Sign in

Language Models in Action, NLP

Suppose one day you want to home-brew your own SIRI for your daily assistance. How can it be done? Well, surprisingly not too difficult. In this post, we will take the basics of home-brewing SIRI into action.

SIRI

Of course, given this is a short reading, there will be no way to explain everything in fine detail such as voice embedding extraction, Mel-Spectrogram analysis, text-to-speech voice synthesis, time-delayed neural network, or all the fancy language models used in this technology. Instead, we will focus on one core area: how your cell phone understands your questions and provides some reasonable answer?

The…

Haoran Pu

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store