A dual-speak state detection method, device, storage medium and terminal equipment
A state detection and detection result technology, applied in two-way sound reinforcement telephone systems, voice analysis, instruments, etc., can solve the problem of poor dual-talk state detection effect, etc., to improve the elimination precision, improve the accuracy, and improve the call experience. Effect
Active Publication Date: 2021-10-29
普联国际有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
This method relies on the echo cancellation effect of the adaptive filter, but the echo cancellation effect of the adaptive filter depends on the effect of the dual-talk state detection, that is, the two depend on each other, so there are often situations where the two become worse at the same time, namely Incorrect dual-talk state detection causes adaptive filtering to update in the wrong direction, which in turn leads to worse dual-talk state detection
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0058] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
[0059] The embodiment of the present invention provides a dual-speak state detection method, see figure 2 As shown, it is a flowchart of a preferred embodiment of a double-speaking state detection method provided by the present invention, and the method includes steps S11 to S14:
[0060] Step S11, acquiring the frequency domain signal of the microphone at the first end and the frequency domain signal of the speaker at the second end respectively;
[0061] Step S...
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
Login to View More Abstract
The invention discloses a dual-speak state detection method, device, storage medium and terminal equipment, comprising: separately acquiring the frequency domain signal of the microphone at the first end and the frequency domain signal of the speaker at the second end; Perform voice activity detection to obtain the detection result of the frequency domain signal of the speaker at the second end; if the detection result of the frequency domain signal of the speaker at the second end is that there is a voice signal at the second end, then calculate the frequency of the microphone at the first end respectively. The first spectral energy of the domain signal and the second spectral energy of the frequency domain signal of the second-end loudspeaker; judge the double-talk state according to the difference between the first spectral energy and the second spectral energy; the present invention according to the first terminal The difference in spectrum energy between the frequency domain signal of the microphone and the frequency domain signal of the speaker at the second end is used to determine the double-talk status, which improves the accuracy of the double-talk status detection results, thereby improving the accuracy of echo cancellation and improving the user's call experience.
Description
technical field [0001] The invention relates to the technical field of voice signal processing, in particular to a dual-speak state detection method, device, storage medium and terminal equipment. Background technique [0002] In a duplex call, see figure 1 , the microphone at the far end A collects the voice signal and transmits the voice signal to the speaker at the near end B for playback, and the microphone at the near end B collects the voice signal just broadcasted by the speaker at the near end B, and transmits it to the speaker at the near end B. Broadcast to the speaker of remote A, causing remote A to say a word, and then hear what he just said from the speaker after a while, thus affecting the user's call experience. [0003] In order to improve the user's call experience, the echo cancellation system is set to eliminate the echo. At present, the echo cancellation system includes a dual-talk state detection module and an adaptive filter module. However, the adapt...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): H04M9/08G10L21/0224G10L21/0232G10L25/18G10L25/60
CPCG10L21/0224G10L21/0232G10L25/18G10L25/60G10L2021/02082H04M9/08
Inventor 陈英博
Owner 普联国际有限公司