Responding to Human Spoken Audio Based on User Input

• US 20170046124A1
• Filed: 10/27/2016
• Published: 02/16/2017
• Est. Priority Date: 01/09/2012
• Status: Abandoned Application

• Current Assignee: Interactive Voice, Inc.
• Original Assignee: Interactive Voice, Inc.
• Inventors: Nostrant, Jonathon
• Application Number:
  US15/336,714
• Publication Number:
  US 20170046124A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/16 using artificial neural networks
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/226 using non-speech characteristics
• CPC Class Codes: G10L 2021/02082 the noise being echo, reverberation of the speech
• CPC Class Codes: G10L 21/00 Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility G10L19/00 takes precedence
• CPC Class Codes: G10L 21/0208 Noise filtering

Abstract

Systems and methods for responding to human spoken are provided herein. Exemplary methods may include receiving audio input for generating a speech signal using at least one microphone communicatively coupled to an intelligent assistant device. The method may also include transmitting the audio input from the intelligent assistant device to a natural language processor, the audio input having been converted from speech to a text query. The method may further include processing the text query using artificial intelligence (AI) logic, determining an Application Programming Interface (API) from a plurality of APIs for processing the text query, and transmitting a response from the API to the intelligent assistant device or another device communicatively coupled to the intelligent assistant device for output.

Claims

1. A system comprising:

an intelligent assistant device comprising a processor which executes logic to perform operations comprising;

receiving audio input for generating a speech signal using at least one microphone communicatively coupled to the intelligent assistant device; and

a natural language processor communicatively coupled with the intelligent assistant device that executes logic to perform operations comprising;

receiving the audio input from the intelligent assistant device;

converting the audio input from speech to a text query;

processing the text query using artificial intelligence (AI) logic;

determining an Application Programming Interface (API) from a plurality of APIs for processing the text query; and

transmitting a response from the API to the intelligent assistant device or another device communicatively coupled to the intelligent assistant device for output.

2. The system of claim 1, wherein the natural language processor further uses machine learning to analyze a string of text.

3. The system of claim 1, wherein the natural language processor uses a neural network to analyze the string of text.

4. The system of claim 1, wherein the natural language processor interprets and learns from patterns and behaviors of a user, attributing data to the patterns and behaviors such that a response to a future command from the user can be automatically generated by the intelligent assistant device.

5. The system of claim 1, wherein the intelligent assistant device acts as a base station connected to at least one enabled device such that the audio input received by the intelligent assistant device is used to adjust an operation of the connected at least one enabled device.

6. The system of claim 5, wherein the at least one enabled device receives data to transmit to or from the intelligent assistant device.

7. The system of claim 5, wherein the at least one enabled device is connected to the intelligent assistant device via Bluetooth.

8. The system of claim 5, wherein the at least one enabled device comprises a smartphone comprising:

at least one microphone for receiving audio commands;

at least one user input interface;

a mobile application for processing audio and user input commands; and

a natural language processor for performing automatic speech recognition of the audio commands.

9. The system of claim 5, wherein the at least one enabled device comprises at least one smart home device.

10. The system of claim 5, wherein the at least one smart home device receives commands from a general server connected to the intelligent assistant device.

11. The system of claim 1, wherein the intelligent assistant device utilizes digital signal processing to separate background noise in the audio input.

12. The system of claim 1, wherein the intelligent assistant device includes indicators that provide interactive feedback.

13. A method, comprising:

receiving audio input for generating a speech signal using at least one microphone communicatively coupled to an intelligent assistant device;

transmitting the audio input from the intelligent assistant device to a natural language processor;

converting the audio input from speech to a text query using the natural language processor;

processing the text query using artificial intelligence (AI) logic using the natural language processor;

determining an Application Programming Interface (API) from a plurality of APIs for processing the text query using the natural language processor; and

transmitting a response from the API to the intelligent assistant device or another device communicatively coupled to the intelligent assistant device for output using the natural language processor.

14. The method of claim 13, further comprising processing the text query using machine learning to analyze a string of text using the natural language processor.

15. The method of claim 13, further comprising processing the text query using a neural network to analyze the string of text using the natural language processor.

16. The method of claim 13, further comprising connecting the intelligent assistant device to at least one enabled device such that the audio input received by the intelligent assistant device is used to adjust an operation of the connected at least one enabled device.

17. The method of claim 16, wherein the at least one enabled device receives data to transmit to or from the intelligent assistant device

18. The method of claim 16, wherein the at least one enabled device comprises a smartphone comprising:

at least one microphone for receiving audio commands;

at least one user input interface;

a mobile application for processing audio and user input commands; and

a natural language processor for performing automatic speech recognition of the audio commands.

19. The method of claim 16, wherein the at least one enabled device comprises at least one smart home device that receives commands from a general server connected to the intelligent assistant device.

20. An interactive device, comprising:

at least one microphone;

at least one speaker; and

a processor that executes logic stored in memory to perform operations comprising;

receiving audio input for generating a speech signal using the at least one microphone;

transmitting the audio input from the device to a natural language processor;

receiving a response to the audio input from a server; and

outputting the response.