Metadata-Version: 2.1
Name: sqtpy
Version: 0.0.4
Summary: Speech Extractor and Reconstructor
Home-page: https://github.com/hasanainaz/sqt
Author: Ahmad Hasanain
Author-email: hasanainaz@gmail.com
Keywords: ASR,Pitch Track,Speech Reconstruction,Speech Processing,Cepstrogram,Singal Processing
Classifier: License :: OSI Approved :: GNU Affero General Public License v3
Classifier: Development Status :: 5 - Production/Stable
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Framework :: Jupyter
Classifier: Framework :: IPython
Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
Classifier: Topic :: Multimedia :: Sound/Audio :: Analysis
Classifier: Topic :: Multimedia :: Sound/Audio :: Sound Synthesis
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Human Machine Interfaces
Classifier: Topic :: Scientific/Engineering :: Image Processing
Classifier: Intended Audience :: Science/Research
Classifier: Intended Audience :: Telecommunications Industry
Classifier: Intended Audience :: Developers
Description-Content-Type: text/markdown
License-File: LICENSE



# The Speech Quefrency Transform (SQT) Python Library

This is an Automatic Speech Recognition (ASR) interface that converts speech audio to and from the cepstral domain. In other words, it extracts the locally stationary speech featuers from the speech signals, and it reconstructs them back to speech singals. It represents the speech series by two features and has several applications. 

### Speech Featrues:
1. Pitch Tracks
2. Responsive-Band Spectrograms (harmonic series). 
    
### Quefrency Scales:
1. Linear-Space
2. Reciprocal (this is similar to the MFCC scale)
3. Geometrical (this is based on the two dimensional view of the pitch function)

### Applications:
1. Speech Analysis and Synthesis 
2. Natural Language Processing (NLP)
3. Machine Learning (ML)
4. Telecommunications
    
    
## Homepage:
https://github.com/hasanainaz/sqt 

