Training AI to read your lips — in multiple languages

Episode 277 November 30, 2022 00:04:09
Training AI to read your lips — in multiple languages
Localization Today
Training AI to read your lips — in multiple languages

Nov 30 2022 | 00:04:09

/

Hosted By

Eddie Arrieta

Show Notes

While widely used speech recognition tools like Siri or Otter generally analyze audio alone, researchers have also made progress in developing visual speech recognition (VSR) models, which rely on visual input to identify what a speaker is saying.

Other Episodes

Episode 200

August 31, 2022 00:03:39
Episode Cover

Localization a key part of gaming industry’s recent, future growth

In an analysis of the 50 most widely frequented gaming websites, BLEND found that nearly half offer a multilingual experience, with 48% supporting four...

Listen

Episode 44

February 25, 2023 00:06:51
Episode Cover

Embracing AI technology, yes! But all that glitters is not gold

The year 2022 was filled with impressive human-quality claims in the machine-learning field with large language models and general pre-trained transformers, but experts have...

Listen

Episode 285

December 13, 2022 00:03:55
Episode Cover

Research from Translated projects that MT is nearing human-like levels of performance

The quality of machine translation (MT) is quickly approaching that of human translators, according to research published today by Translated.

Listen