| 摘要 |
<p>The invention relates to a method in which an information unit (3) that makes a speech input possible is stored on a server (1) and can be retrieved by a client (2) and the client (2) can be coupled through the communications network (6) to a plurality of speech recognizers (7-9) and a speech input given by a user is applied to at least one speech recognizer (7-9) for generating at least one recognition result (11-13) and the recognition result (11-13) is interpreted in a plurality of independent processes and a plurality of interpretation results (22-24) are generated which are sent to a user. The user then receives in a brief period of time a plurality of qualified information items for which otherwise he would several times have had to make an inquiry in databases by means of a speech input.</p> |
