High intelligibility voice announcement system

• US 9,558,747 B2
• Filed: 12/10/2014
• Issued: 01/31/2017
• Est. Priority Date: 12/10/2014
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Kore, Vinayak Sadashiv, Berezowski, Andrew G.
• Primary Examiner(s): Neway, Samuel G
• Application Number:
  US14/566,486
• Publication Number:
  US 20160171982A1
• Time in Patent Office: 783 Days
• US Class Current: 1/1
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 13/02 Methods for producing synthetic speech; Speech synthesisers
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04R 2227/009 Signal processing in [PA] systems to enhance the speech intelligibility
• CPC Class Codes: H04R 27/00 Public address systems circuits for preventing acoustic reaction H04R3/02; circuits for distributing signals to loudspeakers H04R3/12; monitoring or testing arrangements for public address systems H04R29/007; amplifiers H03F

Abstract

A high intelligibility voice announcement system is described herein. One system includes an announcement station containing a speech to text engine in which a spoken announcement from a user is converted to text data, wherein any errors are identified and marked in the converted text data and displayed to the user. After the user has corrected any errors, the corrected text data is transmitted to one or more speakers, where a text to speech engine converts the text data to an audible message that is then broadcast via the speakers.

Claims

1. A high intelligibility voice announcement system, comprising:

an announcement station, including;

a speech to text engine configured to convert a spoken announcement from a user to converted text data;

an error recognition engine configured to identify any errors in the converted text data;

a display on the announcement station configured to display the converted text data, wherein;

the identified errors in the converted text data are identified for the user; and

corrected text data is displayed, via the display on the announcement station, in a queue system including other announcements until corrected text data of the spoken announcement is ready to be sent;

an input device allowing the user to correct any identified errors in the converted text data, resulting in the corrected text data;

a number of zones each including one or more speakers; and

a transmitter configured to send the corrected text data to the one or more speakers of the number of zones; and

a text to speech engine configured to convert the corrected text data to an audible message in preparation for broadcast via the one or more speakers, wherein the broadcast of the audible message is delayed via a configurable delay that is different for the one or more speakers in different ones of the number of zones.

2. The high intelligibility voice announcement system of claim 1, wherein the one or more speakers include diagnostic tools configured to determine a length of the configurable delay for the one or more speakers in the number of zones.

3. The high intelligibility voice announcement system of claim 1, wherein the identified errors in the converted text data are corrected using one or more of user speech inputs and a keyboard.

4. The high intelligibility voice announcement system of claim 1, wherein at least one of the speech to text engine or the error recognition engine is located at one of the announcement station or externally at a server connected via the Internet.

5. The high intelligibility voice announcement system of claim 1, wherein the one or more speakers include one or more diagnostic tools configured to prevent broadcasting audible messages during periodic test trials.

6. The high intelligibility voice announcement system of claim 1, wherein the text to speech engine is located at the one or more speakers or externally via a server or Internet connection.

7. The high intelligibility voice announcement system of claim 1, further comprising a network, wherein the one or more speakers are connected to the announcement station via the network.

19. The high intelligibility voice announcement system of claim 1, wherein the configurable delay is selected using one or more of user speech inputs and a keyboard.

8. A method for a high intelligibility voice announcement system, comprising:

converting a spoken announcement from a user to converted text data;

checking the converted text data to identify any errors;

displaying the converted text data via a display, wherein any errors in the converted text data are identified for the user;

correcting any errors in the converted text data resulting in corrected text data;

displaying the corrected text via the display in a queue system that includes other announcements until the corrected text data is transmitted;

transmitting the corrected text data via a network;

receiving the corrected text data at one or more speakers included in a number of zones;

converting the corrected text data to an audible message; and

broadcasting the audible message via a configurable delay via the one or more speakers, wherein the configurable delay is different for the one or more speakers in different ones of the number of zones.

9. The method of claim 8, further comprising at least two zones, wherein the zones each contain a subset of the one or more speakers.

10. The method of claim 8, wherein the corrected text data is transmitted to at least one zone.

11. The method of claim 10, wherein the zones that the text data is transmitted can be selected by the user via an announcement station utilizing one or more of:

a touch screen; and

a retina movement detection system.

12. The method of claim 8, wherein the spoken announcement is converted to converted text data as the user speaks.

13. The method of claim 8, wherein converting the spoken announcement to converted text data includes using announcement situation specific processing.

14. The method of claim 8, wherein the errors include one or more of grammar, logic, spelling, length, context, and language errors.

15. The method of claim 8, wherein an announcement station creates a user configurable delay before transmitting the corrected text data via the network.

16. A high intelligibility voice announcement system, comprising:

a computing device including;

a memory; and

a processor coupled to the memory, wherein the processor is configured to execute executable instructions stored in the memory to;

convert a spoken announcement from a user to converted text data;

identify any errors in the converted text data;

display the converted text data via a display, wherein;

any errors in the converted text data are identified for the user; and

corrected text data is displayed, via the display, in a queue system including other announcements, until corrected text data of the spoken announcement is ready to be transmitted;

correct any identified errors in the converted text data, resulting in the corrected text data; and

transmit the corrected text data via a network; and

a number of zones including one or more speakers that receive the corrected text data, wherein a broadcast of an audible message of the corrected text data is delayed via a configurable delay that is different for the one or more speakers in different ones of the number of zones.

17. The system of claim 16, wherein the one or more speakers convert the corrected text data to an audible message.

18. The system of claim 16, wherein the corrected text data contains a time stamp that controls one or more of a start, stop, or pause of the broadcast of the audible message.