Automated Music Slideshow Generation Using Web Images Based on Lyrics

In this paper, we propose a system which automatically generates slideshows for music, by utilizing images retrieved from photo sharing web sites, based on query words extracted from song lyrics. The proposed system consists of two major steps: (1) query extraction from song lyrics, (2) image selection from web image search results. Moreover, in order to improve the display duration of each image in the slideshow, we adjust image transition timing by analyzing the duration of each lyric line in the input song. We have conducted subjective evaluation experiments, which prove that the proposal can generate impressive music slideshows for any input song.

[1]  Peter Knees,et al.  Oh Oh Oh Whoah! Towards Automatic Topic Detection In Song Lyrics , 2008, ISMIR.

[2]  Andreas F. Ehmann,et al.  Lyric Text Mining in Music Mood Classification , 2009, ISMIR.

[3]  Yajie Hu,et al.  Lyric-based Song Emotion Detection with Affective Lexicon and Fuzzy Clustering Method , 2009, ISMIR.

[4]  Andreas Rauber,et al.  Rhyme and Style Features for Musical Genre Classification by Song Lyrics , 2008, ISMIR.

[5]  Thorsten Joachims,et al.  SVM Light: Support Vector Machine , 2002 .

[6]  Tao Jin,et al.  Automatic Generation of Music Slide Show Using Personal Photos , 2008, 2008 Tenth IEEE International Symposium on Multimedia.

[7]  Lie Lu,et al.  P-Karaoke: personalized karaoke system , 2004, MULTIMEDIA '04.

[8]  Wei-Ying Ma,et al.  Automated Music Video Generation using WEB Image Resource , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[9]  David A. Shamma,et al.  MusicStory: a personalized music video creator , 2005, MULTIMEDIA '05.

[10]  Tsutomu Terada,et al.  A System for Presenting Background Scenes of Karaoke using an Active Database System , 2003, Computers and Their Applications.

[11]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.