公开(公告)号：US11678120B2

公开(公告)日：2023-06-13

申请号：US16874171

申请日：2020-05-14

Applicant: Nvidia Corporation

Inventor： Mihir Nyayate ,  Angshuman Ghosh ,  Revanth Reddy Nalla ,  Ambrish Dantrey

IPC: H04R5/04 ,  H04R5/033 ,  H04R3/04 ,  G06N5/046 ,  G10L21/0232 ,  G06N3/084 ,  G10L25/84

CPC classification number: H04R5/04 ,  G06N3/084 ,  G06N5/046 ,  G10L21/0232 ,  G10L25/84 ,  H04R3/04 ,  H04R5/033

Abstract: Apparatuses, systems, and techniques are presented to reduce noise in audio. In at least one embodiment, one or more neural networks are used to determine a noise signal in one or more speech signals.

公开(公告)号：US09152374B2

公开(公告)日：2015-10-06

申请号：US13919002

申请日：2013-06-17

Applicant: NVIDIA Corporation

Inventor： Ambrish Dantrey

IPC: G06F3/16 ,  A63F13/00 ,  G07F17/32 ,  G06F9/44 ,  G06F13/10

CPC classification number: G06F3/165 ,  G06F3/162 ,  G06F3/167 ,  G06F9/4411 ,  G06F13/105 ,  G07F17/3204 ,  G07F17/3223

Abstract: A method includes implementing an audio framework to be executed on a data processing device with a virtual audio driver component and a User Mode Component (UMC) communicatively coupled to each other. The virtual audio driver component enables modifying an original default audio endpoint device of an application executing on the data processing device to an emulated audio device associated with a new audio endpoint in response to an initiation through the application in conjunction with the UMC. The virtual audio driver component also enables registering the new audio endpoint as the modified default audio endpoint with an operating system executing on the data processing device. Further, the virtual audio driver component enables capturing audio data intended for the original default audio endpoint device at the new audio endpoint following the registration thereof to enable control of the audio data.

Abstract translation: 一种方法包括实现在数据处理设备上执行的音频框架，其中虚拟音频驱动器组件和通信地彼此耦合的用户模式组件（UMC）。 虚拟音频驱动器组件使得能够响应于通过与UMC结合的应用的启动，将在数据处理设备上执行的应用的原始默认音频端点设备修改为与新音频端点相关联的仿真音频设备。 虚拟音频驱动器组件还使得能够使用在数据处理设备上执行的操作系统将新音频端点注册为修改的默认音频端点。 此外，虚拟音频驱动器组件能够在其注册之后，在新的音频端点捕获旨在用于原始默认音频端点设备的音频数据，以便能够控制音频数据。

公开(公告)号：US20150117666A1

公开(公告)日：2015-04-30

申请号：US14067997

申请日：2013-10-31

Applicant: NVIDIA Corporation

Inventor： Ambrish Dantrey

IPC: H04R3/00

CPC classification number: G06F3/165 ,  H04S3/008

Abstract: A method includes distinctly assigning, through a driver component, each audio channel of multichannel audio data in a memory of a data processing device to one or more audio endpoint device(s) of a number of audio endpoint devices communicatively coupled to the data processing device. Each audio endpoint device of the number of audio endpoint devices is capable of supporting a number of audio channels less than a number of audio channels of the multichannel audio data. The method also includes routing, through a processor of the data processing device communicatively coupled to the memory, audio data related to the each audio channel to the appropriate one or more audio endpoint device(s) based on the assignment through the driver component to enable rendering of the multichannel audio data on the number of audio endpoint devices.

Abstract translation: 一种方法包括通过驱动器组件明确地将数据处理设备的存储器中的多声道音频数据的每个音频通道分配给通信地耦合到数据处理设备的多个音频端点设备的一个或多个音频端点设备 。 音频端点设备数量的每个音频端点设备能够支持少于多声道音频数据的多个音频通道的多个音频通道。 该方法还包括基于通过驱动器组件的分配，将通信地耦合到存储器的数据处理设备的处理器路由到与每个音频通道相关的音频数据到适当的一个或多个音频端点设备，以使得能够 将多声道音频数据呈现在音频端点设备的数量上。