Method and device for the rapid pattern recognition-supported transcription of spoken and written utterances

摘要

The invention relates to a method and a device for transcribing spoken and written utterances. For this purpose, the utterances are subjected to speech or text recognition and the recognition result (ME) for obtaining the transcription is combined with a manually created transcription (MT) of the utterances. The additional information made available by the combination through the recognition result (ME) enables the transcriber to work relatively roughly and thus quickly in manual transcription. For example, when using a keyboard (25), he can limit himself to hitting the keys on only one keyboard line and / or omit some keystrokes entirely. In addition, manual transcribing can also be accelerated by proposing expected continuations (31) of the previously entered text (30) based on the recognition result (ME).