| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| paper | 256.99 KB | Adobe PDF | ||
| slides | 1.21 MB | Adobe PDF | ||
| poster | 914.3 KB | Adobe PDF |
Advisor(s)
Abstract(s)
This paper evaluates the impact of song segmentation on Music Emotion Variation Detection (MEVD). In particular, the All-In-One song-structure segmentation system was employed to this end and compared to a fixed 1.5-sec window approach. Acoustic features were extracted for each obtained segment/window, which were classified with SVMs. The attained results (best F1-score of 55.9%) suggest that, despite its promise, the potential of this song segmentation approach was not fully exploited, possibly due to the small employed dataset. Nevertheless, preliminary results are encouraging.
Description
Keywords
MEVD music emotion variation detection song segmentation