Ear-wearable device modeling

A system comprising:

• one or more storage devices configured to store ear modeling data, wherein the ear modeling data includes a three-dimensional (3D) model of an ear canal of a user;
• and
• one or more processors implemented in circuitry, the one or more processors configured to:
• apply a shell-generation model to generate a shell shape based on the ear modeling data, wherein the shell-generation model is a machine learning (ML) model and the shell shape is a 3D representation of a shell of an ear-wearable device to be worn in the ear canal;
• apply a first component-placement model to generate, based on the ear modeling data, data indicating a position of a component of the ear-wearable device, wherein the component is one or an electronics component, a receiver, or a wax guard;
• apply a second component-placement model to generate, based on the ear modeling data, data indicating an orientation of the component, wherein the first component-placement model and the second component-placement model are independent of the shell-generation model and each of the first component-placement model and the second component-placement model is a separate machine learning model;
• and
• generate, based on the position of the component, the orientation of the component and the shell shape, an ear-wearable device model that is specific to the user.

A non-transitory computer-readable storage medium having instructions stored thereon that, when executed, cause a computing system to:

• obtain ear modeling data, wherein the ear modeling data includes a 3D model of an ear canal of a user;
• apply a shell-generation model to generate a shell shape based on the ear modeling data, wherein the shell-generation model is a machine learning (ML) model and the shell shape is a 3D representation of a shell of an ear-wearable device to be worn in the ear canal;
• apply a first component-placement model to generate, based on the ear modeling data, data indicating a position of a component of the ear-wearable device, wherein the component is one of an electronics component, a receiver, or a wax guard;
• apply a second component-placement model to generate, based on the ear modeling data, data indicating an orientation of the component, wherein the first component-placement model and the second component-placement model are independent of the shell-generation model and each of the first component-placement model and the second component-placement model is a separate machine learning model;
• and
• generate, based on the position of the component and the orientation of the component, and the shell shape, an ear-wearable device model that is specific to the user.