Supercharge Your Innovation With Domain-Expert AI Agents!

Voice processing method and device and electronic equipment

A voice processing and voice frame technology, applied in voice analysis, electrical components, instruments, etc., can solve the problems of increased computing overhead and complexity, transmission network voice information transmission packet loss, bandwidth consumption, etc., to avoid network congestion, Improve voice quality and enhance the effect of data recovery

Pending Publication Date: 2021-03-12
北京融讯科创技术有限公司
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the instability of the transmission network, there will be packet loss in the voice information transmission process, causing the sound to be stuck and discontinuous
[0003] At present, in order to recover data after packet loss, retransmission can be used, but this method requires additional bandwidth consumption, which is easy to cause network congestion, and it is difficult to recover once continuous packet loss occurs
In addition, in real-time voice communication, when a certain delay is exceeded, even if the retransmission arrives, it will be discarded
Using the forward error correction method, there is no need to retransmit the data, but the overhead and complexity of the calculation are increased when encoding and decoding, and the processing power and bandwidth are exchanged for reliability and small reply delay. In the case of high packet loss rate The performance drops significantly under
It is easy to implement using error concealment technology at the receiving end, but the concealment performance is poor and the voice quality is poor

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
  • Voice processing method and device and electronic equipment
  • Voice processing method and device and electronic equipment
  • Voice processing method and device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] figure 1 It is a schematic flow chart of a voice processing method provided by Embodiment 1 of the present invention. This embodiment is applicable to decoding the lost voice frame through the adjacent correct voice frame of the lost voice frame when the voice frame is lost. In the case of , the method can be executed by a speech processing device, and the device can be implemented in the form of software and / or hardware.

[0028] like figure 1 As described, the method of this embodiment specifically includes the following steps:

[0029] S110. When packet loss of a speech frame is detected, determine that the speech frame is a current speech frame and acquire redundant information of a correct speech frame adjacent to the current speech frame.

[0030] Wherein, the correct speech frame adjacent to the current speech frame is the correct speech frame adjacent to the current speech frame before and / or after the current speech frame. The redundant information may inclu...

Embodiment 2

[0037] figure 2 It is a schematic flowchart of a speech processing method provided by Embodiment 2 of the present invention. On the basis of the foregoing embodiments, this embodiment further optimizes the step of "decoding the current speech frame according to redundant information". The explanations of terms that are the same as or corresponding to the above-mentioned embodiments will not be repeated here.

[0038] like figure 2 As shown, the method specifically includes the following steps:

[0039] S210. When packet loss of a speech frame is detected, determine that the speech frame is a current speech frame and acquire redundant information of a correct speech frame adjacent to the current speech frame.

[0040] When acquiring a voice frame, in order to ensure the voice quality, it is necessary to perform packet loss detection on the voice frame. Redundant information of the adjacent correct speech frame, so as to facilitate subsequent packet loss recovery of the cur...

Embodiment 3

[0121] Figure 4 It is a schematic structural diagram of a speech processing device provided in Embodiment 3 of the present invention, and the device includes: a redundant information determination module 310 and a speech decoding module 320 .

[0122] Wherein, the redundant information determining module 310 is used to determine that the speech frame is the current speech frame and determine to obtain the redundant information of the correct speech frame adjacent to the current speech frame when the packet loss of the speech frame is detected; the speech decoding module 320, It is used to decode the current speech frame according to redundant information; wherein the redundant information includes excitation pulse parameters and encoding parameters within a preset transmission duration adjacent to the transmission time of the correct speech frame.

[0123] Optionally, the voice decoding module 320 includes:

[0124] The first correct frame determination submodule is used to ...

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 embodiment of the invention discloses a voice processing method and device and electronic equipment, and the method comprises the steps: determining a voice frame as a current voice frame and obtaining the redundant information of a correct voice frame adjacent to the current voice frame when the packet loss of the voice frame is detected; decoding the current voice frame according to the redundant information, the redundant information comprising an excitation pulse parameter and a coding parameter in a preset transmission duration adjacent to the transmission time of the correct voice frame. According to the technical scheme provided by the embodiment of the invention, the technical problems of large bandwidth consumption and network congestion easily caused by voice frame retransmission and forward error correction coding transmission are solved, a small amount of redundant information is added into part of voice frames to enhance data recovery after packet loss; meanwhile, thetechnical effects of saving bandwidth, avoiding network congestion and improving the voice quality are achieved.

Description

technical field [0001] Embodiments of the present invention relate to audio processing technologies, and in particular, to a voice processing method, device, and electronic equipment. Background technique [0002] In actual voice calls, call quality is mainly affected by network packet loss. Due to the instability of the transmission network, there will be packet loss in the voice information transmission process, causing the sound to be stuck and discontinuous. [0003] At present, in order to restore data after packet loss, retransmission can be used, but this method requires additional bandwidth consumption, which is easy to cause network congestion, and it is difficult to recover once continuous packet loss occurs. In addition, in real-time voice communication, when a certain delay is exceeded, even if the retransmission arrives, it will be discarded. Using the forward error correction method, there is no need to retransmit the data, but the overhead and complexity of ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G10L19/005G10L19/008H04L1/00
CPCG10L19/005G10L19/008H04L1/004H04L1/0042
Inventor 秦永红李勇强
Owner 北京融讯科创技术有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com