Voice synthesis method

Abstract

The invention relates to the field of vehicle-mounted terminals, in particular to a voice synthesis method. The voice synthesis method includes the following steps that audio information of the same parts in broadcast voice information are respectively recorded, thus audio files of the same parts are produced and stored. Audio information of different parts in the broadcast voice information are respectively recorded, thus audio files of different parts are produced and stored. Corresponding audio files of the same parts are read and / or corresponding audio files of different parts are read. The audio files of the same parts and / or the audio files of different parts are respectively decoded, thus audio data of the same parts and audio data of different parts are obtained. The audio data of the same parts and the audio data of different parts are matched according to voice playing requirements. A new file header is set up for the matched audio data. The audio data are decoded, thus broadcast audio files are produced. According to the voice synthesis method, the problems that space is occupied and the playing of the voice is not smooth are solved. Resources are saved. Voice broadcast quality is improved.

Description

technical field [0001] The invention relates to the field of vehicle-mounted terminals, in particular to a speech synthesis method. Background technique [0002] Existing vehicle-mounted terminals generally include a station announcement system. Before arriving at the corresponding station, the station announcement is made. When leaving the current station, it prompts the next station to be arrived. Since the names of the stations are different, one way is to record them separately Multiple station announcement audio files corresponding to the station name are broadcast, and the corresponding information is searched for broadcast according to the current station announcement requirements, and a large storage space is required, which is inconvenient to use. Another way is to record the same part of the audio and different parts of the audio file separately. Find and arrange the required audio files to play sequentially according to the station reporting requirements, but due ...

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to provide a speech synthesis method to solve the problem of poor broadcast quality caused by the use of continuous audio files in the prior art, which takes up a large space and uses separate recording methods for voice broadcasts not smooth.

[0005] The beneficial effects of the present invention are: after using the speech synthesis method of the present invention, since the same part of the audio files and different parts of the audio files are used to record separately and the audio files are spliced ​​according to the broadcasting requirements, both the problem of space occupation and the problem of space occupation are solved. Voice playback is not smooth, which not only saves resources, but also improves the quality of voice broadcast

Images