Search results for "Emotion classification"
showing 3 items of 23 documents
A functional MRI study of happy and sad emotions in music with and without lyrics
2011
Musical emotions, such as happiness and sadness, have been investigated using instrumental music devoid of linguistic content. However, pop and rock, the most common musical genres, utilize lyrics for conveying emotions. Using participants’ self-selected musical excerpts, we studied their behavior and brain responses to elucidate how lyrics interact with musical emotion processing, as reflected by emotion recognition and activation of limbic areas involved in affective experience. We extracted samples from subjects’ selections of sad and happy pieces and sorted them according to the presence of lyrics. Acoustic feature analysis showed that music with lyrics differed from music without lyric…
Fifty shades of blue : Classification of music-evoked sadness
2016
It has been repeatedly shown that sad music induces mainly pleasant or mixed emotions, and is particularly relevant for self-regulation goals. However, this is not entirely compatible with the view that sadness is one of the basic emotions experienced in the face of an unpleasant event or a loss. Also, a distinction between grief and sadness is often drawn, which seemingly does not have relevance in relation to musical experiences. The discrepancy between the positive accounts of emotions associated with sad music and those present in ordinary sadness may be related to the previously unacknowledged spectrum of affects associated with music-related sadness. The present study aims to expose t…
Generalizability and Simplicity as Criteria in Feature Selection: Application to Mood Classification in Music
2011
Classification of musical audio signals according to expressed mood or emotion has evident applications to content-based music retrieval in large databases. Wrapper selection is a dimension reduction method that has been proposed for improving classification performance. However, the technique is prone to lead to overfitting of the training data, which decreases the generalizability of the obtained results. We claim that previous attempts to apply wrapper selection in the field of music information retrieval (MIR) have led to disputable conclusions about the used methods due to inadequate analysis frameworks, indicative of overfitting, and biased results. This paper presents a framework bas…