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

Speech signal processing method, device, system and storage medium

A voice signal processing and voice signal technology, applied in voice analysis, instruments, etc., can solve the problems of low receiving end answering accuracy, high system overhead, poor voice compensation effect, etc. Accurate, computationally lightweight effects

Active Publication Date: 2022-07-01
北京汇金春华科技有限公司
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application provides a voice signal processing method, device, system, and storage medium, which can solve the problem of low answering accuracy at the receiving end due to large system overhead and poor voice compensation effect

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
  • Speech signal processing method, device, system and storage medium
  • Speech signal processing method, device, system and storage medium
  • Speech signal processing method, device, system and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] Embodiments of the present application provide a voice signal processing method, device, system, and storage medium, which can solve the problems of high system overhead and poor voice compensation effect resulting in low answering accuracy at the receiving end.

[0046] The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It is to be understood that data so used can be interchanged under appropriate circumstances so that the embodiments described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having" and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily lim...

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 present application provides a voice signal processing method, by converting a preset length historical voice signal into a first frequency domain signal; determining the first frequency domain based on the frequency point voiced amplitude values ​​of different fundamental frequencies and the corresponding threshold amplitude values The candidate fundamental audio point in the signal; in the case that the candidate fundamental audio point exists in the first frequency domain signal, the frequency point corresponding to the candidate fundamental audio point is divided in the first frequency domain signal The amplitude is set to zero to obtain a second frequency domain signal; a target voiced signal is determined based on the second frequency domain signal; and a speech compensation signal is generated according to the target voiced signal. The signal is analyzed from the frequency domain level. Based on the quasi-periodicity of the voiced signal, the frequency points of the voiced signal are determined by the voiced amplitude of each frequency point, and the frequency points that do not contain the voiced signal or the weaker voiced signal are filtered out. The noise signal and unvoiced signal are filtered out, the final voiced signal is closer to the real situation, the accuracy of the voiced signal estimation is improved, and the calculation amount is relatively light, which solves the problem that the voice signal packet loss compensation in the existing algorithm requires a large amount of calculation. .

Description

technical field [0001] The present application relates to the technical field of speech signal processing, and in particular, to a speech signal processing method, device, system and storage medium. Background technique [0002] For VoIP calls, if there is no data to be played in the voice buffer, packet loss compensation is required, that is, the current data is generated from historical data. Otherwise, the peer end will obviously feel that the sound is discontinuous. The general packet loss compensation scheme first calculates the pitch period of the signal from the historical signal, then uses the voiced signal at the historical moment as the current voiced signal, and then superimposes the unvoiced signal and background noise as the voice signal output. [0003] Since the data signal when calculating the pitch period also includes the unvoiced signal and noise, this will have a certain impact on the result; in addition, the related calculation amount is large, which wil...

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 Patents(China)
IPC IPC(8): G10L21/0208G10L21/0232
CPCG10L21/0208G10L21/0232
Inventor 张斌易鑫
Owner 北京汇金春华科技有限公司