摘要 |
PROBLEM TO BE SOLVED: To provide a multilingual multipoint videoconferencing system which provides real-time translation of speech by conferees.SOLUTION: Audio streams containing speech may be converted into text (220 and 250) and inserted as subtitles into video streams (250, 240). The speech may also be translated from one language to another language (240), the translated speech is inserted into the video streams. The subtitles are selected or the original audio stream is replaced with speech in the other language generated by a text to speech engine (220, 240 and 250). Different conferees may receive different translations of the same speech on the basis of information provided by each conferee on desired languages (210). |