ABSTRACT :
This paper presents a web application that retrieves songs from YouTube and classifies them into music genres. The tool explained in this study is based on models trained using the musical collection data from Audio set. For this purpose, we have used classifiers from distinct Machine Learning paradigms: Probabilistic Graphical Models (Naive Bayes), Feed-forward and Recurrent Neural Networks and Support Vector Machines (SVMs). All these models were trained in a multi-label classification scenario. Because genres may vary along a song’s timeline, we perform classification in chunks of ten seconds. This capability is enabled by Audio set, which offers 10-second samples. The visualization output presents this temporal information in real time, synced with the music video being played, presenting classification results in stacked area charts, where scores for the top-10 labels obtained per chunk are shown. We briefly explain the theoretical and scientific basis of the problem and the proposed classifiers. Subsequently, we show how the application works in practice, using three distinct songs as cases of study, which are then analysed and compared with online categorizations to discuss models performance and music genre classification challenges.
EXISTING SYSTEM :
Machine Learning (ML) is an area of Computer Science that involves the application of Artificial Intelligence techniques to learn from data. In our case, we perform the task of supervised classification. Taking a set of songs as input, labelled by genre, we have learned different models. The songs are characterized by specific features and the labels will guide the learning process. In this case, one song can be labelled with multiple genres, and they are classified in excerpts, as we will explain later. So, the problem that we approach in this work is the annotation of music genres present in a music clip, with the purpose of comparing the performance of different machine learning models when applied to this specific problem. To this end, we use the Audio set repository and its music genre samples to train the following set of models.
DISADVANTAGES OF EXISTING SYSTEM :
1) Less accuracy
2)low Efficiency
PROPOSED SYSTEM :
The design of the precision/sensitivity metric, and its use for comparing the models’ results, is an additional contribution of this paper. The incorporation of available tags from public and online services enabled the proposed evaluation method. We believe that the extension and refinement of these metrics and matching algorithms is a promising future line of work and deserves attention. As mentioned throughout the paper, a consensus for a standardized taxonomy for music genre categorization is an open challenge for MGC. We plan to open a research line approaching this issue, and we feel we should incorporate semantic elements and ontology-based information to properly tackle the genre-mapping problem across different taxonomies.
ADVANTAGES OF PROPOSED SYSTEM :
1) High accuracy
2)High efficiency
SYSTEM REQUIREMENTS
SOFTWARE REQUIREMENTS:
• Programming Language : Python
• Font End Technologies : TKInter/Web(HTML,CSS,JS)
• IDE : Jupyter/Spyder/VS Code
• Operating System : Windows 08/10
HARDWARE REQUIREMENTS:
Processor : Core I3
RAM Capacity : 2 GB
Hard Disk : 250 GB
Monitor : 15″ Color
Mouse : 2 or 3 Button Mouse
Key Board : Windows 08/10
