Metadata-Version: 2.1
Name: audlib
Version: 0.0.1.1
Summary: A speech signal processing library with emphasis on deep learning.
Home-page: https://github.com/raymondxyy/pyaudlib
Author: Raymond Xia
Author-email: raymondxia@cmu.edu
License: MIT
Download-URL: https://github.com/raymondxyy/pyaudlib/archive/v_01.tar.gz
Keywords: SPEECH,AUDIO,SIGNAL,SOUND,DEEP LEARNING,NEURAL NETWORKS
Platform: UNKNOWN
Classifier: License :: OSI Approved :: MIT License
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Topic :: Multimedia :: Sound/Audio :: Analysis
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Description-Content-Type: text/markdown
Requires-Dist: click (>=7.0)
Requires-Dist: numpy (>=1.17.2)
Requires-Dist: soundfile (>=0.10.2)
Requires-Dist: scipy (>=1.3.1)
Requires-Dist: resampy (>=0.2.2)
Requires-Dist: matplotlib (>=3.1.1)
Requires-Dist: torch (>=1.2.0)
Requires-Dist: torchvision (>=0.4.0)
Provides-Extra: tests
Requires-Dist: pytest (>=5.1.3) ; extra == 'tests'

# audlib

[![Build Status](https://travis-ci.com/raymondxyy/pyaudlib.svg?token=xNuzdfgseSXz1yHDnh9L&branch=master)](https://travis-ci.org/raymondxyy/pyaudlib)

> A speech signal processing library in Python with emphasis on deep learning.

audlib provides a collection of utilities for developing speech-related applications using both signal processing and deep learning. The package offers the following high-level features:

- Speech signal processing utilities with ready-to-use applications
- Deep learning architectures for speech processing tasks in [PyTorch][pytorch]
- PyTorch-compatible interface (similar to torchvision) for batch processing
- A command-line interface with a unix-pipe-like syntax
  - I/O utilities for interfacing with [CMUSPHINX][sphinx]

Some use cases of audlib are:

- Extracting common speech features for your backend
- Integrating CMUSPHINX with modern deep learning architectures
- Developing your own deep-learning-based tools for speech tasks
- Quickly try out speech processors and visualize the spectrogram in command line

audlib focuses on correctness, efficiency, and simplicity. Signal processing functionalities are mathematically checked whenever possible (e.g. constant overlap-add, `istft(stft(X))==X`). Deep neural networks follow the [PyTorch][pytorch]'s convention.

## Installation

```sh
pip install audlib
```

## Developer Installation

In the source directory, install the library with test dependencies:

```sh
pip install ".[tests]"
```

Run test:

```sh
python -m pytest tests
```

## Release flow

1. Bump version in setup.py.
2. Package release: `python setup.py sdist bdist_wheel`
3. Upload release: `twine upload --repository-url https://upload.pypi.org/legacy/ dist/*`

## Usage example

More extensive examples can be found in `examples/`.

## Release history

- 0.0.1
  - Work in progress
  - First release on PyPI

## Authors

Raymond Xia - raymondxia@cmu.edu

Mahmoud Alismail - mahmoudi@andrew.cmu.edu

Shangwu Yao - shangwuyao@gmail.com

Andrew Wu - anwu.andrew@hotmail.com

Feel free to send us any issue you find and question you have.

## Contributing

Please contact one of the authors.

## License

Distributed under the MIT license. See ``LICENSE`` for more information.

[pytorch]: https://pytorch.org/
[sphinx]: https://cmusphinx.github.io/


