Method, apparatus, and equipment for processing voice data, and readable storage medium

Abstract

The invention discloses a method for processing voice data. The method comprises: a frequency spectrogram of a target voice file is obtained and the obtained frequency spectrogram is displayed; a target frequency range selected by a user in the frequency spectrogram is received and corresponding target voice data are determined based on the target frequency range; and the target voice data are extracted, the extracted frequency spectrogram processed, and the frequency spectrogram are played. According to the method, the user is able to select a specific determined frequency range automaticallyaccording to the frequency spectrogram of the target voice file; and because the voice data are selected by the user based on the frequency spectrogram, the selected voice data have the optimized quality; no denoiding process is needed for the voice data, so that the original voice audio quality is not affected and thus the voice audio file is played clearly; and the voice data processing efficiency is improved because of the low selected voice volume. Correspondingly, the invention also discloses an apparatus and equipment for processing voice data, and a readable storage medium that have the same technical effects.

Description

technical field [0001] The present invention relates to the technical field of audio processing, and more specifically, relates to a method, device, equipment and readable storage medium for processing voice data. Background technique [0002] With the continuous development and integration of computer technology and audio processing technology, voiceprint identification technology has been widely used in judicial identification, providing a good technical guarantee for judicial identification. [0003] At present, for the voice spectrogram of the voice file to be authenticated, the existing voiceprint identification system can select the voice spectrogram of a specific area in time. However, since the frequency range of each voice signal is specific and constant, and the existing system cannot select a specific frequency range, it is necessary to select all frequency ranges of the voice data, and when the frequency range of the voice data covers the high-frequency region ,...

AI Technical Summary

Problems solved by technology

However, since the frequency range of each voice signal is specific and constant, and the existing system cannot select a specific frequency range, it is necessary to select all frequency ranges of the voice data, and when the frequency range of the voice data covers the high-frequency region , in the process of noise reduction processing, the quality of the original voice and audio is weakened, resulting in unclear playback of the voice and audio, which affects the results of voiceprint identification; at the same time, due to the large amount of selected voice data, it also reduces Improve the processing efficiency of voice data

Images