Personalized HRTF Calculation from Ear Images Using Learned Models

Solution Overview

Problem

Conventional methods for calculating individualized head-related transfer functions (HRTFs) require significant calculation processing loads, leading to long processing times and reduced user convenience.

Innovation Solution

An information processing device calculates HRTFs using a learned model that processes ear images to determine personalized HRTFs without generating 3D models or performing acoustic simulations, thereby reducing processing time and burden on users.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If a 3D digital model is generated based on captured ear images and acoustic simulation is performed to calculate individualized HRTFs, then manufacturing precision and reliability of the HRTF calculation are improved, but calculation processing load increases and processing time extends

Engineering Contradiction:

ImproveHRTF calculation precisionVSAvoidprocessing time

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The system performs acoustic simulations and HRTF calculations for multiple predetermined head positions in advance, before actual use. The calculated HRTFs are stored in a database, so when a user needs an HRTF, the system only needs to retrieve and select from pre-calculated data rather than performing new simulations, dramatically reducing processing time while maintaining precision

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The HRTF calculation problem is divided into two independent parts: (1) calculating HRTFs for predetermined head positions using acoustic simulation, and (2) selecting appropriate HRTFs based on actual head position detection. This segmentation allows the computationally intensive simulation to be done once for multiple positions, rather than repeatedly for each user query

Inventive Principle:

Principle #1Segmentation

2Manufacturing precision

If a 3D digital model is generated based on captured ear images and acoustic simulation is performed to calculate individualized HRTFs, then manufacturing precision is improved, but device complexity increases

Engineering Contradiction:

ImproveHRTF calculation precisionVSAvoidprocessing complexity

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The system performs acoustic simulations and HRTF calculations for multiple predetermined head positions in advance, before actual use. The calculated HRTFs are stored in a database, so when a user needs an HRTF, the system only needs to retrieve and select from pre-calculated data rather than performing new simulations, dramatically reducing processing time while maintaining precision

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

Instead of performing complex acoustic simulations in real-time, the system creates copies of HRTF data for multiple predetermined head positions through pre-calculations. These copied HRTF datasets are stored and can be quickly retrieved and selected based on detected head position, replacing the need for real-time simulation complexity

Inventive Principle:

Principle #26Copying

Data Source

PatentEP3866492B1Information processing device, information processing method, and information processing program

Publication Date: 2025.09.03 SONY GROUP CORP

Figure 1
Figure 2
Figure 3

AI summary

An information processing device (100) according to the present disclosure includes: an acquisition unit (141) configured to acquire a first image including a content image of an ear of a user; and a calculation unit (142) configured to calculate, based on the first image acquired by the acquisition unit (141), a head-related transfer function corresponding to the user by using a learned model having learned to output a head-related transfer function corresponding to an ear when an image including a content image of the ear is input.