A musical mood trajectory estimation method using lyrics and acoustic features

Authors:
Naoki Nishikawa;Katsutoshi Itoyama;Hiromasa Fujihara;Masataka Goto;Tetsuya Ogata;Hiroshi G. Okuno
Affiliations:
Dept. of Intelligence Science and Technology, Grad. School of Informatics, Kyoto University, Kyoto, Japan;Dept. of Intelligence Science and Technology, Grad. School of Informatics, Kyoto University, Kyoto, Japan;National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Japan;National Institute of Advanced Industrial Science and Technology (AIST), Tsukuba, Japan;Dept. of Intelligence Science and Technology, Grad. School of Informatics, Kyoto University, Kyoto, Japan;Dept. of Intelligence Science and Technology, Grad. School of Informatics, Kyoto University, Kyoto, Japan
Venue:
MIRUM '11 Proceedings of the 1st international ACM workshop on Music information retrieval with user-centered and multimodal strategies
Year:
2011

Citing 8
Cited 1

WordNet: a lexical database for English

Communications of the ACM
MARSYAS: a framework for audio analysis

Organised Sound
MARSYAS: a framework for audio analysis

Organised Sound
Topic-bridged PLSA for cross-domain text classification

Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval
Multimodal Music Mood Classification Using Audio and Lyrics

ICMLA '08 Proceedings of the 2008 Seventh International Conference on Machine Learning and Applications
How do you feel about "dancing queen"?: deriving mood & theme annotations from user tags

Proceedings of the 9th ACM/IEEE-CS joint conference on Digital libraries
Feature selection for content-based, time-varying musical emotion regression

Proceedings of the international conference on Multimedia information retrieval
Probabilistic latent semantic analysis

UAI'99 Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence

1st international ACM workshop on music information retrieval with user-centered and multimodal strategies (MIRUM)

MM '11 Proceedings of the 19th ACM international conference on Multimedia

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present a new method that represents an overall musical time-varying impression of a song by a pair of mood trajectories estimated from lyrics and audio signals. The mood trajectory of the lyrics is obtained by using the probabilistic latent semantic analysis (PLSA) to estimate topics (representing impressions) from words in the lyrics. The mood trajectory of the audio signals is estimated from acoustic features by using the multiple linear regression analysis. In our experiments, the mood trajectories of 100 songs in Last.fm's Best of 2010 were estimated. The detailed analysis of the 100 songs confirms that acoustic features provide more accurate mood trajectory and the 21% resulting mood trajectories are matched to realistic musical mood available at Last.fm.