公开(公告)号：US20250069596A1

公开(公告)日：2025-02-27

申请号：US18811550

申请日：2024-08-21

Applicant: Roblox Corporation

Inventor： Mahesh Kumar NANDWANA ,  Joseph LIU ,  Morgan Samuel MCGUIRE ,  Kiran BHAT

IPC: G10L15/183 ,  G10L13/02 ,  G10L15/04 ,  G10L15/06 ,  G10L15/30 ,  G10L21/0216 ,  G10L21/028 ,  G10L25/84

Abstract: A metaverse application receives a user-provided audio stream associated with a user. The metaverse application obtains portions of one or more audio streams. The metaverse application divides the user-provided audio stream into a plurality of portions, wherein each portion corresponds to a particular time window of the audio stream. The metaverse application providing the plurality of portions of the user-provided audio stream as input to an audio machine-learning model. The audio machine-learning model outputs, based on the portions of the user-provided audio stream, a determination of abuse in a particular portion of the plurality of portions. The metaverse application performs a remedial action responsive to the determination of abuse in the particular portion.

公开(公告)号：US20240304210A1

公开(公告)日：2024-09-12

申请号：US18670422

申请日：2024-05-21

Applicant: Roblox Corporation

Inventor： Mahesh Kumar NANDWANA ,  Philippe CLAVEL ,  Morgan MCGUIRE

IPC: G10L25/57 ,  G06V20/40 ,  G10L21/043 ,  G10L25/63 ,  H04N21/454

CPC classification number: G10L25/57 ,  G06V20/41 ,  G10L21/043 ,  G10L25/63 ,  H04N21/4542

Abstract: A computer-implemented method to determine whether to introduce latency into an audio stream from a particular speaker includes an audio stream from a sender device. The method further includes providing, as input to a trained machine-learning model, the audio stream and a speech analysis score, information about one or more voice emotion parameters, and one or more voice emotion scores for a first user associated with the sender device, wherein the trained machine-learning model is iteratively applied to the audio stream and wherein each iteration corresponds to a respective portion of the audio stream. The method further includes generating as output, with the trained machine-learning model, a level of toxicity in the audio stream. The method further includes transmitting the audio stream to a recipient device, wherein the transmitting is performed to introduce a time delay in the audio stream based on the level of toxicity.

公开(公告)号：US20240112689A1

公开(公告)日：2024-04-04

申请号：US17959937

申请日：2022-10-04

Applicant: Roblox Corporation

Inventor： Mahesh Kumar NANDWANA ,  Kiran BHAT ,  Morgan MCGUIRE

IPC: G10L19/16 ,  G10L21/055

CPC classification number: G10L19/167 ,  G10L21/055

Abstract: A computer-implemented method includes receiving, at a server, a first audio stream of a performance associated with a first client device. The method further includes receiving, at the server, a second audio stream of the performance associated with a second client device. The method further includes during a time window of the performance, where the time window is less than a total time of the performance: generating a synthesized first audio stream that predicts a future of the performance based on audio features of the first audio stream and mixing the synthesized first audio stream and the second audio stream to form a combined audio stream that synchronizes the synthesized first audio stream and the second audio stream, where the time window is advanced and the generating and the mixing are repeated until the performance is complete. The method further includes transmitting the combined audio stream to the second client device.

公开(公告)号：US20240338408A1

公开(公告)日：2024-10-10

申请号：US18295744

申请日：2023-04-04

Applicant: Roblox Corporation

Inventor： Spencer William NG ,  Joseph LIU ,  Mahesh Kumar NANDWANA ,  Oleksandr ZHUKOV ,  Frederick William UMMINGER, III

IPC: G06F16/635 ,  A63F13/63 ,  G06F3/0482 ,  G06F3/16 ,  G06F16/638 ,  G06F16/65 ,  H04S7/00

CPC classification number: G06F16/635 ,  A63F13/63 ,  G06F3/0482 ,  G06F3/165 ,  G06F16/638 ,  G06F16/65 ,  H04S7/30 ,  H04S2400/11

Abstract: Implementations described herein relate to methods, systems, and computer-readable media for digital content management. In some implementations, the method includes receiving, by a processor, an audio file, determining whether there is a match of a segment of the audio file with one or more reference audio files, if it is determined that there is no match, classifying the audio file as an authentic audio file, and if it is determined that there is the match, identifying, one or more designated audio segments that are semantically similar to the segment, and replacing the segment of the audio file with a particular designated audio segment of the one or more designated audio segments.

公开(公告)号：US20240112691A1

公开(公告)日：2024-04-04

申请号：US17959736

申请日：2022-10-04

Applicant: Roblox Corporation

Inventor： Mahesh Kumar NANDWANA ,  Kiran BHAT ,  Morgan McGuire

IPC: G10L21/055 ,  G10L13/047

CPC classification number: G10L21/055 ,  G10L13/047

Abstract: A computer-implemented method includes receiving a first audio stream of a performance associated with a first client device. The method further includes during a time window of the performance, wherein the time window is less than a total time of the performance: generating a synthesized first audio stream that predicts a future of the performance based on audio features of the first audio stream and mixing the synthesized first audio stream and a second audio stream associated with a second client device to form a combined audio stream that synchronizes the synthesized first audio stream and the second audio stream, where the time window is advanced and the generating and the mixing are repeated until the performance is complete.

公开(公告)号：US20240087596A1

公开(公告)日：2024-03-14

申请号：US17940749

申请日：2022-09-08

Applicant: Roblox Corporation

Inventor： Mahesh Kumar NANDWANA ,  Philippe CLAVEL ,  Morgan MCGUIRE

IPC: G10L25/57 ,  G06V20/40 ,  G10L21/043 ,  G10L25/63 ,  H04N21/454

CPC classification number: G10L25/57 ,  G06V20/41 ,  G10L21/043 ,  G10L25/63 ,  H04N21/4542

Abstract: A computer-implemented method to determine whether to introduce latency into an audio stream from a particular speaker includes an audio stream from a sender device. The method further includes providing, as input to a trained machine-learning model, the audio stream and a speech analysis score, information about one or more voice emotion parameters, and one or more voice emotion scores for a first user associated with the sender device, wherein the trained machine-learning model is iteratively applied to the audio stream and wherein each iteration corresponds to a respective portion of the audio stream. The method further includes generating as output, with the trained machine-learning model, a level of toxicity in the audio stream. The method further includes transmitting the audio stream to a recipient device, wherein the transmitting is performed to introduce a time delay in the audio stream based on the level of toxicity.