Your browser does not allow JavaScript!
JavaScript is necessary for the proper functioning of this website. Please enable JavaScript or use a modern browser.
Open Science Slovenia
Open Science
DiKUL
slv
|
eng
Search
Browse
New in RUL
About RUL
In numbers
Help
Sign in
Sonifikacija podatkov
ID
Škof, Živa
(
Author
),
ID
Solina, Franc
(
Mentor
)
More about this mentor...
,
ID
Trček, Denis
(
Comentor
)
PDF - Presentation file,
Download
(3,49 MB)
MD5: 9FDB793DE724267A6FE34515D31CF91F
Image galllery
Abstract
V diplomski nalogi s pomočjo nevronskih mrež vhodne podatke, to so besedila v formatu ASCII, pretvarjamo v glasbo v formatu MIDI. S tem želim doseči, da bi bila nevronska mreža sposobna sonificirati podatke in jim določiti čustveni ton. Nevronsko mrežo učimo na slovenskih besedilih, ki so bila predhodno ročno sonificirana. Cilj naloge je tudi, da poleg slovenskih besedil, z isto mrežo sonificiramo tudi druge vrste podatkov, kot je na primer iskanje po spletu ali sledi GPS naših sprehodov. Vsi vhodni podatki bodo v ASCII formatu. Tako bo mogoče pot, ki jo prehodiš npr. po Rožniku, sonificirati in ji pripisati \sn{obarvano sonifikacijo}. Poleg učenja nevronske mreže se diplomska naloga ukvarja tudi z iskanjem najučinkovitejše oblike vnosa ASCII podatkov v nevronsko mrežo in prilagajanjem že obstoječe nevronske mreže, da bo le ta čimbolj učinkovita pri doseganju zadanega cilja.
Language:
Slovenian
Keywords:
nevronska mreža
,
sonifikacija
,
podatki
,
LSTM
,
RNN
,
umetnost
,
glasba
,
MIDI
Work type:
Bachelor thesis/paper
Organization:
FRI - Faculty of Computer and Information Science
Year:
2019
PID:
20.500.12556/RUL-110068
COBISS.SI-ID:
1538334403
Publication date in RUL:
11.09.2019
Views:
1407
Downloads:
254
Metadata:
Cite this work
Plain text
BibTeX
EndNote XML
EndNote/Refer
RIS
ABNT
ACM Ref
AMA
APA
Chicago 17th Author-Date
Harvard
IEEE
ISO 690
MLA
Vancouver
:
Copy citation
Share:
Secondary language
Language:
English
Title:
Sonification of data
Abstract:
The diploma thesis describes a neural network which converts texts in ASCII format into music in MIDI format. The neural network is trained on manually generated sonifications of texts made manually by a composer. The goal is that the sonifications would reflect the emotions contained in the text. With the same neural network other types of data will be used as input for sonification, for example data generated by internet browsing or GPS tracks from walks.
Keywords:
neural network
,
sonification
,
data
,
LSTM
,
RNN
,
art
,
music
,
MIDI
Similar documents
Similar works from RUL:
Similar works from other Slovenian collections:
Back