Voice command-driven database

• US 9,983,849 B2
• Filed: 02/24/2017
• Issued: 05/29/2018
• Est. Priority Date: 07/07/2016
• Status: Active Grant

• Current Assignee: Intelligently Interactive, Inc.
• Original Assignee: Intelligently Interactive, Inc.
• Inventors: Weingartner, Eric H.
• Primary Examiner(s): Neway, Samuel G
• Application Number:
  US15/441,742
• Publication Number:
  US 20180011685A1
• Time in Patent Office: 459 Days
• CPC Class Codes: G06F 2203/0381 Multimodal input, i.e. interface arrangements enabling the user to issue commands by simultaneous use of input devices of different nature, e.g. voice plus gesture on digitizer
• CPC Class Codes: G06F 3/038 Control and interface arrangements therefor, e.g. drivers or device-embedded control circuitry
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 3/0483 Interaction with page-structured environments, e.g. book metaphor
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence
• CPC Class Codes: G06F 3/0488 using a touch-screen or digitiser, e.g. input of commands through traced gestures
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 9/453 Help systems
• CPC Class Codes: G10L 13/02 Methods for producing synthetic speech; Speech synthesisers
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
• 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

Abstract

A voice command-driven system and computer-implemented method are disclosed for selecting a data item in a list of text-based data items stored in a database using a simple affirmative voice command input without utilizing a connection to a network. The text-based data items in the list are converted to speech using an embedded text-to-speech engine and an audio output of a first converted data item is provided. A listening state is entered into for a predefined pause time to await receipt of the simple affirmative voice command input. If the simple affirmative voice command input is received during the predefined pause time, the first converted data item is selected for processing. If the simple affirmative voice command input is not received during the predefined pause time, an audio output of a next converted data item in the list is provided.

Claims

1. A mobile device news reader, comprising:

at least one processor;

at least one database coupled to the at least one processor;

a text-to-speech engine embedded in the mobile device and executable by the at least one processor to convert text data stored in the at least one database to a speech-based output;

a speech-to-text engine embedded in the mobile device and executable by the at least one processor to process a voice command input received from a user of the device and generate data in the form of text that corresponds to the received voice command input; and

non-transient memory coupled to the at least one processor that stores program instructions, which, when executed by the at least one processor, cause the at least one processor to;

receive text-based news articles and text-based headlines associated with the news articles over a network from a remote server,

store an identification of a single, unique, system-wide, and context-independent voice command input for use to select text-based news articles for output by the speech-to-text engine, to select menu options, and to modify output settings,

store a list of the received news articles correlated with a list of the received headlines in the at least one database, and

without utilizing a connection to the network,

retrieve the list of headlines from the at least one database,

enter a first list-pause cycle comprising;

a list-pause that comprises;

 

outputting, via the text-to-speech engine, a headline from the list of received headlines; and

 

a pause of a predetermined length of time;

repeating the list-pause, each repetition of the list-pause outputting a different next headline from the list of received headlines, until determining that the single, unique, system-wide, and context-independent voice command input has been spoken during the pause of a most recent list-pause; and

responsive to determining that the single, unique, system-wide, and context-independent voice command input has been spoken during the pause of the most recent list-pause, outputting, via the text-to-speech engine, at least a portion of the news article from the sequence of news articles correlated with the headline output during that most recent list-pause;

enter a second list-pause cycle comprising;

a list-pause comprising;

 

outputting, via the text-to-speech engine, an identifier of a menu option; and

 

a pause of a predetermined length of time;

repeating the list-pause, each repetition of the list-pause outputting a different next identifier of a menu option, until that the single, unique, system-wide, and context-independent voice command input has been spoken during the pause of a most recent list-pause; and

responsive to determining that the single, unique, system-wide, and context-independent voice command input has been spoken during the pause of the most recent list-pause, navigating to a different menu or mode of the news reader associated with the identifier output during that list-pause; and

enter a third list-pause cycle comprising;

a list-pause comprising;

 

outputting, via the text-to-speech engine, an identifier of an output setting; and

 

a pause of a predetermined length of time;

repeating the list-pause, each repetition of the list-pause outputting a different next identifier of an output setting, until determining that the single, unique, system-wide, and context-independent voice command input has been spoken during the pause of a most recent list-pause; and

responsive to determining that the single, unique, system-wide, and context-independent voice command input has been spoken during the pause of the most recent list-pause, modifying an output setting of the text-to-speech engine to match a setting associated with the identifier output during that list-pause.

2. The mobile device news reader of claim 1, wherein the text-based headlines are received from one or more news feeds.

3. The mobile device news reader of claim 1, wherein the program instructions are further configured to cause the at least one processor to:

generate and output a first listen tone when entering a pause of a list-pause.

4. The mobile device news reader of claim 1, further comprising:

a display screen coupled to the at least one processor; and

wherein the program instructions are further configured to cause the at least one processor to provide a visual display of voice commands available to the user on the display screen.

5. The mobile device news reader of claim 4, wherein the visual display identifies active voice commands available to the user at a current stage within the program instructions.

6. The mobile device news reader of claim 5, wherein the visual display includes text of each active voice command available to the user.

7. The mobile device news reader of claim 6, wherein the display screen is a pressure-sensitive touch screen and each active voice command identified in the visual display is a virtual button configured to generate a signal indicating a selection of one of the active voice commands identified on the touch screen when the user applies pressure on the touch screen in the vicinity of the button associated with the one of the active voice commands.

8. A voice-command driven method for controlling a news reader device, comprising:

receiving, using at least one processor, text-based news articles and text-based headlines associated with the news articles over a network from a remote server;

storing, using the at least one processor, an identification of a single, unique, system-wide, and context-independent voice command input for use to select text-based news articles for output by the speech-to-text engine, to select menu options, and to modify output settings,

storing, using the at least one processor, a list of the received news articles correlated with a list of the received headlines in at least one database coupled to the at least one processor in the device, and

without utilizing a connection to the network,

retrieving, using the at least one processor, the list of headlines from the at least one database,

entering a first list-pause cycle comprising;

a list-pause that comprises;

outputting, via the text-to-speech engine, a headline from the list of received headlines; and

a pause of a predetermined length of time;

repeating the list-pause, each repetition of the list-pause outputting a different next headline from the list of received headlines, until determining that the single, unique, system-wide, and context-independent voice command input has been spoken during the pause of a most recent list-pause; and

responsive to determining that the single, unique, system-wide, and context-independent voice command input has been spoken during the pause of the most recent list-pause, outputting, via the text-to-speech engine, at least a portion of the news article from the sequence of news articles correlated with the headline output during that most recent list-pause;

entering a second list-pause cycle comprising;

a list-pause comprising;

outputting, via the text-to-speech engine, an identifier of a menu option; and

a pause of a predetermined length of time;

repeating the list-pause, each repetition of the list-pause outputting a different next identifier of a menu option, until that the single, unique, system-wide, and context-independent voice command input has been spoken during the pause of a most recent list-pause; and

responsive to determining that the single, unique, system-wide, and context-independent voice command input has been spoken during the pause of the most recent list-pause, navigating to a different menu or mode of the news reader associated with the identifier output during that list-pause; and

enter a third list-pause cycle comprising;

a list-pause comprising;

outputting, via the text-to-speech engine, an identifier of an output setting; and

a pause of a predetermined length of time;

repeating the list-pause, each repetition of the list-pause outputting a different next identifier of an output setting, until determining that the single, unique, system-wide, and context-independent voice command input has been spoken during the pause of a most recent list-pause; and

responsive to determining that the single, unique, system-wide, and context-independent voice command input has been spoken during the pause of the most recent list-pause, modifying an output setting of the text-to-speech engine to match a setting associated with the identifier output during that list-pause.

9. The voice-command driven method of claim 8, wherein the text-based headlines are received from one or more news feeds.

10. The voice-command driven method of claim 8, further comprising:

generating and outputting a first listen tone, using the at least one processor, when entering into a pause of a list-pause cycle.

11. The voice-command driven method of claim 8, further comprising:

providing a visual display of voice commands available to the user on a display screen coupled to the at least one processor.

12. The voice-command driven method of claim 11, wherein the visual display identifies active voice commands available to the user at a current operating state of the device.

13. The voice-command driven method of claim 12, wherein the visual display includes text of each active voice command available to the user.

14. The voice-command driven method of claim 13, wherein the display screen is a pressure-sensitive touch screen and each active voice command identified in the visual display is a virtual button configured to generate a signal indicating a selection of one of the active voice commands identified on the touch screen when the user applies pressure on the touch screen in the vicinity of the button associated with the one of the active voice commands.