Henaff et al. applied a sparse coding algorithm to a single frame of a constant-Q transform spectrogram for musical genre classification [11], and Schülter et al. applied restricted Boltzmann machines (RBMs) to similarity-based music classification [12].
Musical instrument classification is a discipline in its own right, and many systems of classification have been used over the years.
The BOF approach is highly successful in the music information retrieval (MIR) community, and has been applied to virtually every possible musical dimensions: genre classification [33, 34]; instrument classification [35, 36]; percussion instrument classification [37, 38]; audio fingerprinting [39]; noise classification [40].
OMR technology provides a way to convert paper-based scores and has numerous applications, including computer-assisted music teaching, digital music libraries, musical statistics, digital music image automatic classification, and synchronous music and audio communication.
Several studies [27, 28] have used features extracted from musical data for classification and recommendation.
The exponential growth of the music database easily accessible and stored in the cloud promotes automated classification of musical pieces for improved user experience and recommender systems.
Several systematic studies are reported by Zils [46], including the detection of a singing voice in polyphonic recordings, the classification of musical instruments, and the classic problem of music genre classification.
We present a strategy to perform automatic genre classification of musical signals.
Alexandre et al, 2006 [16] Speech/music classification for musical genre classification Spectral centroid/rolloff, ZCR, short-time energy, low short-time energy ratio (LSTER), MFCC, voice-to-white Fisher linear discriminant, K nearest-neighbour Speech (without background music), and music without vocals.
