US 11,081,099 B2Granted

Automated speech pronunciation attribution

AssigneeGoogle Inc.

InventorsJustin Lewis, Lisa Takehana

Life of this patent

Estimating the term…

Loading patent…

Abstract

Methods, systems, and apparatus for determining candidate user profiles as being associated with a shared device, and identifying, from the candidate user profiles, candidate pronunciation attributes associated with at least one of the candidate user profiles determined to be associated with the shared device. The methods, systems, and apparatus are also for receiving, at the shared device, a spoken utterance; determining a received pronunciation attribute based on received audio data corresponding to the spoken utterance; comparing the received pronunciation attribute to at least one of the candidate pronunciation attributes; and selecting a particular pronunciation attribute from the candidate pronunciation attributes based on a result of the comparison of the received pronunciation attribute to at least one of the candidate pronunciation attributes. With the methods, systems, and apparatus, the particular pronunciation attribute, selected from the candidate pronunciation attributes, is provided for outputting audio associated with the spoken utterance.

Claims18

Dependent claims

A method implemented by one or more processors, the method comprising:

receiving, at a shared digital assistant device, a spoken utterance of a user;
determining that the spoken utterance matches a plurality of candidate user profiles;
determining that the spoken utterance corresponds to a command associated with an action to be performed by an assistant of the shared digital assistant device;
determining whether the action to be performed by the assistant must be attributed to a specific user profile;
and
when it is determined that the action to be performed by the assistant must be attributed to a specific user profile:
selecting a particular user profile of the candidate user profiles, wherein selecting the particular user profile comprises:
providing, at a user interface of the shared digital assistant device, a question related to identifying information;
receiving, at the shared digital assistant device, user input responding to the question;
comparing the user input responding to the question to corresponding identifying information for at least one of the plurality of candidate user profiles;
identifying, based on the comparing, the particular user profile, of the plurality of candidate user profiles, as the specific user profile;
and
subsequent to identifying the particular user profile:
attributing the action to the particular user profile;
performing the action associated with the command corresponding to the spoken utterance of the user;
and
providing, at the user interface of the shared digital assistant device, first audio output related to the command, the action, or the attribution;
and
when it is determined that the action to be performed by the assistant need not be attributed to a specific user profile:
providing, at the user interface of the shared digital assistant device, second audio output related to the action or the command.

17 more elements

A system comprising one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:

receiving, at a shared digital assistant device, a spoken utterance of a user;
determining that the spoken utterance matches a plurality of candidate user profiles;
determining that the spoken utterance corresponds to a command associated with an action to be performed by an assistant of the shared digital assistant device;
determining whether the action to be performed by the assistant must be attributed to a specific user profile;
and
when it is determined that the action to be performed by the assistant must be attributed to a specific user profile:
selecting a particular user profile of the candidate user profiles, wherein selecting the particular user profile comprises:
providing, at a user interface of the shared digital assistant device, a question related to identifying information;
receiving, at the shared digital assistant device, user input responding to the question;
comparing the user input responding to the question to corresponding identifying information for at least one of the plurality of candidate user profiles;
identifying, based on the comparing, the particular user profile, of the plurality of candidate user profiles, as the specific user profile;
and
subsequent to identifying the particular user profile:
attributing the action to the particular user profile;
performing the action associated with the command corresponding to the spoken utterance of the user;
and
providing, at the user interface of the shared digital assistant device, first audio output related to the command, the action, or the attribution;
and
when it is determined that the action to be performed by the assistant need not be attributed to a specific user profile in a database:
providing, at the user interface of the shared digital assistant device, second audio output related to the command or the action.

17 more elements

A computer-readable storage device storing instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

receiving, at a shared digital assistant device, a spoken utterance of a user;
determining that the spoken utterance matches a plurality of candidate user profiles;
determining that the spoken utterance corresponds to a command associated with an action to be performed by an assistant of the shared digital assistant device;
determining whether the action to be performed by the assistant must be attributed to a specific user profile;
and
when it is determined that the action to be performed by the assistant must be attributed to a specific user profile:
selecting a particular user profile of the candidate user profiles, wherein selecting the particular user profile comprises:
providing, at a user interface of the shared digital assistant device, a question related to identifying information;
receiving, at the shared digital assistant device, user input responding to the question;
comparing the user input responding to the question to corresponding identifying information for at least one of the plurality of candidate user profiles;
identifying, based on the comparing, the particular user profile, of the plurality of candidate user profiles, as the specific user profile;
and
subsequent to identifying the particular user profile:
attributing the action to the particular user profile;
performing the action associated with the command corresponding to the spoken utterance of the user;
and
providing, at the user interface of the shared digital assistant device, first audio output related to the command, the action, or the attribution;
and
when it is determined that the action to be performed by the assistant need not be attributed to a specific user profile in a database:
providing, at the user interface of the shared digital assistant device, second audio output related to the command or the action.

17 more elements

Dependencies are inferred from the claim text.

Facts

Application: 16/722,942Filed 20 Dec 2019 · continuation
Priority: 29 Dec 2016
Published: US 2020/0243063 A130 Jul 2020
Granted: 3 Aug 2021
Term ends: Not estimatedThe source records don’t support an estimate.

Classification12 codes

G10L 13/02
Speech synthesis; Text to speech systems: methods for producing synthetic speech; Speech synthesisers
G06F 3/167
Sound input; Sound output: audio in a user interface, e.g. using voice commands for navigating, audio feedback
G10L 13/00
Speech synthesis
G10L 15/02
Speech recognition: feature extraction for speech recognition; Selection of recognition unit

Family

Application15/394,104Parent of this continuation · filed 29 Dec 2016
Application15/995,380Parent of this continuation · filed 1 Jun 2018
US 10,013,971 B1Parent of this continuation · filed 3 Jul 2018
US 2020/0243063 A1Pre-grant publication · published 30 Jul 2020
US 10,559,296 B2Parent of this continuation
US 2018/0190262 A1Published application
US 2018/0286382 A1Published application
US 11,081,099 B2This patent

From the US filing history. Foreign family members aren’t listed.