The performance in music genre and mood classification is assessed by reporting the classification accuracy.
Both overall and per-rater music mood classification accuracies are reported.
Therefore, mood classification can be reasonably done independently in each dimension, as presented in Table 2.
At the machine learning stage, music genre and mood classification are treated as single-label multi-class classification problems.
Having presented the current state of research in automatic mood classification the main goals for this article are presented.
Recently the second challenge in audio mood classification was held as a part of the MIREX 2008.
This consists of several elemental tasks such as genre classification, artist identification, music mood classification, cover song identification, fundamental frequency estimation, and melody extraction.
Within the Music Information Retrieval (MIR) community, one particular task that has become increasingly popular is the task of music emotion (or mood) classification.
In particular, the GTZAN [17], ISMIR, Homburg [54], Unique [16], and 1517-Artists [16] datasets are employed for music genre classification, the MTV dataset [15] for music mood classification, and the CAL500 dataset [1] for music tagging.
It is suitable for both single-label (i.e., genre or mood classification) and multi-label (i.e., music tagging) multi-class classification problems, providing a systematic way to handle multiple audio features capturing the different aspects of music.
Also MIREX (Music Information Retrieval Evaluation eXchange) uses word clusters for its Audio Mood Classification (AMC) task as shown in Table 2. Table 1 Ajdective groups (A J) as presented by Farnsworth [4], K M were extended by Li and Ogihara[5].
