved.
Czech name
—
Czech description
—
Classification
Type
J<sub>SC</sub> - Article in a specialist periodical, which is included in the SCOPUS database
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Hudebni Veda
ISSN
00187003
e-ISSN
—
Volume of the periodical
60
Issue of the periodical within the volume
4
Country of publishing house
US - UNITED STATES
Number of pages
33
Pages from-to
501 - 533
UT code for WoS article
—
EID of the result in the Scopus database
2-s2.0-85183626777