Multi-assistant natural language input processing

Patent metadata

Field	Value
Publication number	US-12475883-B2
Application number	US-202318182762-A
Country	US
Kind code	B2
Filing date	Mar 13, 2023
Priority date	Sep 24, 2019
Publication date	Nov 18, 2025
Grant date	Nov 18, 2025

Abstract

Techniques for a natural language processing (NLP) system to implement more than one assistant are described. The NLP system may receive a natural language input corresponding to more than one user command. The NLP system may respond to a first command, of the natural language input, using a TTS voice of a first NLP system assistant. The NLP system may respond to a second command, of the natural language input, using a TTS voice of a second NLP system assistant.

First claim

What is claimed is:

1 . A computer-implemented method, comprising:
receiving, by a component corresponding to at least a first virtual assistant and a second virtual assistant, first input data representing a first natural language input provided to a first device; receiving a device identifier corresponding to the first device; determining, using the device identifier, that the first virtual assistant is, for the first device, preferred to the second virtual assistant; based at least in part on the first virtual assistant being preferred, processing the first input data using first data corresponding to the first virtual assistant to determine response data responsive to the first natural language input; generating output data by performing speech synthesis processing using the response data and second data representing a synthetic voice corresponding to the first virtual assistant, wherein the output data comprises output audio data representing synthetic speech in the synthetic voice; and causing presentation of the output data.

2 . The computer-implemented method of claim 1 , wherein:
receiving the first input data comprises receiving first input audio data representing an utterance of the first natural language input, wherein the utterance was captured by at least one microphone of the first device; and performing speech processing using the first input audio data.

3 . The computer-implemented method of claim 2 , wherein the utterance comprises a wakeword associated with the first virtual assistant.

4 . The computer-implemented method of claim 2 , wherein performing the speech processing comprises operating a speech processing component associated with the first virtual assistant.

5 . The computer-implemented method of claim 1 , further comprising:
including, in the output data, an identifier corresponding to the first virtual assistant.

6 . The computer-implemented method of claim 1 , further comprising:
processing the device identifier to determine a profile associated with the first device; and determining the profile is associated with the first virtual assistant.

7 . The computer-implemented method of claim 1 , further comprising:
processing the device identifier to determine a device type of the first device; and determining the device type is associated with the first virtual assistant.

8 . A system comprising:
at least one processor; and at least one memory comprising instructions that, when executed by the at least one processor, cause the system to:
receive, by a component corresponding to at least a first virtual assistant and a second virtual assistant, first input data representing a first natural language input provided to a first device;
receive a device identifier corresponding to the first device;
determining, using the device identifier, that the first virtual assistant is, for the first device, preferred to the second virtual assistant;
based at least in part on the first virtual assistant being preferred, process the first input data using first data corresponding to the first virtual assistant to determine response data responsive to the first natural language input;
based at least in part on the first virtual assistant being preferred, generate output data by performing speech synthesis processing using the response data and second data representing a synthetic voice corresponding to the first virtual assistant, wherein the output data comprises output audio data representing synthetic speech in the synthetic voice; and
cause presentation of the output data.

9 . The system of claim 8 , wherein:
the instructions that cause the system to receive the first input data comprise instructions that, when executed by the at least one processor, cause the system to receive first input audio data representing an utterance of the first natural language input, wherein the utterance was captured by at least one microphone of the first device; and the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to perform speech processing using the first input audio data.

10 . The system of claim 9 , wherein the utterance comprises a wakeword associated with the first virtual assistant.

11 . The system of claim 9 , wherein the instructions that cause the system to perform the speech processing comprise instructions that, when executed by the at least one processor, cause the system to operate a speech processing component associated with the first virtual assistant.

12 . The system of claim 8 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
include, in the output data, an identifier corresponding to the first virtual assistant.

13 . The system of claim 8 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
process the device identifier to determine a profile associated with the first device; and determine the profile is associated with the first virtual assistant.

14 . The system of claim 8 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
process the device identifier to determine a device type of the first device; and determine the device type is associated with the first virtual assistant.

Assignees

• Amazon Tech Inc

Inventors

• Mahmood Munir
• Bushkin Leopold
• Loeb Alexander Thomas
• Schwartz Michael
• Arif Mohammed
• Shen Rongzhou
• Gundeti Vikram Kumar
• Anwar Shemyla
• Khan Yaser
• Foyle Edward Page
• Li Bo

Classifications

• G10L13/00

  Speech synthesis; Text to speech systems · CPC title

• G10L15/30

  Distributed recognition, e.g. in client-server systems, for mobile phones or network applications · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G10L15/22

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G06F3/167

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title