| 摘要 |
The invention provides an apparatus, and a method of use, in which a video input signal 210 is captured. Text elements, such as menu items, are identified from the video signal. The text or a selected text element is recognised and the text used to generate 260 a speech signal. The apparatus comprises video output 215, audio codec 235 to add generated speech to output video 215. The apparatus further comprises CPU 240, system ROM 250, video RAM 252, exceptions dictionary 254 and an infra red detector 270. The speech synthesis further comprises text to speech, TTS, processor 262 and language ROM 264. The apparatus and method may be used to effect an electronic program guide EPG for visually impaired people. |
