It is the problem of identifying to which of a set of classes a song belongs, using a training set of genres already classified. Perrot and Gjerdingen conducted a study where college student were tested to make music genre classification among a total of ten music genres. The study showed that humans with little to moderate musical training can achieve up to 70% classification accuracy. Another study conducted the experiment on 27 human listeners, each listening to the central 30 seconds of a music track and received inter-participant genre classification of 76%. Genre classification requires empiric knowledge and familiarity with a set of songs to accurately classify them. There are different approaches to solving the classification problem. The project rely on the Cepstral analysis – a content-based analysis of the music signal.
sharonMandel/Music-genre-classification-based-on-Cepstral-Analysis
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
This project focuses on the problem of the music genre classification
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published