公开(公告)号：US20220383868A1

公开(公告)日：2022-12-01

申请号：US17825288

申请日：2022-05-26

Applicant: Analog Devices, Inc.

Inventor： Jonathan Samuel YEDIDIA ,  Daniel SCHMIDT ,  Cristobal ALESSANDRI ,  Reuben Harry COHN-GORDON ,  Ilker BAYRAM ,  Ravi Kiran RAMAN ,  Nicholas Eastman MORAN ,  Atulya YELLEPEDDI ,  Milutin PAJOVIC ,  Sunrita PODDAR

IPC: G10L15/193 ,  G10L15/26

Abstract: It is not trivial to implement speech and natural language processing in offline embedded systems. Voice control of devices in various settings and applications can benefit from an embedded speech and natural language processing solution. One feature that helps to correct automatic speech recognition outputs is grammar projection. Another feature addresses situations where there is imperfect information or incomplete information by providing an application programming interface to enable structured queries and responses between an interpreter and an application.

公开(公告)号：US20240330590A1

公开(公告)日：2024-10-03

申请号：US18404666

申请日：2024-01-04

Applicant: Analog Devices, Inc.

Inventor： Jonathan Samuel YEDIDIA ,  Nicholas Eastman MORAN

IPC: G06F40/289

CPC classification number: G06F40/289

Abstract: Technologies are provided for a distributed spoken language interface for speech control of multiple apparatuses. In some aspects, a first apparatus can receive an audio signal representative of speech. The first apparatus can detect, based on applying a keyphrase recognition model to the speech, a keyphrase. The keyphrase can include a first string of characters defining an identifier corresponding to at least one second apparatus and also includes a second string of characters defining a command. The first apparatus can cause, based on the identifier, a communication unit integrated in the first apparatus to send the keyphrase to the at least one second apparatus. The at least one second apparatus can receive the keyphrase, and can cause one or more components to execute the command.