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

Audio code stream compression method and device based on deep learning

A technology of deep learning and compression methods, applied in neural learning methods, speech analysis, instruments, etc., can solve problems such as waste of resources, and achieve the effect of saving resources

Pending Publication Date: 2022-04-26
慧之安信息技术股份有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This encoding method can compress the code stream to a very small size, but it is difficult to restore the uncompressed complete code stream from the compressed code stream, so when the complete code stream is needed, the complete code stream can only be retransmitted, which brings waste of some resources

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 code stream compression method and device based on deep learning
  • Audio code stream compression method and device based on deep learning
  • Audio code stream compression method and device based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] Exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present application can be more thoroughly understood, and the scope of the present application can be fully conveyed to those skilled in the art.

[0056] It should be noted that the terms "first" and "second" in the description and claims of the present application and the above drawings are used to distinguish similar objects, but not necessarily used to describe a specific sequence or sequence. It is to be understood that such terms are interchangeable under appropriate circumstances such that the embodiments of the application described herein can be prac...

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 provides an audio code stream compression method and device based on deep learning, and relates to the technical field of audio data processing. According to the method, code streams compressed by using a deep learning algorithm are subjected to reverse restoration, and the restoration degrees of the code streams before and after the compression and restoration of the deep learning algorithm are compared; performing optimization iteration on compression and reduction of the deep learning algorithm according to the reduction degree until the reduction degree reaches a preset threshold value after all the audio code streams are compressed and reduced by the deep learning algorithm, and recording the number of times of optimization iteration in the optimization iteration process; and judging whether the deep learning algorithm needs to be replaced or not according to the number of optimization iterations, and further performing compression processing on the audio code stream by using the deep learning algorithm obtained by judgment. Therefore, according to the embodiment of the invention, the uncompressed code stream can be restored through the trained deep learning algorithm framework, so that the condition of retransmission when the code stream with complete quality is needed is omitted, and resources are saved.

Description

technical field [0001] The present application relates to the technical field of audio data processing, and in particular to a deep learning-based audio stream compression method and device. Background technique [0002] The current audio compression method is mainly based on the shielding effect and the hearing range of the human ear to remove the shielded sound and the sound that the human ear cannot hear. This encoding method can compress the code stream to a very small size, but it is difficult to restore the uncompressed complete code stream from the compressed code stream, so when the complete code stream is needed, the complete code stream can only be retransmitted, which brings A waste of some resources. Therefore, it is urgent to solve this technical problem. Contents of the invention [0003] In view of the above problems, this application is proposed to provide a deep learning-based audio stream compression method and device that overcomes the above problems o...

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): G10L19/16G06N3/08
CPCG10L19/167G06N3/08
Inventor 兰雨晴黄永琢余丹王丹星唐霆岳
Owner 慧之安信息技术股份有限公司