Back to results
US 10,854,188 B2Granted
Synthesized voice selection for computational agents
AssigneeGoogle Inc.
InventorsValerie Nygaard, Bogdan Caprita, Robert Stets, Saisuresh Krishnakumaran, Jason Brant Douglas
Life of this patent
Estimating the term…
Abstract
An example method includes receiving, by a computational assistant executing at one or more processors, a representation of an utterance spoken at a computing device; selecting, based on the utterance, an agent from a plurality of agents, wherein the plurality of agents includes one or more first party agents and a plurality of third-party agents; responsive to determining that the selected agent comprises a first party agent, selecting a reserved voice from a plurality of voices; and outputting synthesized audio data using the selected voice to satisfy the utterance.
Claims20
A method comprising:
- receiving, by a computational assistant executing at one or more processors, a representation of an utterance spoken by a user of a computing device;
- selecting, based on the utterance, an agent from a plurality of agents, wherein the plurality of agents includes one or more first party agents and a plurality of third-party agents;
- responsive to determining that the selected agent comprises a third-party agent, selecting a voice from a plurality of voices for the third-party agent, wherein the selected voice is distinct from a reserved voice, and wherein the reserved voice is associated with the one or more first party agents;
- and
- outputting, by one or more speakers of the computing device and using the selected voice, synthesized audio data, for the third-party agent, to satisfy the utterance;
- subsequent to outputting the synthesized audio data using the selected voice to satisfy the utterance:
- outputting, by one or more of the speakers of the computing device using the reserved voice associated with the one or more first party agents, a request for feedback, from the user of the computing device, about the third-party agent, and
- in response to outputting the request for feedback, receiving a representation of a user sentiment toward the third-party agent;
- and
- updating, in one or more databases and based on the user sentiment, a value that influences whether the third-party agent is selected responsive to future occurrences of the utterance.
7 more elements
A computing system comprising:
- at least one processor;
- and
- at least one memory comprising instructions that when executed, cause the at least one processor to execute an assistant configured to:
- receive, by the assistant, a representation of an utterance spoken by a user of a computing device;
- select, based on the utterance, an agent from a plurality of agents, wherein the plurality of agents includes one or more first party agents and a plurality of third-party agents;
- responsive to determining that the selected agent comprises a third-party agent, select a voice from a plurality of voices for the third-party agent, wherein the selected voice is distinct from a reserved voice, and wherein the reserved voice is associated with the one or more first party agents;
- and
- output, by one or more speakers of the computing device and using the selected voice, synthesized audio data, for the third-party agent, to satisfy the utterance;
- subsequent to outputting the synthesized audio data using the selected voice to satisfy the utterance:
- output, by one or more of the speakers using the reserved voice associated with the one or more first party agents, a request for feedback, from the user, about the third-party agent, and
- in response to outputting the request for feedback, receive a representation of a user sentiment toward the third-party agent;
- and
- update, in one or more databases and based on the user sentiment, a value that influences whether the third-party agent is selected responsive to future occurrences of the utterance.
10 more elements
A non-transitory computer-readable storage medium storing instructions that, when executed, cause one or more processors to execute an assistant configured to:
- receive a representation of an utterance spoken by a user of a computing device;
- select, based on the utterance, an agent from a plurality of agents, wherein the plurality of agents includes one or more first party agents and a plurality of third-party agents;
- responsive to determining that the selected agent comprises a third-party agent, select a voice from a plurality of voices for the third-party agent, wherein the selected voice is distinct from a reserved voice, and wherein the reserved voice is associated with the one or more first party agents;
- and
- output, by one or more speakers of the computing device and using the selected voice, synthesized audio data, for the third-party agent, to satisfy the utterance;
- subsequent to outputting the synthesized audio data using the selected voice to satisfy the utterance:
- output, by one or more of the speakers using the reserved voice associated with the one or more first party agents, a request for feedback, from the user, about the third-party agent, and
- in response to outputting the request for feedback, receive a representation of a user sentiment toward the third-party agent;
- and
- update, in one or more databases and based on the user sentiment, a value that influences whether the third-party agent is selected responsive to future occurrences of the utterance.
7 more elements
Dependencies are inferred from the claim text.