2020
DOI: 10.1007/s11042-020-08798-6
|View full text |Cite
|
Sign up to set email alerts
|

Audio style transfer using shallow convolutional networks and random filters

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
6
0

Year Published

2021
2021
2023
2023

Publication Types

Select...
5
1
1

Relationship

0
7

Authors

Journals

citations
Cited by 10 publications
(6 citation statements)
references
References 14 publications
0
6
0
Order By: Relevance
“…(5) Constantly update the particle velocity and position parameters according to equations ( 2)-( 4). ( 6) e end of the specified condition is reached, otherwise it goes back to step (2). e algorithm flow is shown in Figure 5.…”
Section: Complexitymentioning
confidence: 99%
See 1 more Smart Citation
“…(5) Constantly update the particle velocity and position parameters according to equations ( 2)-( 4). ( 6) e end of the specified condition is reached, otherwise it goes back to step (2). e algorithm flow is shown in Figure 5.…”
Section: Complexitymentioning
confidence: 99%
“…Music visualization is one of the expressions of music iconography that focuses on music feature extraction, emotion detection, and image processing [1,2]. Visualization is a form of data expression and delivery, similar to the way computers simulate the way people express emotions that can be seen through expressions, body movements, and so forth.…”
Section: Introductionmentioning
confidence: 99%
“…Moreover, the deviation of the musicality of protein music from that of specific music style may be further reduced by the advanced artificial intelligence methods. Deep learning algorithms for recomposing the style of one audio data using the style of another have been developed [44] (arXiv:1711.11160v1). These algorithms may be potentially extended for the calibration of our derived protein music towards the Fantasy-Impromptu style or any other targeted style.…”
Section: Discussionmentioning
confidence: 99%
“…There are several initial attempts at audio style transfer [99,100,45,101]. In a blog, authors have recommended the use of shallow networks instead of deep pre-trained PAPERS networks such as in the case of image processing [102].…”
Section: Deep Learning For Texture Synthesismentioning
confidence: 99%