Music In this, the musical instrument’s audio sample

Music is social or cultural activity, an art form whose medium is sound
and silence. Rhythm (and its associated concepts tempo, Pitch (which governs
melody and harmony), meter, and articulation), the sonic qualities of timbre
and texture (which are sometimes termed the “color” of a musical
sound) and dynamics (loudness and softness) are the common elements of music. With
a vast range of instruments, music is performed. Various instruments like
tabla, harmonium, flute or violin are used in north Indian classical music. To
identify type of musical instruments and singer voice, in the recent past,
varies researches have been carried out.

Musical instrument identification/classification
is a subdomain of music information retrieval (MIR) and analysis. There are
various ways to classify the musical instruments. In this project our aim is to
identify specific musical instrument based on the classification of musical
instruments from the sound generated through them. For example ten flutes are
played, and then we should identify the specific number of flute among all the
flutes played. We are considering Monophonic music for this research. In this,
the musical instrument’s audio sample is recognized for its basic type of
musical instrument. The audio input is preprocessed with respect to noise and
then normalized by amplitude. The audio feature extraction unit extracts the
audio attributes of the musical instrument in terms of audio descriptors. These
audio descriptors together give entire data space. Feature extractors such as
Mel Frequency Cepstrum coefficient (MFCC) as one feature space and combination
of MFCC with other Timbral audio descriptors as another feature space are
analyzed together.  The Musical
instrument classifier has ‘Training’ and ‘Testing’ phases that makes use of
Vector Quantization to generate codebook. This codebook contains feature sample
per musical instrument class which will be used during the testing phase.
K-means being non-hierarchical method initially takes the number of components
of the population equal to the final required number of clusters. We attempt to
use K means classifier based on the technique of vector Quantization for
identification of a musical instrument and K nearest neighbor (KNN) as one the
statistical classifiers to identify the musical instrument. The final
conclusion will be based on the performance evaluation of both of these
classifiers.

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

x

Hi!
I'm Rick!

Would you like to get a custom essay? How about receiving a customized one?

Check it out