Apparatuses, methods and systems for a text-to-sign language translation platform

• US 8,566,075 B1
• Filed: 05/31/2007
• Issued: 10/22/2013
• Est. Priority Date: 05/31/2007
• Status: Active Grant

• Current Assignee: Icommunicator, LLC
• Original Assignee: Ppr Direct
• Inventors: Bruner, Steve
• Primary Examiner(s): He, Jialong
• Application Number:
  US11/756,298
• Time in Patent Office: 2,336 Days
• Field of Search: 704/2, 704/3, 704/270, 704/271, 704/277, 715/706, 715/865
• US Class Current: 704/2
• CPC Class Codes: G06F 40/55 Rule-based translation
• CPC Class Codes: G09B 21/009 Teaching or communicating with deaf persons G09B21/04 takes precedence; deaf and dumb persons G09B21/00
• CPC Class Codes: G10L 21/10 Transforming into visible information
• CPC Class Codes: H04N 21/234336 by media transcoding, e.g. video is transformed into a slideshow of still pictures or audio is converted into text
• CPC Class Codes: H04N 21/4884 for displaying subtitles
• CPC Class Codes: H04N 21/6582 Data stored in the client, e.g. viewing habits, hardware capabilities, credit card number arrangements where receivers interact with the broadcast H04H20/38

Abstract

The present disclosure details apparatuses, methods, and systems for a text-to-sign language translation platform (“translation platform”). The translation platform enables efficient, real-time processing of written speech elements, such as may be supplied by a Closed Captioning feed, and conversion to sign language video clips that may be output to a video display, such as via an embedded “picture-in-picture” window. The translation platform is configurable to process homographs, synonyms, grammatical context, multiple speakers, tone of voice, and/or the like.

Claims

1. A processor-implemented method for translating information, comprising:

receiving a textual speech input element;

translating the textual speech input element using predefined selection modification criteria;

querying a moving image database for a moving image corresponding the translated textual speech input element;

selecting from the moving image database at least one sign language target image clip based on the translating of the textual speech input element, the at least one sign language target image clip exhibiting continuity promoting images including a figure with hands in a neutral position in opening and closing frames of the sign language target mage clip; and

outputting the at least one sign language target image clip to a display device.

2. The method of claim 1, wherein the translating the textual speech input element using predefined selection modification criteria comprises one or more of:

querying the moving image database for synonymous word correlation of the textual speech input element and the moving image in the moving image database;

querying a thesaurus database for corresponding synonyms of the textual input element using a thesaurus;

querying a grammar engine for improving contextual translation of the textual speech input element;

determining whether a word-drop threshold has been reached;

identifying a gender of a person associated with the textual speech element;

detecting a tone of a person associated with the textual speech input element; and

combinations thereof.

3. The method of claim 2, wherein the identifying the gender of the person associated with the textual speech element results in an outputting the at least one sign language target image clip to a display device of a person of that same gender.

4. The method of claim 2, wherein the detecting the tone of the person associated with the textual speech input element results in an outputting the at least one sign language target image clip to a display device of a predefined color corresponding to a predefined tone.

5. The method of claim 2, wherein if the querying the moving image database for synonymous word correlation of the textual speech input element and the moving image in the moving image database is unsuccessful, the method further comprises retrieving a series of constituent letter and alpha-numeric video elements and aggregating the constituent letter and alpha-numeric video elements as a corresponding moving image element for display;

and outputting the corresponding moving image element for display on the display device.

6. The method of claim 1, wherein the moving image database is selected from a database having:

video recordings of a real person, cartoon figures, computer-generated avatars, and combinations thereof.

7. The method of claim 1, wherein the textual speech input element is derived from a Closed Captioning feed.

8. The method of claim 1, further comprising:

determining whether a timing discrepancy between the textual speech input element and the sign language target image clip exists; and

implementing a timing discrepancy corrective process.

9. The method of claim 8, further comprising:

transitioning back to non-corrective processing, when the timing discrepancy has been corrected.

10. The system of claim 1, further comprising continuously connecting the images in the opening and closing frames via a morphing system to promote the continuity of the images in the opening and closing frames.

11. A processor-implemented method for translating information, comprising:

receiving a textual speech input element;

translating the textual speech input element using predefined selection modification criteria, the selection modification criteria including implementing a word-drop threshold when a timing discrepancy is identified, determining whether the word-drop threshold is reached, and dropping at least one word from the translating of the textual speech input element when the word-drop threshold is reached;

querying a moving image database for a moving image corresponding the translated textual speech input element;

selecting from the moving image database at least one sign language target image clip based on the translating of the textual speech input element; and

outputting the at least one sign language target image clip to a display device.

12. The method of claim 11, wherein the selection modification criteria includes identifying a gender of a person associated with the textual speech element.

13. The method of claim 11, wherein the selection modification criteria includes detecting a tone of a person associated with the textual speech input element.

14. The method of claim 11, wherein the dropping at least one word from the translating of the textual speech input element includes dropping one of every third word, every fifth word, every sixth word, and every eighth word from the translating of the textual speech input element.