Please use this identifier to cite or link to this item:
Title: Creating a visual music interface via emotion detection
Authors: Lim, Clement Shi Hong.
Keywords: DRNTU::Visual arts and music
Issue Date: 2010
Abstract: In this technological age, the number of digital music files inside personal computers is expanding at an exponential rate. Furthermore, with the growing market of portable digital audio players, music is now easily accessible to the general public. However, there is one group of people that is the deaf who are unable to find a satisfying audio player that allows them to appreciate music in a meaningful way. Music classification based on moods, plays an important part in multimedia applications. It allows the user to easily find what songs they really want in the huge library of music and how to effectively manage the music database in today modern society. By exploiting the use of short-time analysis techniques together with the Support Vector Machine Classifier, it is possible to classify music based on emotions. Besides classifying music based on emotions, another area of concern is to express the emotion of the songs via colours and images. In order to achieve this, pictures of virtual humans are used to express the emotion of the songs. This is achievable via the manipulation of lighting parameters (colours and intensity) and filter parameters (hue, saturation and brightness). In this project, an attempt is made to integrate these two different methods in order to design a music appreciation system that provides the listener with the opportunity to see the music visually in terms of lyrics, colours, images, frequency and time domain plots of the song’s signal. Through a more in-depth understanding of the content and context of the songs, the deaf will be able to appreciate their music in an exciting new way whereby emotions of the songs can be easily detected and expressed.
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
1.84 MBAdobe PDFView/Open

Page view(s)

checked on Sep 28, 2020


checked on Sep 28, 2020

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.