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

Double-talk detection method and device, computer equipment and storage medium

A detection method and audio signal technology, applied in speech analysis, instruments, etc., can solve the problem of high false alarm probability, achieve the effect of low false alarm probability and maintain accuracy

Active Publication Date: 2019-12-31
GUANGZHOU SHIYUAN ELECTRONICS CO LTD
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present invention provide a double-talk detection method, device, computer equipment, and storage medium to solve the problem of high false alarm probability caused by using a static threshold value for double-talk 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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Double-talk detection method and device, computer equipment and storage medium
  • Double-talk detection method and device, computer equipment and storage medium
  • Double-talk detection method and device, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] figure 1 It is a flow chart of a double-talk detection method provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation where a threshold value is dynamically set for double-talk detection. This method can be executed by a double-talk detection device. The double-talk The detection device can be implemented by software and / or hardware, and can be configured in computer equipment, such as personal computers, mobile terminals, conference machines, etc., and the computer equipment is equipped with a microphone and a speaker, where the microphone is called a microphone, also known as a microphone 1. Microphone is an energy conversion device that converts sound signals into electrical signals. Loudspeakers, also known as horns, are transducer devices that convert electrical signals into acoustic signals.

[0065] Further, the microphone and the loudspeaker can be independent components, and can also be integrated in the same component,...

Embodiment 2

[0092] figure 2 It is a flow chart of a dual-talk detection method provided by Embodiment 2 of the present invention. This embodiment further refines the processing operations for calculating the average power and the threshold value based on the foregoing embodiments. The method specifically includes the following steps:

[0093] S201. When performing voice communication, receive an audio signal from a microphone.

[0094] Wherein, the audio signal has an echo signal.

[0095] S202. Determine a reference audio signal.

[0096] The reference audio signal belongs to the audio signal and can be used to estimate the power of the echo signal.

[0097] In one case, before the audio signal played by the speaker, the audio signal to be played is collected by an internal circuit, and the audio signal is set as the reference audio signal.

[0098] For the computer equipment at the local end, after the audio signal is played by the speaker, the audio signal reaches the microphone t...

Embodiment 3

[0191] image 3 A schematic structural diagram of a dual-talk detection device provided in Embodiment 3 of the present invention, the device may specifically include the following modules:

[0192] An audio signal receiving module 301, configured to receive an audio signal from a microphone when performing voice communication, the audio signal having an echo signal;

[0193] A first power determining module 302, configured to determine the power of the echo signal;

[0194] Threshold value determination module 303, used for determining the threshold value of the current detection double-talk state according to the power of the echo signal;

[0195] A second power determining module 304, configured to determine the power of the audio signal;

[0196] The double-talk state determining module 305 is configured to determine that the voice communication exists in the double-talk state if the power of the audio signal is greater than the threshold.

[0197] In an embodiment of th...

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 double-talk detection method and device, computer equipment and a storage medium. The method comprises the steps of when voice communication is performed, receiving an audio signal from a microphone, wherein the audio signal has an echo signal; determining the power of the echo signal; determining a threshold value of a current detection double-talk state according to the power of the echo signal; determining the power of the audio signal; and if the power of the audio signal is more than the threshold value, determining that voice communication hasa double-talk state. In combination with statistical characteristics of the echo signal, the method dynamically adapts to sound emitting states of an opposite-end user, and generates a double-talk detection threshold value; when different levels of interference or noise exist in an environment, the method still can adapt to the state of the environment, accuracy of the threshold value can be kept,and thus the condition that a relatively low false alarm probability is kept when the threshold value is used for performing double-talk detection is ensured.

Description

technical field [0001] Embodiments of the present invention relate to audio processing technologies, and in particular, to a double-talk detection method, device, computer equipment, and storage medium. Background technique [0002] In an audio device with both a speaker and a microphone, the audio signal emitted by the speaker is reflected multiple times in the space and reaches the microphone to form an echo signal. [0003] For voice communication such as video conferencing, the echo signal will seriously damage the communication quality and reduce the voice recognition rate, especially in the case of double-talk, in order to ensure the performance of the filter in the double-talk situation, echo cancellation is generally Both include the function of double-speaking detection. [0004] At present, the double-talk detection based on correlation or energy detection uses static threshold value as the basis for judgment. When there are different levels of interference or noi...

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): G10L21/0208G10L21/0216
CPCG10L21/0208G10L21/0216G10L2021/02082G10L2021/02165
Inventor 王亮亮
Owner GUANGZHOU SHIYUAN ELECTRONICS CO LTD