You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
78 lines
3.2 KiB
78 lines
3.2 KiB
6 years ago
|
# Technology of the sound and image, AUTH
|
||
|
|
> Speech/Music classification of audio files using machine learning techniques.
|
||
|
|
|
||
|
|
## Clone
|
||
|
|
|
||
|
|
Clone this repo to your local machine using git:
|
||
|
|
```bash
|
||
|
|
git clone https://github.com/laserscout/THE-Assignment.git
|
||
|
|
```
|
||
|
|
|
||
|
|
## Dependencies
|
||
|
|
|
||
|
|
The way we recommend you run the scripts in this repository, in order to avoid python v.2/3 incompatibilities and/or other uncomfortable code breakage is setting up and using a virtual environment using python's module `venv` (or any other preferred) as described bellow:
|
||
|
|
|
||
|
|
```bash
|
||
|
|
cd THE-Assignment/classifier/
|
||
|
|
python3 -m venv myenv
|
||
|
|
source myenv/bin/activate
|
||
|
|
pip install -U scikit-learn
|
||
|
|
pip install --upgrade pandas
|
||
|
|
pip install numpy
|
||
|
|
pip install seaborn
|
||
|
|
pip install scipy
|
||
|
|
pip install essentia
|
||
|
|
```
|
||
|
|
|
||
|
|
## Feature extraction
|
||
|
|
|
||
|
|
The file `feature_extraction/feature_extractor` is a python module that uses the open-source library [Essentia](http://essentia.upf.edu/documentation/index.html) to extract audio features from an audio file in the path specified in the first parameter and save the features' values to a json file in the path specified in the second parameter.
|
||
|
|
|
||
|
|
The module can be imported or executed as a script using the following command:
|
||
|
|
```bash
|
||
|
|
python feature_extractor.py <audio_file_path> <extracted_features_file_path> <audio_file_sample_rate>
|
||
|
|
```
|
||
|
|
|
||
|
|
A python script is also provided for a batch feature extraction. The script can be executed using the following command:
|
||
|
|
```bash
|
||
|
|
python batch_feature_extractor.py <audio_files_directory> <feature_files_directory> <audio_files_sample_rate>
|
||
|
|
```
|
||
|
|
|
||
|
|
## Data preprocessing
|
||
|
|
|
||
|
|
The file `preprocessing/data_preprocessing` is a python module that uses the open-source library [scikit-learn](https://scikit-learn.org/stable/) to perform several data preprocessing techniques to the data previously extracted.
|
||
|
|
|
||
|
|
The module can be imported or executed as a script using the following command:
|
||
|
|
```bash
|
||
|
|
python data_preprocessing.py <music_data_directory> <speech_data_directory>
|
||
|
|
```
|
||
|
|
|
||
|
|
## Model training
|
||
|
|
|
||
|
|
The file `training/model_training` is a python module that uses the open-source library [scikit-learn](https://scikit-learn.org/stable/) to train several different models and one ensembles (Random Forest).
|
||
|
|
|
||
|
|
The module can be imported or executed as a script using the following command:
|
||
|
|
```bash
|
||
|
|
python model_training.py <dataset_pickle> <model_selection>
|
||
|
|
```
|
||
|
|
|
||
|
|
Where:
|
||
|
|
- *dataset_pickle* is the pandas pickle (.pkl) file of the dataset dataframe saved on the disk. This file is generated by the data_preprocessing module.
|
||
|
|
- *model_selection* is a string denoting which model the script should use. It can be one of svm (SVM model), dtree (Decision tree), nn (Multi-layer Perceptron), bayes (Naive Bayes), rndForest (Random Forest).
|
||
|
|
|
||
|
|
## Pipelines (putting it all together)
|
||
|
|
|
||
|
|
An example of how to use all the modules and functions provided can be seen reading the file `pipeline.py`.
|
||
|
|
|
||
|
|
## Support
|
||
|
|
|
||
|
|
Reach out to us:
|
||
|
|
|
||
|
|
- [apostolof's email](mailto:apotwohd@gmail.com "apotwohd@gmail.com")
|
||
|
|
- [christina284's email](mailto:christtk@auth.gr "christtk@auth.gr")
|
||
|
|
- [laserscout's email](mailto:frankgou@auth.gr "frankgou@auth.gr")
|
||
|
|
|
||
|
|
## License
|
||
|
|
|
||
|
|
[](https://github.com/laserscout/THE-Assignment/blob/master/LICENSE.md)
|