TU Darmstadt / ULB / TUbiblio

Personalized Visual-Interactive Music Classification

Ritter, Christian and Altenhofen, Christian and Zeppelzauer, Matthias and Kuijper, Arjan and Schreck, Tobias and Bernard, Jürgen (2018):
Personalized Visual-Interactive Music Classification.
In: International EuroVis Workshop on Visual Analytics (EuroVA) 2018, Brno, Czech Republic, June 4, 2018, ISBN 978-3-03868-064-2,
DOI: 10.2312/eurova.20181109,
[Conference or Workshop Item]

Abstract

We present an interactive visual music classification tool that will allow users to automatically structure music collections in a personalized way. With our approach, users play an active role in an iterative process of building classification models, using different interactive interfaces for labeling songs. The interactive tool conflates interfaces for the detailed analysis at different granularities, i.e., audio features, music songs, as well as classification results at a glance. Interactive labeling is provided with three complementary interfaces, combining model-centered and human-centered labeling-support principles. A clean visual design of the individual interfaces depicts complex model characteristics for experts, and indicates our work-in-progress towards the abilities of non-experts. The result of a preliminary usage scenario shows that, with our system, hardly any knowledge about machine learning is needed to create classification models of high accuracy with less than 50 labels.

Item Type: Conference or Workshop Item
Erschienen: 2018
Creators: Ritter, Christian and Altenhofen, Christian and Zeppelzauer, Matthias and Kuijper, Arjan and Schreck, Tobias and Bernard, Jürgen
Title: Personalized Visual-Interactive Music Classification
Language: English
Abstract:

We present an interactive visual music classification tool that will allow users to automatically structure music collections in a personalized way. With our approach, users play an active role in an iterative process of building classification models, using different interactive interfaces for labeling songs. The interactive tool conflates interfaces for the detailed analysis at different granularities, i.e., audio features, music songs, as well as classification results at a glance. Interactive labeling is provided with three complementary interfaces, combining model-centered and human-centered labeling-support principles. A clean visual design of the individual interfaces depicts complex model characteristics for experts, and indicates our work-in-progress towards the abilities of non-experts. The result of a preliminary usage scenario shows that, with our system, hardly any knowledge about machine learning is needed to create classification models of high accuracy with less than 50 labels.

ISBN: 978-3-03868-064-2
Uncontrolled Keywords: Labeling, Information visualization, Human-centered computing, Interactive Machine Learning, Visual analytics, Music information retrieval, Classification methods, Man-machine interaction, User interfaces
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
20 Department of Computer Science > Mathematical and Applied Visual Computing
Event Title: International EuroVis Workshop on Visual Analytics (EuroVA) 2018
Event Location: Brno, Czech Republic
Event Dates: June 4, 2018
Date Deposited: 29 Aug 2019 05:56
DOI: 10.2312/eurova.20181109
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item