Metadata-Version: 2.1
Name: pyclarity
Version: 0.1.1
Summary: Tools for the Clarity Challenge
Home-page: https://github.com/claritychallenge/clarity
Author: The PyClarity team
Author-email: clarity-group@sheffield.ac.uk
License: MIT
Project-URL: Bug Tracker, https://github.com/claritychallenge/clarity/issues
Project-URL: Documentation, https://claritychallenge.github.io/clarity_CC_doc
Project-URL: Source, https://github.com/claritychallenge/clarity
Keywords: machine learning,challenges,speech-enhancement,hearing-aids
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Education
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Natural Language :: English
Requires-Python: >=3.7
Description-Content-Type: text/markdown
Provides-Extra: tests
Provides-Extra: docs
Provides-Extra: dev
Provides-Extra: pypi
License-File: LICENSE

## Machine learning challenges for hearing aid processing.
<p align="center">
  <img src="docs/images/earfinal_clarity_customColour.png" alt="drawing" width="250"/>
</p>

We are organising a series of machine learning challenges to enhance hearing-aid signal processing and to better predict how people perceive speech-in-noise. For further details of the Clarity Project visit [the Clarity project website](http://claritychallenge.org/), and for details of our latest challenge visit our [challenge documentation site](https://claritychallenge.github.io/clarity_CC_doc/). You can contact the Clarity Team by email at [claritychallengecontact@gmail.com](claritychallengecontact@gmail.com).

In this repository, you will find code to support all Clarity Challenges, including baselines, toolkits, and systems from participants. **We encourage you to make your system/model open source and contribute to this repository.**

### The 2nd Clarity Enhancement Challenge (CEC2) has launched! [Take part](https://claritychallenge.github.io/clarity_CC_doc/docs/category/taking-part):fire::fire::fire:

## Installation


### PyPI

Clarity is available on the [Python Package Index (PyPI)](https://pypi.org/project/pyclarity) to install create and/or
activate a virtual environment and then use `pip` to install.

``` bash
conda create --name clarity python=3.8
conda activate clarity

pip install pyclarity
```

### GitHub Cloning

```bash
# First clone the repo
git clone https://github.com/claritychallenge/clarity.git
cd clarity

# Second create & activate environment with conda, see https://docs.conda.io/projects/conda/en/latest/user-guide/install/index.html
conda create --name clarity python=3.8
conda activate clarity

# Last install with pip
pip install -e .
```

### GitHub pip install

Alternatively `pip` allows you to install packages from GitHub sources directly. The following will install the current
`main` branch.

``` bash
pip install -e git+https://github.com/claritychallenge/clarity.git@main
```

## Challenges

Current challenge

- [The 2nd Clarity Enhancement Challenge (CEC2)](./recipes/cec2)

Previous challenges

- [The 1st Clarity Prediction Challenge (CPC1)](./recipes/cpc1)
- [The 1st Clarity Enhancement Challenge (CEC1)](./recipes/cec1)


## Available tools

We provide also a number of tools in this repository:
- **Hearing loss simulation**
    - [Cambridge MSBG hearing loss simulator](./clarity/evaluator/msbg): descriptions can be found in the [CEC1 description](./recipes/cec1); an usage example can be found in the [CEC1 baseline](./recipes/cec1/baseline) evaluation script `evaluate.py`.
- **Objective intelligibility measurement**
    - [Modified binaural STOI (MBSTOI)](./clarity/evaluator/mbstoi/mbstoi.py): a python implementation of MBSTOI. It is jointly used with the MSBG hearing loss model in the [CEC1 baseline](./recipes/cec1/baseline). The official matlab implementation can be found here: http://ah-andersen.net/code/
    - [Hearing-aid speech perception index (HASPI)](./clarity/evaluator/haspi/haspi.py): a python implementation of HASPI Version 2, and the better-ear HASPI for binaural speech signals. For official matlab implementation, request here: https://www.colorado.edu/lab/hearlab/resources
- **Hearing aid enhancement**
    - [Cambridge hearing aid fitting (CAMFIT)](./clarity/enhancer/gha/gainrule_camfit.py): a python implementation of CAMFIT, translated from the [HörTech Open Master Hearing Aid (OpenMHA)](http://www.openmha.org/about/); the CAMFIT is used together with OpenMHA enhancement as the [CEC1 baseline](./recipes/cec1/baseline), see `enhance.py`.
    - [NAL-R hearing aid fitting](./clarity/enhancer/nalr.py): a python implementation of NAL-R prescription fitting. It is used as the [CEC2 baseline](./recipes/cec2/baseline), see `enhance.py`.

In addition, differentiable approximation to some tools are provided:
* [x] [Differentiable MSBG hearing loss model](./clarity/predictor/torch_msbg.py). See also the BUT implementation: https://github.com/BUTSpeechFIT/torch_msbg_mbstoi
* [ ] Differentiable HASPI (coming)



## Open-source systems
- CPC1:
  - [Exploiting Hidden Representations from a DNN-based Speech Recogniser for Speech Intelligibility Prediction in Hearing-impaired Listeners](./recipes/cpc1/e032_sheffield)
  - [Unsupervised Uncertainty Measures of Automatic Speech Recognition for Non-intrusive Speech Intelligibility Prediction](./recipes/cpc1/e029_sheffield)
- CEC1:
  - [A Two-Stage End-to-End System for Speech-in-Noise Hearing Aid Processing](./recipes/cec1/e009_sheffield)
