Audio Cover Song Suite (acoss): A benchmarking suite for cover song identification tasks
acoss: Audio Cover Song Suite
acoss: Audio Cover Song Suite is a feature extraction and benchmarking frameworks for the cover song identification tasks. This tool has been developed along with the DA-TACOS dataset.
Setup & Installation
We recommend you to install the python package from source.
Install from source (recommended)
- Clone or download the repo.
acosspackage by using the following command inside the directory.
python3 setup.py install
Install using pip
pip3 install acoss
NOTE: While using pip install, you might need to have a local installation of librosa python library.
How to cite
Please site our paper if you use this tool in your resarch.
Furkan Yesiler, Chris Tralie, Albin Correya, Diego F. Silva, Philip Tovstogan, Emilia Gómez, and Xavier Serra. Da-TACOS: A Dataset for Cover Song Identification and Understanding. In 20th International Society for Music Information Retrieval Conference (ISMIR 2019), Delft, The Netherlands, 2019.
How to contribute?
- Fork the repo!
- Create your feature branch: git checkout -b my-new-feature
- Please read the documentation for adding your new audio feature or cover identification algorithm to acoss.
- Commit your changes: git commit -am 'Add some feature'
- Push to the branch: git push origin my-new-feature
- Submit a pull request
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
|Filename, size||File type||Python version||Upload date||Hashes|
|Filename, size acoss-0.0.1-cp36-cp36m-manylinux1_i686.whl (106.6 kB)||File type Wheel||Python version cp36||Upload date||Hashes View hashes|
|Filename, size acoss-0.0.1-cp36-cp36m-manylinux1_x86_64.whl (111.7 kB)||File type Wheel||Python version cp36||Upload date||Hashes View hashes|
Hashes for acoss-0.0.1-cp36-cp36m-manylinux1_i686.whl
Hashes for acoss-0.0.1-cp36-cp36m-manylinux1_x86_64.whl