Text-to-speech converter of a facsimile graphic image

• US 4,996,707 A
• Filed: 02/09/1989
• Issued: 02/26/1991
• Est. Priority Date: 02/09/1989
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Berkeley Speech Technologies, Inc. (Intel Corporation)
• Inventors: Peters, Elisabeth, O'Malley, Sara, O'Malley, Michael H.
• Primary Examiner(s): Ng, Jin F.
• Assistant Examiner(s): Woo, Stella L.
• Application Number:
  US07/308,792
• Time in Patent Office: 747 Days
• Field of Search: 379/100, 379/94, 379/214, 381/41, 381/43, 381/44, 381/52, 358/476, 358/474
• US Class Current: 379/100.13
• CPC Class Codes: H04N 1/00204 with a digital computer or a digital computer system, e.g. an internet server programmed control between transmitter and receiver or between image input and image output device H04N1/32561
• CPC Class Codes: H04N 1/00206 Transmitting or receiving computer data via an image communication device, e.g. a facsimile transceiver H04N1/00236 takes precedence
• CPC Class Codes: H04N 1/4115 involving the recognition of specific patterns, e.g. by symbol matching
• CPC Class Codes: H04N 2201/0068 Converting from still picture data
• CPC Class Codes: H04N 2201/3211 of a company logo or the like
• CPC Class Codes: H04N 2201/3274 Storage or retrieval of prestored additional information
• CPC Class Codes: Y10S 379/903 Password
• CPC Class Codes: Y10S 379/905 Fax mail
• CPC Class Codes: Y10S 379/908 Multimedia

Abstract

A computer system is described that includes a capability to receive and store graphic images from remote facsimile machines. The system includes a software that can convert graphic images of textual material into an ASCII coded file so that either keywords or the coverted text may be converted to speech giving the addressee-user the ability to review incoming facsimiles from a remote telephone. The system includes a relay capability, the capability to print on command and to originate facsimiles either from text files or scanned papers.

Claims

1. A device for converting a graphic image of into spoken words, the graphic image represented by a single string of data composed of an ordered set of pixels, where each pixel may be represented by a binary bit, the device comprising:

computer data means for manipulating strings of data;

storage means for storing the graphic image in binary form as a single string of data, at least some of said graphic image representing written words;

recognition means for recognizing, assembling and processing at least portions of the graphic image into groups of coded characters each coded character represented by a plurality of more than one but less than nine binary bits and each coded character capable of being manipulated as a separate string of data by the computer data means; and

text-to-speech means for converting the groups of coded characters into spoken words.

2. The device of claim 1 further comprising facsimile means for receiving from a remote sender and transmitting to a remote receiver graphic images of textual material.

3. The device of claim 1 further comprising facsimile means for converting binary coded data strings, each string representing a character, into areas of pixels having dimensions of n bits by m bits, said facsimile means further for transmitting said nxm areas of pixels to a remote site.

4. The device of claim 1 further including means to store recorded spoken words and wherein the text-to-speech means includes means for serially mixing recorded spoken words with spoken words obtained from converting groups of coded characters whereby the recorded spoken words and the spoken words obtained from converted groups may sequentially heard.

5. The device of claim 4 wherein the computer means further includes scanner means for optically scanning marked pages and converting the markings into string of binary bits;

processor means for manipulating said strings of binary bits; and

printer means responsive to said processor means for printing pages of said strings of binary bits whereby the printed pages substantially resemble the scanned marked pages.

6. The device of claim 2 further comprising:

logo storage means for storing known images along with a unique identification

logo recognition means for comparing portions of a received facsimile images to known images to identify the remote sender of at least some of the received facsimile images.

7. The device of claim 2 further including keyword means for comparing groups of coded characters converted from graphic images by said recognition means to known groups of coded characters

8. The device of claim 6 further including:

communication means for establishing telephonic communication over telephone circuitry with a human being remotedly located relative to said device; and

notification means responsive to the coded characters converted by said recognition means for activating said communication means to notify a human being remotely located from said device of the presence of said facsimile.

9. The device of claim 1 further including:

communication means for establishing telephonic communication over telephone circuitry with a human being remotedly located relative to said device; and

notification means responsive to the coded characters converted by said recognition means for activating said communication means to notify a human being remotely located from said device of the presence of said facsimile.

10. The device of claim 7 further including:

communication means for establishing telephonic communication over telephone circuitry with a human being remotedly located relative to said device; and

notification means responsive to the coded characters converted by said recognition means for activating said communication means to notify a human being remotely located from said device of the presence of said facsimile.

11. The device of claim 3 further including means to store recorded spoken words and wherein the text-to-speech means includes means for serially mixing recorded spoken words with spoken words obtained from converting groups of coded characters whereby the recorded spoken words and the spoken words obtained from converted groups may sequentially be heard.

26. The device of claim 9 wherein the notification means includes speech means for aurally including at least some of the words of the spoken words obtained from converting the coded characters.

12. A computerized system for converting to the spoken word a series of graphic images of textual material represented by a set pixels, where each pixel represents the presence or absence of shade of gray and wherein each pixel may be represented by a binary code, the computerized system comprising

a processor including operating system means for manipulating binary coded strings of data;

memory means responsive to the processor;

for receiving, storing, and making available to the processor binary coded strings of data;

means for receiving binary representations of a series of graphic images at least some of said graphic images representing written words;

recognition means responsive to the processor for assembling and converting at least a portion of received binary representations of said series of graphic images into coded characters capable of being manipulated by said processor; and

text-to-speech means for converting groups of coded characters into spoken words.

13. The system of claim 12 wherein the text-to-speech means further includes language means responsive to said processor for directing the conversion of groups of words to be accomplished such that the spoken word shall be in a particular language.

14. The system of claim 13 wherein the processor includes means for converting textual matter represented by binary coded characters into a graphic image wherein the binary coded characters are represented by pixels, each pixel being represented by a binary digit.

15. The system of claim 13 wherein the means for receiving binary representations further includes means for transmitting a graphic image to a remote site.

16. The system of claim 15 further including reception means for receiving data from a remote site, said reception means further including means for distinguishing voice communications from binary representation of data.

17. The system of claim 15 further including input means for inputting textual matter in a character by character manner, each of said characters uniquely represented by a group of at least five binary digits;

and

text to graphic conversion means for converting groups of binary digits representing characters to strings of binary digits representing a graphic depiction of the inputted textual matter.

18. The system of claim 12 further comprising facsimile means for receiving from a remote sender and transmitting to a remote receiver images of textual material.

19. The system of claim 18 further comprising:

logo storage means for storing known images along with a unique identification

logo recognition means for comparing portions of a received facsimile images to known images to identify the remote sender of at least some of the received facsimile images.

20. The system of claim 18 further including keyword means for comparing groups of coded characters converted from graphic images by said recognition means to known groups of coded characters.

21. The system of claim 18 further including:

communication means for establishing telephonic communication over telephone circuitry with a human being remotely located relative to said device; and

notification means responsive to the coded characters converted by said recognition means for activating said communication means to notify a human being remotely located from said device of the presence of said facsimile.

22. The system of claim 19 further including:

communication means for establishing telephonic communication over telephone circuitry with a human being remotedly located relative to said device; and

notification means responsive to the coded characters converted by said recognition means for activating said communication means to notify a human being remotely located from said device of the presence of said facsimile.

23. The system of claim 20 further including:

communication means for establishing telephonic communication over telephone circuitry with a human being remotely located relative to said device; and

notification means responsive to the coded characters converted by said recognition means for activating said communication means to notify a human being remotely located from said device of the presence of said facsimile.

24. The system of claim 12 further including:

communication means for establishing telephonic communication over telephone circuitry with a human being remotely located relative to said device; and

notification means responsive to the coded characters converted by said recognition means for activating said communication means to notify a human being remotely located from said device of the presence of said facsimile.

25. The system of claim 24 wherein the notification means includes speech means for aurally including at least some of the words of the spoken words obtained from converting the coded characters.

27. A device for converting a graphic image of textual material represented by a set of pixels where each pixel may be presented in a binary code into spoken words comprising:

computer data means for manipulating strings of data;

first storage means for storing a graphic image in binary form, at least some of said graphic image representing written words;

recognition means for assembly and processing at least portions of the stored graphic image into coded characters each character capable of being manipulated by the computer data means;

second storage means for storing recorded spoken words;

text-to-speech means for converting the groups of coded characters into spoken words; and

,

mixing means for serially mixing recorded spoken words with the spoken words obtained from converting groups of coded characters.

28. A computerized system for converting to spoken words a series of graphic images of textural material represented by a set of pixels, where each pixel represents the presence or absence of a shade of grey and wherein each pixel may be represented by a binary code, the computerized system comprising:

a processor including operating systems means for manipulating binary coded strings of data;

memory means responsive to the processor;

for receiving storing and making available to the processor binary coded strings of date;

means for receiving binary representations of the series of graphic images at least some of said graphic images representing written words;

recognition means responsive to the processor for assembling and converting at least a portion of the received binary representations of said series of graphic images into coded characters capable of being manipulated by said processors;

text-to-speech means for converting groups of coded. characters into spoken words in a particular language;

input means for inputting textual matter in a character by character manner, each of said characters uniquely represented by a group of at least five binary digits;

text-to-graphic conversion means for converting groups of binary digits representing characters to strings of binary digits representing a graphic depiction of the inputed textual matter;

said means for receiving binary representations further including means for transmitting a graphic image to a remote site.