​MINOR PROJECT-2

Synopsis

​Music Genre Classification

Submitted by:-

Aman Prakash Mishra(18102236) Batch-A1

Aakansha (18102205) Batch-A2

Shashank Mishra(18802011) Batch A9

Abstract:-

Music plays a very important role in people’s lives. Music brings like-minded people together
and is the glue that holds communities together. Communities can be recognized by the type of
songs that they compose, or even listen to. The purpose of our project and research is to find a
better machine learning algorithm than the pre-existing models that predicts the genre of songs.

Introduction:-

Sound is represented in the form of an audio signal having parameters like frequency,decibel,
bandwidth etc.
A typical audio signal can be expressed as a function of amplitude and time.
These audio signals come in various formats which make it possible and easy for computer to
read and analyse them.
Companies (such as Soundcloud, Apple Music, Spotify, Wynk etc) use music classification to
place recommendations.
Classification of genre can be very valuable to explain some interesting problems such as
creating song references, tracking down related songs, discovering societies that will like that
specific song, sometimes it can also be used for survey purposes.

Machine Learning:-

Machine learning (ML) is the study of computer ​algorithms​ that improve automatically through
experience. It is seen as a part of ​artificial intelligence​. Machine learning algorithms build a
model based on sample data, known as "​training data​", in order to make predictions or
decisions without being explicitly programmed to do so.

Deep Learning:-

Deep learning is an AI function that mimics the workings of the human brain in processing data
for use in detecting objects, recognizing speech, translating languages, and making decisions.
Dataset:-

The number of audio clips in each category has been tabulated in Table1. Each audio file is
about 1 megabyte, hence the entire fma_small dataset is about 8 GB.
Each genre comes with 1,000 representative audio segments. With the sample rate of 44,100
Hz.

S No. ​Genre Name Count

1. Electronic 1000

2. Experimental 1000

3. Folk 1000

4. Hip hop 1000

5. Instrumental 1000

6. International 1000

7. Pop 1000

8. Rock 1000

​Total 8000

Table 1:-No.of instance in class Genre

Applications:-

1. Different companies nowadays use music classification to represent recommendations to

the customer.
2. It identifies some piece of music ​belonging to a shared tradition.

References:-

● T Bertin-Mahieux, D PW Ellis, B Whitman, and P Lamere. The million song dataset. In

ISMIR, 2011​.
● We will be using the famous ​GITZAN​ dataset for our case study.
● ] Hareesh Bahuleyan, Music Genre Classification using Machine Learning Techniques,
University of Waterloo, 2018.
● Michaël Defferrard, Kirell Benzi, Pierre Vandergheynst, Xavier Bresson. FMA: A Dataset
For Music Analysis. Sound; Information Retrieval. arXiv:1612.01840v3, 2017.