Apple wants Siri to be able to identify special user voices (and where they’re coming from)

Apple wants Siri, its personal digital assistant, to be able to identify special user voices (and where they’re coming from) as evidenced by a new patent filing (number 20210010797) for “self-mixing interferometry sensors used to sense vibration of a structural or housing component defining an exterior surface of a device.”

Apple notes that sensor systems included in many of today’s electronic devices may be used to sense the presence of objects, distances to objects or proximities of objects, movements of objects (e.g., whether objects are moving, or the speed, acceleration, or direction of movement of objects), and so on. Sensor systems may also identify sounds made by an object or person, sounds made by an object or person interacting with its environment, or sounds made by an object or person interacting with a sensor system or device in which the sensor system is housed. 

Here’s the summary of the patent filing: “A device includes an electronic display, a cover through which the electronic display projects an image, and an array of SMI sensors. The array of SMI sensors is positioned on a same side of the cover as the electronic display. Each SMI sensor is configured to emit electromagnetic radiation toward a respective portion of: an interior surface of the cover, or a surface of a component of the device attached to the cover; and generate a respective SMI output including information indicative of vibration of the respective portion of the cover or the component. The device also includes circuitry configured to characterize a vibratory waveform impinging on the device. The vibratory waveform is characterized using at least two of the SMI outputs.