Unlock instant, AI-driven research and patent intelligence for your innovation.

Audio data classification method, device and equipment and storage medium

A technology of audio data and classification method, applied in audio data clustering/classification, audio data retrieval and other directions, can solve the problems of heavy workload and low accuracy, and achieve the effect of improving classification accuracy

Pending Publication Date: 2020-12-11
GUANGZHOU QUWAN NETWORK TECH CO LTD
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] This application provides a classification method, device, equipment and storage medium for audio data, which solves the technical problems of heavy workload and low accuracy in existing audio classification methods

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Audio data classification method, device and equipment and storage medium
  • Audio data classification method, device and equipment and storage medium
  • Audio data classification method, device and equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] Embodiments of the present application provide an audio data classification method, device, device, and storage medium, which solve the technical problems of heavy workload and low accuracy in existing audio classification methods.

[0052]In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiment of the application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiment of the application. Obviously, the described embodiment is only It is a part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0053] see figure 1 , a schematic flowchart of Embodiment 1 of a method for classifying audio data in the embodiment of the pr...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an audio data classification method, device and equipment and a storage medium, and the method comprises the steps: in response to an audio classification instruction, obtaining to-be-classified audio data; performing audio detection on the to-be-classified audio data frame by frame to obtain the percentage of non-voice data in the to-be-classified audio data; obtaining a pre-classification result of the to-be-classified audio data according to the percentage, a special sound threshold and an invalid sound threshold; classifying the to-be-classified audio data accordingto a preset determination condition of sound classification corresponding to the pre-classification result to obtain a classification result of the to-be-classified audio data. By pre-classifying theto-be-classified audio data in the whole classification process, and correcting the pre-classification result in combination with the pre-classification result and the corresponding preset determination condition, the classification accuracy is improved, extra training, marking and other operations are not needed, and therefore the technical problems that an existing audio classification method is high in workload and not high in accuracy rate are solved.

Description

technical field [0001] The present application relates to the technical field of voice classification, in particular to a method, device, device and storage medium for classifying audio data. Background technique [0002] In audio apps, there are scenarios where users record audio, especially in audio social apps. Users hope to meet new friends through audio and socialize based on audio. However, the user's recording behavior is uncontrollable. For example, a new user just wants to try a certain function and does not speak during the recording. At this time, the audio card obtained is an "invalid" audio card without valid information, or in the APP platform. Special audio cards with small noises, noises, etc. If users always hear audio without valid information, it will affect the product experience. In order to improve the user experience, the APP platform needs to screen the audio data and clear the audio without valid information. During the screening process, the audio...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F16/65
CPCG06F16/65
Inventor 熊佳谢欲强徐志坚
Owner GUANGZHOU QUWAN NETWORK TECH CO LTD