Mixing method, device, and equipment and storage medium

A sound mixing and audio streaming technology, applied in speech analysis, speech recognition, instruments, etc., can solve the problem of volume reduction and achieve clear human voice, good practicability, and good user experience

Active Publication Date: 2019-02-26
苏州谦问万答吧教育科技有限公司
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The present invention provides a sound mixing method, device, equipment and storage medium, which can effectively solve the problem

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
  • Mixing method, device, and equipment and storage medium
  • Mixing method, device, and equipment and storage medium
  • Mixing method, device, and equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] figure 1 It is a flow chart of the audio mixing method provided in Embodiment 1. This method is applicable to online voice scenarios such as multi-party conference calls or network conferences. It can be executed by software / hardware deployed on the server or client, such as figure 1 As shown, a mixing method provided in this embodiment includes:

[0048] S102. Receive at least two channels of audio stream data.

[0049] Receive the audio stream data of all channels in the working state in a conference call or web conference.

[0050] S104. Detect the types of the audio stream data of all channels through the pre-trained vocal detection model, so as to identify the audio stream data of the vocal channel and the audio stream data of the noise channel.

[0051] The pre-trained human voice detection model in this embodiment is preferably but not limited to the GMM model based on Gaussian probability density function, the SVM model based on vector machine, the DNN model b...

Embodiment 2

[0069] figure 2 It is a flow chart of the sound mixing method provided by the implementation of the present invention, such as figure 2 As shown, with respect to the foregoing embodiments, the mixing method provided by this embodiment further includes:

[0070] S1051. Determine whether the human voice channel audio stream data is smaller than a preset adjustment amplitude.

[0071] S1052. If yes, normalize the human voice channel audio stream data to the first preset amplitude range, so as to update the human voice channel audio stream data.

[0072] Within the preset time interval, when the maximum amplitude of the human voice channel audio stream data is lower than the preset adjustment amplitude, the human voice channel audio stream data is normalized to the first preset amplitude range, Increase the amplitude of the human voice channel audio stream data, thereby increasing the amplitude of the human voice channel audio stream data before mixing, and increasing the ampl...

Embodiment 3

[0080] image 3 It is a flow chart of the sound mixing method provided by the implementation of the present invention, such as image 3 As shown, in order to better improve the human voice in the result mixing data, with respect to the foregoing embodiments, this embodiment preferably further includes:

[0081] S1053. Determine whether the difference between the amplitude of the human voice channel audio stream data and the noise channel audio stream data is within a preset amplitude difference range.

[0082] S1054. If so, normalize the human voice channel audio stream data to the second preset amplitude range to update the human voice channel audio stream data; normalize the noise channel audio stream data to the third preset The amplitude range is set to update the audio stream data of the noise channel, wherein the second preset amplitude range is greater than the third preset amplitude range.

[0083] In this embodiment, after the human voice channel audio stream data a...

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 a mixing method, device, and equipment and a storage medium. The mixing method comprises the following steps that: audio stream data of at least two paths of sound channels arereceived; types of audio stream data of all sound channels are detected by using a pre-trained vocal detection model to identify vocal channel audio stream data and noise channel audio stream data; mixing is carried out on the vocal channel audio stream data to generate vocal mixing data; mixing is carried out on the noise channel audio stream data to generate noise mixing data; and then mixing is carried out on the vocal mixing data and the noise mixing data to generate result mixing data. According to the embodiment of the invention, the vocal channel audio stream data and noise channel audio stream data are distinguished by using the pre-trained vocal detection model, mixing is carried out on the two kinds of data, and then the mixing results are superpose to generate the result mixingdata, so that the amplitude of the vocal audio stream data in the result mixing data is highlighted and thus the vocal sound after mixing becomes clear. Therefore, the practicability and the user experience are improved.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of sound mixing, and in particular, to a sound mixing method, device, equipment, and storage medium. Background technique [0002] In a VOIP conference call, there are multiple people involved in the conversation, and in order for one receiver to hear everyone else's voice, everyone else's audio stream needs to be mixed. The audio mixing processing function is set on the server side, which can save bandwidth and reduce the computing pressure on the client, but it will increase the computing pressure on the server, which is suitable for many people to participate in the session at the same time; No pressure, suitable for a small number of people to talk at the same time. [0003] No matter which end the sound mixing is placed on, it is necessary for the listener to clearly hear the voice of the speaker. The classic sound mixing algorithm in the prior art is a linear superposition al...

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): G10L21/007G10L21/02G10L21/0272G10L21/0316G10L25/84G10L15/14G10L15/16G10L15/18H04S3/00
CPCG10L21/0202G10L15/14G10L15/16G10L15/18G10L21/007G10L21/0272G10L21/0316G10L25/84H04S3/008
Inventor 吴威麒张凯磊
Owner 苏州谦问万答吧教育科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap