Image-to-speech system

• US 8,694,321 B2
• Filed: 03/11/2010
• Issued: 04/08/2014
• Est. Priority Date: 03/12/2009
• Status: Active Grant

• Current Assignee: Speaks4me Limited
• Original Assignee: Speaks4me Limited
• Inventors: Lodge, Stephen Anthony
• Primary Examiner(s): Saint Cyr, Leonard
• Application Number:
  US12/721,872
• Publication Number:
  US 20100231752A1
• Time in Patent Office: 1,489 Days
• Field of Search: None
• US Class Current: 704/271
• CPC Class Codes: G09B 21/001 Teaching or communicating with blind persons G09B21/02 - G09B21/06 take precedence
• CPC Class Codes: G10L 13/027 Concept to speech synthesisers; Generation of natural phrases from machine-based concepts generation of parameters for speech synthesis out of text G10L13/08

Abstract

Apparatus for communicating includes a processor, a memory, a storage, a display, a manual input arrangement and audio output. Image data elements are stored in the storage and the processor is configured to output a plurality of the image data elements to the display, receive manual input selecting at least one of the image data elements and receive manual input indicating that selection is completed. For each selected image data element, the processor produces and outputs a further data element.

Claims

1. Apparatus for communicating, comprising a processor, a memory, a storage, a display and a manual input arrangement, wherein image data elements are stored in said storage and said processor is configured to:

output a plurality of said image data elements to said display;

output a plurality of empty slots to said display;

process at least two manual inputs, wherein for each said manual input said processing comprises;

receiving said manual input, wherein said manual input selects at least one of said image data elements and drags said selected image data element to one of said empty slots, and

displaying said selected image data element in said slot, and

arranging said image data elements in a desired sequential order in a group in at least two said empty slots;

receive a further manual input indicating that a selection is completed; and

for each group of said selected image data elements, produce and output a further data element as an originally generated formed sentence structure in real time, formed by said sequential ones of said image data elements in said desired sequential order, wherein said sentence structure is output in the order in which said selected image data elements are displayed in said slots.

2. Apparatus according to claim 1, wherein said apparatus further comprises an audio output, each said further data element is an audio data element that represents a spoken word relevant to said image data element, and each said audio data element is output to said audio output.

3. Apparatus according to claim 2, wherein for each of said image data elements a name is stored, and for each said selected image data element, said processor is configured to produce an audio data element by converting the name of said image data element to speech.

4. Apparatus according to claim 2, wherein audio data elements are stored in said storage and each of said image data elements is associated with an audio data element, and for each said selected image data element, said processor is configured to produce an audio data element by retrieving an associated audio data element from storage.

5. Apparatus according to claim 1, wherein for each of said image data elements a name is stored, and said apparatus further comprises a network connection, each said further data element is a name of each said image data element, and said names are combined to produce a message that is output via said network communication.

6. Apparatus according to claim 1, wherein said processor is further configured to receive a manual input indicating a language, and wherein each said further data element is in said language.

7. Apparatus according to claim 1, further comprising a camera and an audio input, wherein said processor is further configured to:

receive an image data element via said camera;

receive an audio data element via said audio input;

store said data elements in said storage; and

store, in said storage, an indication that said data elements are associated with each other.

8. Apparatus according to claim 1, wherein each of said image data elements belongs to a category, and said processor is configured to display image data elements of the same category together.

9. Apparatus according to claim 1, wherein said processor is configured to store information regarding frequency of use of said image data elements.

10. Apparatus according to claim 9, wherein said processor is further configured to alter the prominence of displayed image data elements relative to their frequency of use.

11. Apparatus according to claim 10, wherein text data elements are stored in said storage, each said text data element being associated with an image data element, and said processor is further configured to, when outputting an image data element to said display:

retrieve the text data element associated with said image data element;

retrieve a frequency of use parameter for said image data element; and

output said text data element to said display as an overlay on said image data element, wherein the amount of transparency of said overlay is inversely relative to said frequency of use parameter.

12. Apparatus according to claim 11, wherein said processor is further configured to alter the transparency of said image data element relative to said frequency of use parameter.

13. A method of communication, comprising:

storing image data elements;

displaying a plurality of said image data elements;

displaying a plurality of empty slots;

processing at least two manual inputs, wherein for each said manual input said processing step comprises;

receiving said manual input, wherein said manual input selects at least one of said image data elements and drags said selected image data element to one of said empty slots, and

displaying said selected image data element in said slot;

arranging said image data elements in a desired sequential order in a group in at least two said empty slots;

receiving a further manual input indicating that selection is completed; and

for each group of said selected image data elements, producing and outputting a further data element as an originally generated formed sentence structure in real time, formed by said sequential ones of said image data elements in said desired sequential order, wherein said sentence structure is output in the order in which said selected image data elements are displayed in said slots.

14. A method according to claim 13, wherein each said further data element is an audio data element that represents a spoken word relevant to said image data element, further comprising the step of outputting each said audio data element to an audio output.

15. A method according to claim 14, further comprising the step of storing a name for each of said image data elements, and for each said selected image data element, said step of producing an audio data element is performed by converting the name of said image data element to speech.

16. A method according to claim 13, further comprising the step of storing a name for each of said image data elements, wherein for each image data element, said step of producing said further data element comprises retrieving the name of said image data element, further comprising the step of combining said names to produce a message that is output via a network communication.

17. A method according to claim 13, further comprising the step of receiving an indication of a language, and wherein each said further data element is in said language.

18. A method according to claim 13, further comprising the step of storing information regarding frequency of use of said image data elements.

19. A method according to claim 18, further comprising the step of altering the prominence of displayed image data elements relative to their frequency of use.

20. A method according to claim 19, further comprising the step of storing text data elements, each said text data element being associated with an image data element, and said step of displaying an image data element comprises:

retrieving the text data element associated with said image data element;

retrieving a frequency of use parameter for said image data element; and

displaying said text data element as an overlay on said image data element, wherein the amount of transparency of said overlay is inversely relative to said frequency of use parameter.

21. A method according to claim 20, further comprising the step of altering the transparency of said image data element relative to said frequency of use parameter.

22. A non-transitory computer-readable medium having computer-readable instructions executable by a computer, such that when executing said instructions a computer will:

store image data elements;

display a plurality of said image data elements;

display a plurality of empty slots;

process at least two manual inputs, wherein for each said manual input said processing step comprises;

receiving said manual input, wherein said manual input selects at least one of said image data elements and drags said selected image data element to one of said empty slots, and

displaying said selected image data element in said slot;

arranging said image data elements in a desired sequential order in a group in at least two said empty slots;

receive a further manual input indicating that selection is completed; and

for each group of said selected image data elements, produce and play an audio data element that represents spoken words relevant to said image data elements as an originally generated formed sentence structure in real time, formed by said sequential ones of said image data elements in said desired sequential order, wherein said sentence structure is output in the order in which said selected image data elements are displayed in said slots.