A library for audio processing by Discrete Cosine Transform (DCT)
Project description
libdct: A library for audio processing by Discrete Cosine Transform (DCT)
The library is to facilitate audio processing with Discrete Cosine Transform.
DCT are the kind of transforms that avoid doing signal process in complex Fourier space. Since most deep networks are difficult to capture relations in complext space, DCT are good choices for extacting audio features or generating audio signal using deep learning
The wav graph of LJ001-0025.wav:
The dct_spectrogram:
install
git clone https://github.com/ranchlai/libdct.git cd libdct && python setup.py install
or
pip install libdct --upgrade
Reference:
[1] Method and device for conducting noise suppression on image, WO2015135208A1
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
libaudiodata-0.0.3.tar.gz
(1.5 kB
view hashes)
Built Distribution
Close
Hashes for libaudiodata-0.0.3-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | ff6c9943cf9d13b148d4d3d920827fe4258c531f97d467f9c863079103e295d1 |
|
MD5 | da642f5b9669d2f64d0c08f191cf51c0 |
|
BLAKE2b-256 | 8e97f774a12851fe6613549462a6d86d5b1e009dfc6ca172d5b3998971bed9a3 |