Systems and methods for facilitating communications involving hearing-impaired parties

• US 7,315,612 B2
• Filed: 11/02/2004
• Issued: 01/01/2008
• Est. Priority Date: 11/04/2003
• Status: Expired due to Fees

• Current Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Original Assignee: Verizon Business Global LLC (Verizon Communications Inc.)
• Inventors: McClelland, William A.
• Primary Examiner(s): WOO, STELLA L
• Application Number:
  US10/979,093
• Publication Number:
  US 20050094777A1
• Time in Patent Office: 1,155 Days
• Field of Search: 379/52, 379/93.15, 379/93.35, 379/93.09, 379/93.17, 379/93.21, 379/93.23, 379/93.24, 379/93.34, 379/90.01, 379/218.02, 379/207.02, 704/206, 704/227, 370/352
• US Class Current: 379/52
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 2207/18 wireless networks
• CPC Class Codes: H04M 3/42391 where the subscribers are hearing-impaired persons, e.g. telephone devices for the deaf
• CPC Class Codes: H04M 7/006 Networks other than PSTN/ISDN providing telephone service, e.g. Voice over Internet Protocol (VoIP) , including next generation networks with a packet-switched transport layer H04L65/00 takes precedence; aspects not specific to the type of network H04M3/00; special services in those networks H04M3/42
• CPC Class Codes: H04M 7/12 for working between exchanges having different types of switching equipment, e.g. power-driven and step by step or decimal and non-decimal

Abstract

A method for providing communication services for communications between a hearing-impaired party and a hearing party includes establishing a voice link with the hearing party. The method also includes receiving a voice message from the hearing party via the voice link and generating a text message corresponding to the voice message using voice recognition. The method may also include transmitting the text message to the hearing-impaired party. Optionally, a high speed text input device may also be used with, or instead of, the voice recognition to generate the text message.

Claims

1. A method for providing communication services for communications between a hearing-impaired party and a hearing party, comprising:

establishing a voice link with the hearing party;

receiving a first voice message from the hearing party via the voice link;

identifying the hearing party based on a telephone number associated with the hearing party;

accessing at least one stored file based on the identified hearing party, the at least one stored file including a plurality of words and a plurality of corresponding corrections made by an operator in previous voice messages from the hearing party;

generating a first text message corresponding to the first voice message using voice recognition and the at least one stored file, wherein the generating a first text message includes;

identifying, in the first voice message, one of the plurality of words stored in the at least one stored file, and

using one of the plurality of corrections corresponding to the identified one of the plurality of words as the most likely word for the identified one of the plurality of words voiced in the first voice message; and

transmitting the first text message to the hearing-impaired party.

2. The method of claim 1, further comprising:

receiving a second text message from the hearing-impaired party;

generating a second voice message corresponding to the second text message using text-to-voice software; and

transmitting the second voice message to the hearing party.

3. The method of claim 1, further comprising:

reading, by a communication assistant, the first text message; and

modifying, by the communication assistant, the first text message based on the received first voice message before transmitting the first text message to the hearing-impaired party.

4. The method of claim 1, wherein the at least one stored file comprises a voice file.

5. The method of claim 1, further comprising:

simultaneously transmitting the first text message and the first voice message to the hearing-impaired party.

6. The method of claim 1, wherein the at least one stored file comprises:

a file storing rules or grammars associated with speech of the hearing party.

7. A method for providing communication services for communications between a first party and a second party, comprising:

establishing a voice link with the first party;

receiving a first voice message from the first party via the voice link;

identifying the first party based on at least one of automatic number identification or a telephone number provided by the second party;

accessing at least one stored voice file associated with the identified first party, the at least one stored voice file including a plurality of words and a plurality of corresponding corrections made by an operator in previous voice messages from the first party;

generating a first text message corresponding to the first voice message using voice recognition and the at least one stored voice file; and

transmitting the first text message to the second party.

8. The method of claim 7, wherein the identifying the first party comprises identifying the first party based on automatic number identification.

9. A system, comprising:

a server configured to;

receive a call from a hearing-impaired party for establishing a communication link to a hearing party,

identify a communication assistant, and

forward the call to the identified communication assistant; and

a first device associated with the identified communication assistant, the first device being configured to;

receive the forwarded call from the server,

establish a voice link with the hearing party,

identify at least one stored file associated with the hearing party the at least one stored file comprising a plurality of words and a plurality of corresponding corrections made to the plurality of words in previous calls to or from the hearing party,

receive a voice message from the hearing party, and

generate a text message corresponding to the voice message using voice recognition and the at least one stored file, wherein the generating a text message includes;

identifying, in the voice message, one of the plurality of words stored in the at least one stored file, and

using one of the plurality of corrections corresponding to the identified one of the plurality of words as the most likely word for the one of the plurality of words voiced in the voice message.

10. The system of claim 9, wherein the first device is further configured to:

transmit the text message to the hearing-impaired party.

11. The system of claim 10, wherein the first device comprises a workstation associated with the identified communication assistant.

12. The system of claim 9, wherein the first device is further configured to:

receive text messages from the hearing-impaired party, and

generate voice messages corresponding to the text messages using text-to-voice software.

13. The system of claim 9, wherein the at least one stored file associated with the hearing party comprises a voice file.

14. The system of claim 9, wherein when identifying the at least one stored file, the first device is configured to:

identify the hearing party using automatic number identification or identify the hearing party based on a telephone number provided by the hearing-impaired party.

15. The system of claim 14, wherein when identifying the at least one stored file, the first device is further configured to:

identify the at least one stored file based on the identified hearing party.

16. The system of claim 9, wherein the at least on stored file comprises:

a file storing rules or grammars associated with speech of the hearing party.

17. A system comprising:

a server configured to;

receive a call from a hearing-impaired party for establishing a communication link to a hearing party,

identify a communication assistant, and

forward the call to the identified communication assistant; and

at least one device associated with the identified communication assistant, the at least one device being configured to;

receive the forwarded call from the server,

establish a voice link with the hearing party,

receive a voice message from the hearing party, and

execute voice recognition software to generate a text message corresponding to the voice message; and

a memory configured to store voice files associated with a plurality of parties, wherein when generating the text message, the at least one device is configured to;

identify the hearing party based on a telephone number associated with the hearing party,

access at least one stored voice file associated with the identified hearing party. the at least one stored voice file comprising a plurality of words and a plurality of corresponding corrections associated with previous voice messages,

determine, using the at least one stored voice file, whether one of the words in the voice message corresponds to a word in the at least one stored voice file, and

automatically provide, in the text message, the correction corresponding to the one of the words when one of the words in the voice message corresponds to a word in the at least one stored voice file.

18. The system of claim 17, wherein when identifying the hearing party, the at least one device is configured to identify the hearing party using automatic number identification.

19. A method for providing communications services, comprising:

receiving a call from a hearing-impaired party for establishing a communication link to a hearing party;

identifying a communication assistant;

forwarding the call to the identified communication assistant;

establishing, by the communication assistant, a voice link with the hearing party;

receiving, by the communication assistant, a voice message from the hearing party via the voice link;

identifying the hearing party based on a telephone number associated with the hearing party;

accessing at least one stored file associated with the identified hearing party, the at least one stored file comprising a plurality of words and a plurality of corrections made in previous voice messages from the hearing party;

generating, by the communication assistant, a text message corresponding to the voice message using a high speed text input device and the at least one accessed file; and

transmitting the text message to the hearing-impaired party.

20. The method of claim 19, wherein the high speed text input device comprises a communication access real-time translation device.

21. The method of claim 19, wherein the high speed text input device comprises a stenographic input device and the generating a text message includes automatically converting output of the stenographic input into readable text representing the voice message.

22. The method of claim 19, further comprising:

transmitting the voice message to the hearing-impaired party simultaneously with the text message.

23. The method of claim 19, wherein the at least one stored file comprises:

a file storing rules or grammars associated with speech of the hearing party.

24. A system, comprising:

means for establishing a voice link with a first party;

means for receiving a voice message from the first party via the voice link;

means for identifying the first party based on a telephone number associated with the first party;

means for accessing at least one stored file associated with the first party;

means for automatically generating a text message corresponding to the voice message using the at least one stored file, the at least one stored file comprising a plurality of words and a plurality of corrections made in previous voice messages from the first party; and

means for transmitting the text message to a second party.

25. The system of claim 24, wherein the second party represents a hearing-impaired party and the means for automatically generating a text message comprises voice recognition software.

26. A system, comprising:

processing logic configured to;

receive a voice message from a first party,

identify the first party based on a telephone number associated with the first party,

access at least one stored file associated with the identified first party, the at least one stored file comprising a plurality of words and a plurality of corresponding corrections made in previous voice messages from the first party, and

generate a text message corresponding to the voice message using voice recognition and the at least one stored file; and

a transmit element configured to transmit the text message to a hearing-impaired party.

27. The system of claim 26, further comprising:

an output device for displaying the text message prior to transmitting the text message.

28. The system of claim 26, further comprising:

a telephone device configured to receive a telephone call from the hearing-impaired party and establish a bridge connection with the first party.

29. The system of claim 26, wherein the at least on stored file comprises:

rules associated with performing voice recognition for the first party or a voice file associated with the first party.

30. A method, comprising:

receiving a first voice message from a hearing party via a voice link;

identifying the hearing party based on a telephone number associated with the hearing party;

accessing at least one stored file associated with the identified hearing party, the at least one stored file comprising a plurality of words and a plurality of corresponding corrections made in previous voice messages from the hearing party;

generating at least one of a second voice message or a first text message corresponding to the first voice message using voice recognition and the at least one stored file; and

transmitting the at least one of the second voice message or first text message to the hearing party for verification.

31. The method of claim 30, further comprising:

transmitting a prompt to the hearing party providing instructions for verifying that the at least one of the second voice message or first text message is correct.

32. The method of claim 30, further comprising:

receiving an indication from the hearing party that the at least one of the second voice message or first text message is correct; and

transmitting the first text message to a hearing-impaired party.

33. The method of claim 30, further comprising:

receiving an indication from the hearing party that the at least one of the second voice message or first text message is not correct;

generating at least one of a third voice message or a second text message corresponding to the first voice message; and

transmitting the at least one of the third voice message or second text message to the hearing party for verification.

34. The method of claim 33, further comprising:

receiving an indication from the hearing party that the at least one of the third voice message or the second text message is not correct; and

requesting that the hearing party repeat the first voice message.

35. The method of claim 30, wherein the at least one stored file comprises:

a file storing rules associated with performing voice recognition for the identified hearing party or a voice file associated with the identified hearing party.

36. A system, comprising:

processing logic configured to;

receive a first voice message from a hearing party via a voice link,

identify the hearing party based on a telephone number associated with the hearing party,

access at least one stored file associated with the identified hearing party, the at least one stored file comprising a plurality of words and a plurality of corresponding corrections made in previous voice messages from the hearing party,

generate at least one of a second voice message or a first text message corresponding to the first voice message using voice recognition and the at least one stored file, and

transmit the at least one of the second voice message or first text message to the hearing party for verification.

37. The system of claim 36, wherein the processing logic is further configured to:

transmit instructions for verifying that the at least one of the second voice message or first text message is correct.

38. The system of claim 36, wherein the processing logic is further configured to:

receive an indication from the hearing party that the at least one of the second voice message or first text message is correct, and

transmit the first text message to a hearing-impaired party.

39. The system of claim 36, wherein the processing logic is further configured to:

receive an indication from the hearing party that the at least one of the second voice message or first text message is not correct,

generate at least one of a third voice message or a second text message corresponding to the first voice message, and

transmit the at least one of the third voice message or second text message to the hearing party for verification.

40. The system of claim 39, wherein the processing logic is further configured to:

receive an indication from the hearing party that the at least one of the third voice message or the second text message is not correct, and

transmit a request that the hearing party repeat the first voice message.