Audio data processing method and device, equipment and storage medium

Abstract

The invention relates to an artificial intelligence technology, and discloses an audio data processing method, device and equipment and a storage medium, and the method comprises the steps: obtaining audio data of each preset character in a preset audio format, converting the audio data into binary data, and obtaining a corresponding frame number; if the frame number of the character binary data is greater than or equal to 3, cutting the binary data into a head part, a middle part and a tail part by adopting a preset cutting mode; taking the binary data corresponding to the middle part as pronunciation frames of the corresponding characters, associating the pronunciation frames with the corresponding characters, and storing the pronunciation frames and the corresponding characters locally; after the service data is obtained, determining the number level of the service data, and obtaining to-be-processed data corresponding to the service data based on the number level; obtaining characters in to-be-processed data, obtaining pronunciation frames associated with the characters in the to-be-processed data locally, and splicing the corresponding pronunciation frames in sequence to obtain first audio data. According to the invention, the audio data corresponding to the data part can be timely and smoothly broadcasted.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to an audio data processing method, device, equipment and storage medium. Background technique [0002] For voice broadcasting in different scenarios, in order to reduce labor costs, the text-to-speech (TTS) broadcasting method is currently used to broadcast the content or information that needs to be broadcasted. For the voice broadcast of data, known schemes include the following two types: [0003] The first is to send the data part, such as 12345.67 yuan, to the middle station, call the corresponding word conversion service, and play the audio of the processed data. The disadvantage of this method is that if a large amount of data is requested to be transcribed in each time period, the middle station will be subjected to high concurrent processing, and the requested data and downloaded data will be very large, which will easily cause delays in voice broa...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that since the minimum playback time of the audio file is 1 second, the interval between each digit after splicing the audio is long, which makes the voice of the data part of the broadcast incoherent and affects the experience

Images