Method of assembling messages for speech synthesis

摘要

The invention concerns a method of composing messages for speech output, in particular the improvement of the quality of reproduction of speech outputs of this kind. For this purpose a series of original sentences for messages is segmented. These segments (10) are stored in the form of audio files together with search criteria in a database (11). Additionally to this information further entries (12) are made on the segments (10), in that the length, the position and the transition values for the respective segments (10) are recorded and stored. If a sentence is to be reproduced it is transmitted in a format corresponding to the format of the search criteria. Then an investigation is done into whether the sentence to be reproduced can be fully reproduced by one segment or by a succession of stored segments (10). If this is the case the segments found in each case are examined using their entries (12) as to how far the individual segments match as regards speech rhythm, wherein the audio files of the segments (10) in which the examination resulted in the pre-requisites for optimal maintaining of the natural speech rhythm are then combined and output for reproduction.