Apple Vision Pro Future Can Accept Orders Only By Reading Lip Movements

Apple Vision Pro can be trained to recognize user speech patterns. (photo: x @M1Astra)

JAKARTA - Apple is developing a new feature for the future Apple Vision Pro that will allow the device to receive commands or dips simply by reading the user's lip movements.

This feature is an extension of existing technology in the AirPods Pro, where users can nod to accept calls or shake their heads to reject it.

According to the recently revealed patent document, this feature is aimed at situations where users can't or don't want to talk, for example in noisy public places, or want to maintain privacy.

Paten berjudul "Electronic Device With Dictation Structure" (Perangkat Elektronik dengan Struktur Dikte) ini menjelaskan bahwa suara latar belakang dapat mengganggu pengendaan suara, sehingga dibutuhkan metode lain yang lebih relih untuk memasukan perintah.

To make this happen, Apple proposes several combinations of sensors. One of them is to use a "visual censor that is mounted on the screen frame and leads down" to detect mouth movements. In addition, it can also be used "additional censorship to detect facial vibrations or deformations."

As an additional option, this device can also use an internal face-to-face camera to detect input options based on eye movements. In fact, there could also be a "sensor that includes external cameras to detect hand movements as input confirmation." That way, users can make signatures to start or end the dicte process.

Apple also mentions that Vision Pro can be trained to recognize user speech patterns. The training data can be in the form of audio recordings on normal or whispering volumes, as well as visual data from various points of view that focus on the user's mouth.

This patent document is credited to an inventor named Paul X. Wang, known for his many patents for Apple, including the game controller for Vision Pro. This patent shows one of the future Apple Vision Pro development directions to improve user functionality and convenience under various conditions.