Music Information Retrieval

In contemporary history, the digitization of human societies and media convergence are inextricably linked. Framework conditions for media representatives, recipients, interest groups and regulatory bodies are changing accordingly. Due to digitization in all media sectors, it is much necessary to analyse the media market conditions and their operations. The objective of this study is to develop and evaluate methods to systematically classify public radio stations in Germany to discover and interpret their broadcasts on a set of empirical research questions. This study helps in assigning a DNA like identification to each of the radio stations based on the broadcast music and music-related editorial contents. The study is divided into three tasks: One, data collection and identification; two, data validation; and three, data mining to find answers for a list of given empirical factors which are understood as the DNA structure of corresponding broadcast station.

Project Details

Date: Mar 1, 2017

Author: Ganesh Harugeri

Categories: projectmusic information retrieval


Related Works.

Bidirectional Learning for Robust Neural Networks

Recognizing Challenging Handwritten Annotations with Fully Convolutional Networks

Real-Time Document Image Classification using Deep CNN and Extreme Learning Machines

Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification

TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network


We believe that creativity comes with freedom and to solve challenging problems in AI we need to have freedom and creative thinking. We provide an unconstrained environment to highly motivated students to do whatever that comes to their minds and explore deep learning.

Social Links

Our Bunker

Building 86,
Davenport 11,
67663 Kaiserslautern,