摘要 |
PURPOSE:To provide convenience for visually handicapped person. CONSTITUTION:The video signal 01 from a television receiver, etc., is converted by a video signal conversion part 1 into digital image data, which are stored in an image memory 2; and character patterns are recognized from the image data in the memory 2 through a character recognition part 3 and converted into character codes, which are stored in a character code memory 5. Then the character codes from the memory 5 are converted by a speech code conversion part 6 into speech codes indicating characters in a document and the speech codes are stored in a speech code memory 8. Then a speech synthesis part 9 converts the speech codes from the memory 8 into a speech signal, which is outputted to a speaker 10. |