aka voice recognition, speech-to-text, STT

The counterpart to Speech synthesis

https://github.com/facebookresearch/wav2letter?utm_source=SitePoint&utm_medium=email&utm_campaign=Versioning

https://www.wikiwand.com/en/Speech_recognition

Unsupervised Learning of Temporal Features for Word Categorization in a Spiking Neural Network Model of the Auditory Brain

Baidu: http://venturebeat.com/2017/03/13/baidu-launches-swiftscribe-an-app-that-transcribes-audio-with-ai/

https://twitter.com/Reza_Zadeh/status/936125877435351040