Which technique is used for voice to text transformation?

[henriquecouto]

I am trying to find the technique used in transforming voice into text, if neural network is used, or some other method, but I was unsuccessful.

Question
Which AI technique is used for voice to text transformation?

Background Story
I am writing an article where a web application uses WebSpeechAPI, and important information is the technique used.

[foolip]

@henriquecouto the text-to-speech engine used will be different for each browser and could differ between platforms.

@andrenatal @marcoscaceres perhaps you can share what Firefox uses, is it https://github.com/mozilla/TTS?

[marcoscaceres]

@andrenatal?

[andrenatal]

@henriquecouto : for STT we are currently planning to use http://github.com/mozilla/deepspeech, which yes, is a neural net based speech recognition framework, but for TTS we offload the request to the OS, using, for example, SAPI on Windows, and the appropriate technology on other OSes.

We have, as @foolip rightfully mentioned, an open source project aiming to build a neural net based TTS framework, but it isn't currently in production on Firefox: https://github.com/mozilla/TTS