| 摘要 |
A data processing system which vocalizes text information on a web page, applying an appropriate modification to the original text, depending on the genre of that web page content. A call reception unit accepts a call signal from a user's telephone set. A speech recognition unit recognizes the user's verbal message received from the telephone set. When a request for a particular web page is recognized by the speech recognition unit, a web page data collector makes access to the requested web page to obtain its web page data. A keyword extractor then extracts a predetermined keyword from the obtained web page data. A replacement unit locates a character string that is associated with the extracted keyword, and modifies the text of the web page data by replacing the located character string with another character string. Finally, a vocalizer performs a text-to-speech conversion for at least a part of the resultant text which has been modified by the replacement unit. |
