Systems and methods for HRTF personalization

Patent metadata

Field	Value
Publication number	US-10028070-B1
Application number	US-201715627849-A
Country	US
Kind code	B1
Filing date	Jun 20, 2017
Priority date	Mar 6, 2017
Publication date	Jul 17, 2018
Grant date	Jul 17, 2018

Abstract

Systems and methods for HRTF personalization are provided. More specifically, the systems and methods provide HRTF personalization for a user based on a depth image of the user. Accordingly, the provided systems and methods are less complicated, easier to use, and easier to implement for personalizing HRTFs when compared to previously utilized systems and methods that required high-resolution three-dimensional head scans or one or more specific and/or discrete anthropomorphic measurements of the user.

First claim

The invention claimed is:

1. A system for head-related transfer function (HRTF) personalization, the system comprising:
at least one processor; and
a memory for storing and encoding computer executable instructions that, when executed by the at least one processor, are operative to:
collect a generic set of HRTFs;
collect a base three-dimensional face template;
collect a depth image of a face of a user;
bend the base three-dimensional face template until the base three-dimensional face template matches the face of the user in the depth image to form a modified three-dimensional face template;
calculate distortion parameters between the base three-dimensional face template and the modified three-dimensional face template;
adjust the generic set of HRTFs based on the distortion parameters to create a personalized set of HRTFs for the user; and
generate three-dimensional sound for the user based on the personalized set of HRTFs for the user.

2. The system of claim 1 , wherein the distortion parameters are mapped to HRTF features.

3. The system of claim 2 , wherein the distortion parameters are mapped by a linear regression, using ground-truth measured HRTFs with corresponding three-dimensional head scans to the ground-truth measured HRTFs.

4. The system of claim 1 , wherein the memory for storing and encoding the computer executable instructions that, when executed by the at least one processor are further operative to:
provide the three-dimensional sound to the user,
wherein the 3-dimensional sound is provided to the user via one or more speakers.

5. The system of claim 4 , wherein the one or more speakers are head phones or ear buds.

6. The system of claim 1 , wherein the depth image is a single depth image.

7. The system of claim 1 , wherein adjust the generic set of HRTFs based on the distortion parameters to create the personalized set of HRTFs for the user comprises:
adjust interaural time differences of the generic set of HRTFs.

8. The system of claim 1 , wherein calculate the distortion parameters between the base three-dimensional face template and the modified three-dimensional face template comprises:
calculate a distortion between each face point on the base three-dimensional face template and the modified three-dimensional face template.

9. A method for head related transfer function (HRTF) personalization, the method comprising:
collecting a generic set of HRTFs;
collecting a base three-dimensional face template;
collecting a depth image of a face of a user;
bending the base three-dimensional face template until the base three-dimensional face template matches the face of the user in the depth image to form a modified three-dimensional face template;
calculating distortion parameters between the base three-dimensional face template and the modified three-dimensional face template;
adjusting the generic set of HRTFs based on the distortion parameters to obtain a personalized set of HRTFs for the user; and
generating three-dimensional sound for the user based at least on the personalized set of HRTFs for the user.

10. The method of claim 9 , wherein the distortion parameters are mapped to HRTF features.

11. The method of claim 10 , wherein the distortion parameters are mapped by a linear regression, using ground-truth measured HRTFs with corresponding three-dimensional head scans to the ground-truth measured HRTFs.

12. The method of claim 9 , wherein collecting the depth image of the face of the user comprises:
taking the depth image of the face of the user.

13. The method of claim 9 , further comprising:
providing the three-dimensional sound to the user,
wherein the 3-dimensional sound is provided to the user via one or more speakers.

14. The method of claim 9 , wherein the depth image is a single depth image.

15. The method of claim 9 , wherein adjusting the generic set of HRTFs based on the distortion parameters to create the personalized set of HRTFs for the user comprises:
adjusting interaural time differences of the generic set of HRTFs.

16. The method of claim 9 , wherein calculating distortion parameters between the base three-dimensional face template and the modified three-dimensional face template comprises:
calculating a difference between each y-coordinate of a face point on the base three-dimensional face template and on the modified three-dimensional face template.

17. A system for head related transfer function (HRTF) personalization, the system comprising:
a computing device including a processing unit and a memory, the computing device is operable to:
bend a base three-dimensional face template until the base three-dimensional face template matches a face of a user in a depth image to form a modified three-dimensional face template;
calculate one or more distortion parameters between the base three-dimensional face template and the modified three-dimensional face template; and
adjust a generic set of HRTFs based on the one or more distortion parameters to create a personalized set of HRTFs for the user.

18. The system of claim 17 , wherein the computing device is further operable to:
generate three-dimensional sound for the user based at least on the personalized set of HRTFs for the user; and
provide the three-dimensional sound to the user.

19. The system of claim 17 , wherein the computing device is further operable to:
take the depth image of the face of the user.

20. The system of claim 17 , wherein the distortion parameters are mapped to HRTF features,
wherein the distortion parameters are mapped by a linear regression, using a database of ground-truth measured HRTFs.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Gamper Hannes
• Johnston David
• Tashev Ivan

Classifications

• G06V10/751

  Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching · CPC title

• H04S7/302 Primary

  Electronic adaptation of stereophonic sound system to listener position or orientation (H04S7/301 takes precedence) · CPC title

• H04S2420/01

  Enhancing the perception of the sound image or of the spatial distribution using head related transfer functions [HRTF's] or equivalents thereof, e.g. interaural time difference [ITD] or interaural level difference [ILD] · CPC title

• H04S2400/11

  Positioning of individual sound objects, e.g. moving airplane, within a sound field (H04S2420/13 takes precedence) · CPC title

• G06K9/00268

  Physics · mapped topic