pc2752 / choir_separation_f0_analysis

Multi Pitch Extraction and Source Separation Based For SATB Choirs

Pritish Chandna, Helena Cuesta, Emilia Gómez

Music Technology Group, Universitat Pompeu Fabra, Barcelona

This repository contains the source code for multi-pitch extration, based on DeepSalience[1] and for source separation for the case of SATB choirs.

Installation

To install, clone the repository and use

pip install requirements.txt 

to install the packages required.

The main code is in the main.py file.

Training and inference

Once setup, you can run the followinf commands. To train the model:

python main.py -t

.

To display evaluation metrics for a particular file: Use

python main.py -e filename

To save evaluation metrics for the entrie dataset and save to a csv file: Use

python main.py -v filename

to evaluate a wavefile and save multi pitch output to a csv file: Use

python main.py -w filename outfile

to evaluate all wavefiles in a folder and save multi pitch output to a csv file: Use

python main.py -w foldername outfolder

Evaluation

We will further update the repository in the coming months.

Acknowledgments

The TITANX used for this research was donated by the NVIDIA Corporation. This work is partially supported by the Towards Richer Online Music Public-domain Archives (TROMPA) (H2020 770376) European project.

[1] Bittner, Rachel M., et al. "Deep Salience Representations for F0 Estimation in Polyphonic Music." ISMIR. 2017.