Voice and face recognition

Neural Cube can learn to recognize the people it lives with, both by voice and by face. This is what lets the robot address people by name, keep track of who said or did what, and separate its memories of one person from its memories of another.

Recognition is fully on-device. Voice samples, face embeddings, and the names attached to them never leave the robot.

✎1 — Enroll once

VoiceA few short recordings of them speaking naturally

FaceA handful of shots at different angles and lighting

stored as

◍2 — A fingerprint

Kept as a set of numbers used for comparison. Does not use raw photos or audio, and never leaves the robot.

later

≟3 — Every time it sees or hears someone

Match foundTheir name is attached to whatever the robot is doing, and to anything it remembers from the exchange

No matchTreated as “someone”. It still talks, still helps, still remembers things without a name, which can be linked to them later

Enrollment only needs to happen once. After that, every voice heard and face seen is checked against what is stored. Someone the robot does not know is simply addressed without a name.