Pinned Repositories
ai-audio-descriptions
Fork of Microsoft's AI audio description program
GAN-Speech_engine_and_research_tools
A GAN (Generative Adversarial Network) can currently create a very good speech vocoder using linked voice and text data. This voice and text data exists license free on the web. This means the knowledge, data and tools exist to create a license free Speech Engine and to enable further work.
hifi-gan
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
JWJPaton.github.io
Webpages
python_speech_features
This library provides common speech features for ASR including MFCCs and filterbank energies.
SALT
Speech as lookup table - Using an updatable list of pre-recorded audio clips to provide speech access to static and semi-static menu systems
AccessibleGamingReport
RNIB's Accessible Gaming Report
Gaming_Devkit
Repository for RNIB's gaming accessibility Devkit
RNIB-MediaAndCulture.github.io
Web frontend for RNIB Media and Culture team pages
JWJPaton's Repositories
JWJPaton/ai-audio-descriptions
Fork of Microsoft's AI audio description program
JWJPaton/GAN-Speech_engine_and_research_tools
A GAN (Generative Adversarial Network) can currently create a very good speech vocoder using linked voice and text data. This voice and text data exists license free on the web. This means the knowledge, data and tools exist to create a license free Speech Engine and to enable further work.
JWJPaton/hifi-gan
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
JWJPaton/JWJPaton.github.io
Webpages
JWJPaton/python_speech_features
This library provides common speech features for ASR including MFCCs and filterbank energies.
JWJPaton/SALT
Speech as lookup table - Using an updatable list of pre-recorded audio clips to provide speech access to static and semi-static menu systems