公开(公告)号：US20240257812A1

公开(公告)日：2024-08-01

申请号：US18160249

申请日：2023-01-26

Applicant: META PLATFORMS TECHNOLOGIES, LLC

Inventor： Antje IHLEFELD ,  Alexander REICH ,  Morteza KHALEGHIMEYBODI

IPC: G10L15/26 ,  G02B27/01 ,  G10L25/51

CPC classification number: G10L15/26 ,  G02B27/017 ,  G10L25/51

Abstract: One embodiment of the present invention sets forth a technique for developing a curated transcription of an acoustic experience containing spoken words. The technique includes computing a first metric for a word based on biomarkers associated with the user, where the metric indicates an attentional state of a user perceiving the word during an auditory experience. The technique further includes computing a second metric corresponding to an intelligibility of the word during the auditory experience. The technique also includes computing a third metric corresponding to an importance of the word in a context of other proximate words during the auditory experience. Based on a weighting assigned to each of the first, second and third metric, the technique includes determining whether to transcribe the word on a display.

公开(公告)号：US20240236602A1

公开(公告)日：2024-07-11

申请号：US18612758

申请日：2024-03-21

Applicant: Meta Platforms Technologies, LLC

Inventor： Philip ROBINSON ,  William Owen BRIMIJOIN, II ,  Antje IHLEFELD

IPC: H04S7/00

CPC classification number: H04S7/303 ,  H04S2420/01

Abstract: Techniques are described for generating spatialized audio content based on head orientation information and torso orientation information obtained from a drift compensation system. The drift compensation system compensates for drift in measurements performed by an inertial measurement unit (IMU), based on biological constraints pertaining to a user. The head orientation information is applied to a first set of filters to generate intermediate audio content. In turn, the torso orientation information and the intermediate audio content are applied to a second set of filters to generate the spatialized audio content. The first set of filters includes one or more audio filters that receive an input audio signal corresponding to a left channel. The second set of filters includes one or more audio filters that receive an input audio signal corresponding to a right channel. The spatialized audio content includes separate output signals for the left channel and the right channel.

公开(公告)号：US20240305951A1

公开(公告)日：2024-09-12

申请号：US18597643

申请日：2024-03-06

Applicant: Meta Platforms Technologies, LLC

Inventor： Andrew FRANCL ,  Tobias Daniel KABZINSKI ,  Hao LU ,  Antje IHLEFELD ,  William Owen BRIMIJOIN, II

IPC: H04S7/00 ,  G02B27/00 ,  G02B27/01

CPC classification number: H04S7/306 ,  G02B27/0093 ,  G02B27/0172 ,  G02B2027/0138 ,  G02B2027/014 ,  H04R2499/15 ,  H04S2400/11 ,  H04S2420/01

Abstract: Techniques for determining personalized head-related transfer functions (HRTFs) using a head-mounted device and in-ear devices include: receiving, from a sensor array of the head-mounted device, a first sound signal associated with a sound from a sound source in a local environment of a user of the head-mounted device; determining that reverberation characteristics and spectral characteristics of the sound meet predetermined criteria based on the first sound signal; determining that the sound source is stationary within a time period; determining a relative location of the sound source with respect to the user; receiving, from an in-ear device in an ear of the user, a second sound signal associated with the sound from the sound source; and determining, based on at least the second sound signal, an HRTF or one or more parameters of the HRTF associated with the relative location of the sound source for the user.