Systems and methods for responding to human spoken audio
AssigneeInteractive Voice, Inc.
InventorJonathon Nostrant
Life of this patent
Estimating the term…
Abstract
Systems and methods for responding to human spoken are provided herein. Exemplary methods may include continuously listening, via an intelligent assistant device, for an initiating command. Additionally, the method may include upon receiving the initiating command, continuously listening, via the intelligent assistant device, for an audio command and transmitting the audio command from the intelligent assistant device to a command processing server. The method may also include transmitting the audio command to at least one information source, the audio command having been converted from speech-to-text, receiving at the command processing server, a response from the at least one information source, and transmitting the response from the command processing server to the intelligent assistant device.
Claims20
A method, comprising:
- continuously listening, via a microphone on an intelligent assistant device, for a first audio command, the first audio command being an audio initiating command;
- upon receiving the audio initiating command and processing it on the intelligent assistant device, continuously listening, via the intelligent assistant device, for a second audio command;
- transmitting the second audio command from the intelligent assistant device to a command processing server;
- selecting, by the command processing server, at least one information source Application Programming Interface (API) from a plurality of APIs, for processing the second audio command, the second audio command having been converted from speech-to-text, wherein the selecting is based on at least one of:
- context, category, meaning, and keywords in the converted text of the second audio command;
- transmitting, by the command processing server, the converted text of the second audio command to the selected at least one information source API for processing;
- receiving at the command processing server, a response to the second audio command from the selected at least one information source API, the response provided via a notifications server;
- transmitting the response from the command processing server to the intelligent assistant device;
- and
- outputting the response via the intelligent assistant device.
A device, comprising:
- a first microphone and a second microphone;
- a speaker;
- and
- a processor that executes logic stored in memory to perform operations comprising:
- continuously listening, via the first microphone and the second microphone, for a first audio command, the first audio command being an audio initiating command;
- upon receiving the audio initiating command, continuously listening, via the first microphone and the second microphone, for a second audio command;
- transmitting the second audio command from the device to a command processing server;
- receiving a response to the second audio command from the command processing server, the response provided via a notifications server;
- and
- outputting the response and one or more informational objects via any of a display screen or the speaker of the device.
A system, comprising:
- an intelligent assistant device comprising a processor which executes logic to perform operations comprising:
- continuously listening, via at least one microphone, for a first audio command, the first audio command being an audio initiating command;
- and
- upon receiving the audio initiating command and processing it, continuously listening, via the at least one microphone, for a second audio command;
- and
- a command processing server communicatively coupled with the intelligent assistant device, the command processing server comprising a processor that executes logic to perform operations comprising:
- receiving the second audio command from the intelligent assistant device;
- transmitting the second audio command to at least one information source Application Programming Interface (API) from a plurality of APIs, the second audio command having been converted from speech-to-text;
- receiving at the command processing server, a response to the second audio command from the at least one information source API, the response being provided via a notifications server;
- and
- transmitting the response and one or more informational objects from the command processing server to the intelligent assistant device.
Dependencies are inferred from the claim text.