Music Emotion Recognition: From Content- to Context-Based Models

Abstract

The striking ability of music to elicit emotions assures its prominent status in human culture and every day life. Music is often enjoyed and sought for its ability to induce or convey emotions, which may manifest in anything from a slight variation in mood, to changes in our physical condition and actions. Consequently, research on how we might associate musical pieces with emotions and, more generally, how music brings about an emotional response is attracting ever increasing attention. First, this paper provides a thorough review of studies on the relation of music and emotions from di↵erent disciplines. We then propose new insights to enhance automated music emotion recognition models using recent results from psychology, musicology, a↵ective computing, semantic technologies and music information retrieval.

Categorization of ICMR Using Feature Extraction Strategy and MIR with Ensemble Learning

“…In the Fig 3. raga cluster formation technique includes the KNN [9] [14]and SOM approach which is the best suited. In the fig.…”

The mood of Chinese Pop music: Representation and recognition

“…In contrast, dimensional models represent music moods with continuous values in a low‐dimensional space. The most adopted dimensional model in MIR is Russell's model (Barthet, Fazekas, & Sandler, ; Kim et al, ; Yang & Chen, ), which consists of two dimensions, valence (measuring the level of pleasure) and arousal (measuring the level of activity) (Russell, ). This study also adopts this model, as reprinted in Figure .…”

“…Studies on music mood recognition (MMR) revealed that, for dimensional models, music valence was consistently more difficult to predict than arousal (Barthet, Fazekas, & Sandler, ; Yang & Chen, ). For categorical models, it is also found that performances vary across mood categories and the differences might be related to the valence and arousal values corresponding to the categories (Hu, Choi, & Downie, ).…”

A Survey on musical instrument Raag detection

“…Their test data consisted of 30 tunes in 3 ragas sung by 4 artists. They use harmonic product spectrum algorithm [6][7][8][9][10][11][12] to extract the pitch. The tonic is manually fed.…”

“…The central idea in this approach, which is to model a raaga as HMM, was also used in [9]. The same idea is used in an attempt to automatically generate Hindustani classical music [10], but with less success.…”