A speech signal processing library with emphasis on deep learning.
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-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
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's convention.
audioreadfollows the interface of
audiowritefollows the interface of
- The argument
sris removed from all short-time transforms
pip install audlib
In the source directory, install the library with test dependencies:
pip install ".[tests]"
python -m pytest tests
- Bump version in setup.py.
- Package release:
python setup.py sdist bdist_wheel
- Upload release:
twine upload --repository-url https://upload.pypi.org/legacy/ dist/*
More extensive examples can be found in
- First release of the command-line tool audpipe
- Streamlines optional installation
- Improves API (see breaking changes)
- Adds coverage test
- First release on PyPI
Raymond Xia - email@example.com
Mahmoud Alismail - firstname.lastname@example.org
Shangwu Yao - email@example.com
Andrew Wu - firstname.lastname@example.org
Feel free to send us any issue you find and question you have.
Please contact one of the authors.
Distributed under the MIT license. See
LICENSE for more information.
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 audlib-0.0.3.3-py3-none-any.whl (1.5 MB)||File type Wheel||Python version py3||Upload date||Hashes View|
|Filename, size audlib-0.0.3.3.tar.gz (1.5 MB)||File type Source||Python version None||Upload date||Hashes View|