公开(公告)号：US20240412728A1

公开(公告)日：2024-12-12

申请号：US18333041

申请日：2023-06-12

Applicant: Amazon Technologies, Inc.

Inventor： Michael Thomas Peterson ,  Gengshen Fu ,  Aaron Challenner ,  Rong Chen ,  Cody Jacques ,  Stefan M Bradstreet

IPC: G10L15/22 ,  G10L15/16

Abstract: A device is configured to detect multiple different wakewords. A device may operate a joint encoder that operates on audio data to determine encoded audio data. The device may operate multiple different decoders which process the encoded audio data to determine if a wakeword is detected. Each decoder may correspond to a different wakeword. The decoders may use fewer computing resources than the joint encoder, allowing for the device to more easily perform multiple wakeword processing. Enabling/disabling wakeword(s) may involve the reconfiguring of a wakeword detector to add/remove data for respective decoder(s). Specific decoders may be activated/deactivated depending on device context, thereby efficiently managing device resources.

公开(公告)号：US11942100B1

公开(公告)日：2024-03-26

申请号：US17713084

申请日：2022-04-04

Applicant: Amazon Technologies, Inc.

Inventor： Aditya Sharadchandra Joshi ,  Carlo Murgia ,  Michael Thomas Peterson

IPC: G10L19/02 ,  G06F3/16 ,  G10L19/002 ,  G10L21/02 ,  H04L65/70 ,  H04L65/75

CPC classification number: G10L19/02 ,  G06F3/16 ,  G06F3/165 ,  G10L19/002 ,  G10L21/02 ,  H04L65/70 ,  H04L65/75

Abstract: Techniques for encoding audio data with metadata are described. In an example, a device receives audio data corresponding to audio detected by a microphone and receives metadata associated with the audio. The device generates encoded data based at least in part on encoding the audio data with the metadata. The encoding involves replacing a portion of the audio data with the metadata, such that the encoded data includes the metadata and a remaining portion of the audio data. The device sends the encoded data to an audio processing application.

公开(公告)号：US11315581B1

公开(公告)日：2022-04-26

申请号：US16995220

申请日：2020-08-17

Applicant: Amazon Technologies, Inc.

Inventor： Aditya Sharadchandra Joshi ,  Carlo Murgia ,  Michael Thomas Peterson

IPC: G10L19/002 ,  G10L19/02 ,  H04L65/60 ,  G10L21/02 ,  G06F3/16

Abstract: Techniques for encoding audio data with metadata are described. In an example, a device receives audio data corresponding to audio detected by a microphone and receives metadata associated with the audio. The device generates encoded data based at least in part on encoding the audio data with the metadata. The encoding involves replacing a portion of the audio data with the metadata, such that the encoded data includes the metadata and a remaining portion of the audio data. The device sends the encoded data to an audio processing application.