-
公开(公告)号：US20230217205A1
公开(公告)日：2023-07-06
申请号：US18181920
申请日：2023-03-10
Applicant: Magic Leap, Inc.
Inventor： Colby Nelson LEIDER , Justin Dan MATHEW , Michael Z. LAND , Blaine Ivin WOOD , Jung-Suk LEE , Anastasia Andreyevna TAJIK , Jean-Marc JOT
IPC: A63F13/577 , A63F13/285
CPC classification number: A63F13/577 , A63F13/285 , A63F2300/8082
Abstract: Disclosed herein are systems and methods for generating and presenting virtual audio for mixed reality systems. A method may include determining a collision between a first object and a second object, wherein the first object comprises a first virtual object. A memory storing one or more audio models can be accessed. It can be determined if the one or more audio models stored in the memory comprises an audio model corresponding to the first object. In accordance with a determination that the one or more audio models comprises an audio model corresponding to the first object, an audio signal can be synthesized, wherein the audio signal is based on the collision and the audio model corresponding to the first object, and the audio signal can be presented to a user via a speaker of a head-wearable device. In accordance with a determination that the one or more audio models does not comprise an audio model corresponding to the first object, an acoustic property of the first object can be determined, a custom audio model based on the acoustic property of the first object can be generated, an audio signal can be synthesized, wherein the audio signal is based on the collision and the custom audio model, and the audio signal can be presented, via a speaker of a head-wearable device, to a user.
-
公开(公告)号：US20220230658A1
公开(公告)日：2022-07-21
申请号：US17714708
申请日：2022-04-06
Applicant: Magic Leap, Inc.
Inventor： Jung-Suk LEE , Jean-Marc Jot
IPC: G10L25/78 , G10L25/51 , H04R3/00 , H04R3/04 , H04R5/04 , G06F3/01 , G02B27/00 , G02B27/01 , G06F17/18
Abstract: In some embodiments, a first audio signal is received via a first microphone, and a first probability of voice activity is determined based on the first audio signal. A second audio signal is received via a second microphone, and a second probability of voice activity is determined based on the first and second audio signals. Whether a first threshold of voice activity is met is determined based on the first and second probabilities of voice activity. In accordance with a determination that a first threshold of voice activity is met, it is determined that a voice onset has occurred, and an alert is transmitted to a processor based on the determination that the voice onset has occurred. In accordance with a determination that a first threshold of voice activity is not met, it is not determined that a voice onset has occurred.
-
公开(公告)号：US20240284138A1
公开(公告)日：2024-08-22
申请号：US18649778
申请日：2024-04-29
Applicant: Magic Leap, Inc.
Inventor： Colby Nelson LEIDER , Justin Dan MATHEW , Michael Z. LAND , Blaine Ivin WOOD , Jung-Suk LEE , Anastasia Andreyevna TAJIK , Jean-Marc JOT
IPC: H04S7/00 , A63F13/285 , A63F13/577 , G06F3/16 , G06T19/00
CPC classification number: H04S7/303 , A63F13/285 , A63F13/577 , G06F3/165 , G06T19/006 , A63F2300/8082
Abstract: Disclosed herein are systems and methods for generating and presenting virtual audio for mixed reality systems. A method may include determining a collision between a first object and a second object, wherein the first object comprises a first virtual object. A memory storing one or more audio models can be accessed. It can be determined if the one or more audio models stored in the memory comprises an audio model corresponding to the first object. In accordance with a determination that the one or more audio models comprises an audio model corresponding to the first object, an audio signal can be synthesized, wherein the audio signal is based on the collision and the audio model corresponding to the first object, and the audio signal can be presented to a user via a speaker of a head-wearable device. In accordance with a determination that the one or more audio models does not comprise an audio model corresponding to the first object, an acoustic property of the first object can be determined, a custom audio model based on the acoustic property of the first object can be generated, an audio signal can be synthesized, wherein the audio signal is based on the collision and the custom audio model, and the audio signal can be presented, via a speaker of a head-wearable device, to a user.
-
公开(公告)号：US20210306751A1
公开(公告)日：2021-09-30
申请号：US17214446
申请日：2021-03-26
Applicant: Magic Leap, Inc.
Inventor： David Thomas ROACH , Jean-Marc JOT , Jung-Suk LEE
Abstract: Disclosed herein are systems and methods for processing speech signals in mixed reality applications. A method may include receiving an audio signal; determining, via first processors, whether the audio signal comprises a voice onset event; in accordance with a determination that the audio signal comprises the voice onset event: waking a second one or more processors; determining, via the second processors, that the audio signal comprises a predetermined trigger signal; in accordance with a determination that the audio signal comprises the predetermined trigger signal: waking third processors; performing, via the third processors, automatic speech recognition based on the audio signal; and in accordance with a determination that the audio signal does not comprise the predetermined trigger signal: forgoing waking the third processors; and in accordance with a determination that the audio signal does not comprise the voice onset event: forgoing waking the second processors.
-
Patent Agency Ranking
公开(公告)号：US20250006219A1
公开(公告)日：2025-01-02
申请号：US18764006
申请日：2024-07-03
Applicant: Magic Leap, Inc.
Inventor： Jung-Suk LEE , Jean-Marc JOT
IPC: G10L25/78 , G02B27/00 , G02B27/01 , G06F3/01 , G06F17/18 , G10L25/51 , H04R3/00 , H04R3/04 , H04R5/04
Abstract: In some embodiments, a first audio signal is received via a first microphone, and a first probability of voice activity is determined based on the first audio signal. A second audio signal is received via a second microphone, and a second probability of voice activity is determined based on the first and second audio signals. Whether a first threshold of voice activity is met is determined based on the first and second probabilities of voice activity. In accordance with a determination that a first threshold of voice activity is met, it is determined that a voice onset has occurred, and an alert is transmitted to a processor based on the determination that the voice onset has occurred. In accordance with a determination that a first threshold of voice activity is not met, it is not determined that a voice onset has occurred.
-
公开(公告)号：US20240163612A1
公开(公告)日：2024-05-16
申请号：US18418131
申请日：2024-01-19
Applicant: Magic Leap, Inc.
Inventor： David Thomas ROACH , Jean-Marc JOT , Jung-Suk LEE
CPC classification number: H04R5/04 , G02B27/0172 , G10L15/08 , H04R3/005 , H04R3/04 , H04R5/033 , G06T19/006
Abstract: Disclosed herein are systems and methods for processing speech signals in mixed reality applications. A method may include receiving an audio signal; determining, via first processors, whether the audio signal comprises a voice onset event; in accordance with a determination that the audio signal comprises the voice onset event: waking a second one or more processors; determining, via the second processors, that the audio signal comprises a predetermined trigger signal; in accordance with a determination that the audio signal comprises the predetermined trigger signal: waking third processors; performing, via the third processors, automatic speech recognition based on the audio signal; and in accordance with a determination that the audio signal does not comprise the predetermined trigger signal: forgoing waking the third processors; and in accordance with a determination that the audio signal does not comprise the voice onset event: forgoing waking the second processors.
-
公开(公告)号：US20210195360A1
公开(公告)日：2021-06-24
申请号：US17127204
申请日：2020-12-18
Applicant: Magic Leap, Inc.
Inventor： Colby Nelson LEIDER , Justin Dan MATHEW , Michael Z. LAND , Blaine Ivin WOOD , Jung-Suk LEE , Anastasia Andreyevna TAJIK , Jean-Marc JOT
Abstract: Disclosed herein are systems and methods for generating and presenting virtual audio for mixed reality systems. A method may include determining a collision between a first object and a second object, wherein the first object comprises a first virtual object. A memory storing one or more audio models can be accessed. It can be determined if the one or more audio models stored in the memory comprises an audio model corresponding to the first object. In accordance with a determination that the one or more audio models comprises an audio model corresponding to the first object, an audio signal can be synthesized, wherein the audio signal is based on the collision and the audio model corresponding to the first object, and the audio signal can be presented to a user via a speaker of a head-wearable device. In accordance with a determination that the one or more audio models does not comprise an audio model corresponding to the first object, an acoustic property of the first object can be determined, a custom audio model based on the acoustic property of the first object can be generated, an audio signal can be synthesized, wherein the audio signal is based on the collision and the custom audio model, and the audio signal can be presented, via a speaker of a head-wearable device, to a user.
-
公开(公告)号：US20250168567A1
公开(公告)日：2025-05-22
申请号：US19026149
申请日：2025-01-16
Applicant: Magic Leap, Inc.
Inventor： David Thomas ROACH , Jean-Marc JOT , Jung-Suk LEE
Abstract: Disclosed herein are systems and methods for processing speech signals in mixed reality applications. A method may include receiving an audio signal; determining, via first processors, whether the audio signal comprises a voice onset event; in accordance with a determination that the audio signal comprises the voice onset event: waking a second one or more processors; determining, via the second processors, that the audio signal comprises a predetermined trigger signal; in accordance with a determination that the audio signal comprises the predetermined trigger signal: waking third processors; performing, via the third processors, automatic speech recognition based on the audio signal; and in accordance with a determination that the audio signal does not comprise the predetermined trigger signal: forgoing waking the third processors; and in accordance with a determination that the audio signal does not comprise the voice onset event: forgoing waking the second processors.
-
公开(公告)号：US20210043223A1
公开(公告)日：2021-02-11
申请号：US16987267
申请日：2020-08-06
Applicant: Magic Leap, Inc.
Inventor： Jung-Suk LEE , Jean-Marc JOT
IPC: G10L25/78 , G10L25/51 , H04R3/00 , H04R3/04 , H04R5/04 , G06F17/18 , G06F3/01 , G02B27/00 , G02B27/01
Abstract: In some embodiments, a first audio signal is received via a first microphone, and a first probability of voice activity is determined based on the first audio signal. A second audio signal is received via a second microphone, and a second probability of voice activity is determined based on the first and second audio signals. Whether a first threshold of voice activity is met is determined based on the first and second probabilities of voice activity. In accordance with a determination that a first threshold of voice activity is met, it is determined that a voice onset has occurred, and an alert is transmitted to a processor based on the determination that the voice onset has occurred. In accordance with a determination that a first threshold of voice activity is not met, it is not determined that a voice onset has occurred.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.015 seconds)
