Echo cancellation system and method, display equipment and computer readable storage medium

Abstract

The invention discloses an echo cancellation system and method, a display device and a computer readable storage medium, and the system comprises an audio signal generator which is used for generating a first calibration audio signal; the pickup module is used for receiving the first calibration audio signal output by the loudspeaker to obtain a second calibration audio signal; a delay determination module connected with the pickup module and used for determining a target delay parameter based on the first calibration audio signal and the second calibration audio signal; and the echo cancellation module is connected with the delay determination module and the pickup module, and is used for performing echo cancellation processing on the to-be-processed audio signal output by the pickup module based on the target delay parameter and the original audio signal to obtain a target audio signal. The system provided by the invention can be used for accurately measuring the delay parameter and improving the accuracy of echo cancellation.

Description

Technical Field

[0001] The present application relates to the field of speech processing technology, and in particular to an echo cancellation system, method, display device and computer-readable storage medium. Background Art

[0002] With the rapid development of speech recognition and voice control technologies, voice interaction systems have been widely used in smart homes, car systems, conference systems and other fields. In practical applications, far-field voice interaction systems face many challenges, one of the most significant of which is that the sound emitted by the local system is collected by the microphone to form echo interference, affecting the normal collection of external human voices. Therefore, echo cancellation technology is needed to eliminate the influence of the sound emitted by the local system on the collection of external human voices when the microphone is collecting sound.

[0003] Traditional echo cancellation methods mainly rely on adaptive filtering technology to eliminate echo signals in the echo path by sampling the electrical signal output by the speaker or sampling the audio signal before the audio signal amplifier. Since the echo path in the far-field environment is long and complex, it is difficult for traditional adaptive filters to accurately estimate and eliminate all echo components, resulting in poor echo cancellation effect. Summary of the invention

[0004] The embodiments of the present application provide an echo cancellation system, method, display device, and computer-readable storage medium, which can accurately measure delay parameters and improve the accuracy of echo cancellation.

[0005] The technical solution adopted by the present invention to solve the problem is as follows:

[0006] In one aspect, the present application provides an echo cancellation system, comprising:

[0007] An audio signal generator, configured to generate a first calibration audio signal;

[0008] An audio signal processing module, configured to transmit a first calibration audio signal to a speaker;

[0009] A sound pickup module, used for receiving a first calibration audio signal output by the speaker to obtain a second calibration audio signal;

[0010] A delay determination module, connected to the sound pickup module and the audio signal processing module, for determining a target delay parameter based on the first calibration audio signal and the second calibration audio signal;

[0011] The echo cancellation module is connected to the delay determination module, the sound pickup module and the audio signal processing module, and is used to perform echo cancellation processing on the audio signal to be processed collected by the sound pickup module based on the target delay parameter and the original audio signal output by the audio signal processing module to obtain the target audio signal.

[0012] In some embodiments of the present application, the delay determination module includes:

[0013] A first filtering unit, connected to the audio signal processing module, configured to filter the first calibration audio signal to obtain a third calibration audio signal;

[0014] A second filtering unit, connected to the sound pickup module, configured to filter the second calibration audio signal to obtain a fourth calibration audio signal;

[0015] The delay determination unit is connected to the first filtering unit and the second filtering unit, and is used to determine a target delay parameter based on the third calibration audio signal and the fourth calibration audio signal.

[0016] In some embodiments of the present application, the third calibration audio signal and the fourth calibration audio signal each include a plurality of third calibration audio signals and the plurality of fourth calibration audio signals correspond one to one, respectively, and the delay determination unit includes:

[0017] A first determining unit, configured to perform phase comparison between each third calibration audio signal and a fourth calibration audio signal corresponding to each third calibration audio signal, to obtain a plurality of first delay parameters;

[0018] The second determining unit is used to calculate and process the multiple first delay parameters to obtain a target delay parameter.

[0019] In some embodiments of the present application, the echo cancellation module includes:

[0020] A delay processing unit, connected to the delay determination module and the audio signal processing module, for performing delay processing on the original audio signal output by the audio signal processing module based on the target delay parameter to obtain a first audio signal;

[0021] The echo cancellation unit is connected to the delay processing unit and the sound pickup module, and is used to perform echo cancellation processing on the audio signal to be processed collected by the sound pickup module based on the first audio signal to obtain a target audio signal.

[0022] In some embodiments of the present application, the audio signal processing module includes: an audio signal processing unit, an audio sampling unit, and an audio signal output unit;

[0023] The audio signal processing unit is connected to the audio signal generator, the audio sampling unit and the audio signal output unit, and is used to transmit the first calibration audio signal and the original audio signal to the audio sampling unit and the audio signal output unit;

[0024] The audio sampling unit is connected to the delay determination module and the echo cancellation module, and is used to transmit the first calibration audio signal to the delay determination module and transmit the original audio signal to the echo cancellation module;

[0025] The audio signal output unit is used to transmit the first calibration audio signal and the original audio signal to the speaker, so as to output the first calibration audio signal and the original audio signal through the speaker.

[0026] In some embodiments of the present application, the echo cancellation system further includes:

[0027] The audio recognition module is connected to the echo cancellation module and is used to recognize and process the target audio signal to obtain target recognition information.

[0028] In a second aspect, an embodiment of the present invention further provides an echo cancellation method, comprising:

[0029] generating a first calibration audio signal by an audio signal generator;

[0030] transmitting a first calibration audio signal to a speaker;

[0031] Receiving a first calibration audio signal output by a speaker to obtain a second calibration audio signal;

[0032] Determining a target delay parameter based on the first calibration audio signal and the second calibration audio signal;

[0033] The audio signal to be processed is subjected to echo cancellation processing based on the target delay parameter and the original audio signal to obtain a target audio signal.

[0034] In some embodiments of the present application, determining a target delay parameter based on the first calibration audio signal and the second calibration audio signal includes:

[0035] Performing filtering processing on the first calibration audio signal to obtain a third calibration audio signal;

[0036] Performing filtering processing on the second calibration audio signal to obtain a fourth calibration audio signal;

[0037] A target delay parameter is determined based on the third calibration audio signal and the fourth calibration audio signal.

[0038] In some embodiments of the present application, the third calibration audio signal and the fourth calibration audio signal each include a plurality of third calibration audio signals and the plurality of fourth calibration audio signals correspond one to one respectively;

[0039] Determining a target delay parameter based on the third calibration audio signal and the fourth calibration audio signal includes:

[0040] Performing phase comparison on each third calibration audio signal and a fourth calibration audio signal corresponding to each third calibration audio signal to obtain a plurality of first delay parameters;

[0041] The plurality of first delay parameters are calculated and processed to obtain a target delay parameter.

[0042] In some embodiments of the present application, performing echo cancellation processing on the audio signal to be processed based on the target delay parameter and the original audio signal to obtain the target audio signal includes:

[0043] Performing delay processing on the original audio signal based on the target delay parameter to obtain a first audio signal;

[0044] The audio signal to be processed is subjected to echo cancellation processing based on the first audio signal to obtain a target audio signal.

[0045] In a third aspect, the present application further provides a display device, the display device comprising the echo cancellation system of any one of the first aspects.

[0046] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and the computer program is loaded by a processor to execute the steps in any one of the echo cancellation methods in the second aspect.

[0047] The beneficial effects of the present invention are as follows: a first calibration audio signal is generated by an audio signal generator, the first calibration audio signal output by a speaker is received by a sound pickup module to obtain a second calibration audio signal, and a target delay parameter is determined based on the first calibration audio signal and the second calibration audio signal, so that the delay parameter can be accurately measured; based on the target delay parameter and the original audio signal, echo cancellation processing is performed on the audio signal to be processed output by the sound pickup module, so that the sound signal actively emitted by the display device in the audio signal to be processed collected by the sound pickup module can be identified and eliminated, and only the audio signal not actively emitted by the display device is retained, thereby improving the accuracy of echo cancellation. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0049] Figure 1 This is a first structural block diagram of the echo cancellation system provided by an embodiment of the present invention;

[0050] Figure 2 is a second structural block diagram of the echo cancellation system provided by an embodiment of the present invention;

[0051] Figure 3 is a third structural block diagram of the echo cancellation system provided by an embodiment of the present invention;

[0052] Figure 4 is a fourth structural block diagram of the echo cancellation system provided by an embodiment of the present invention;

[0053] Figure 5 is a fifth structural block diagram of the echo cancellation system provided by an embodiment of the present invention;

[0054] Figure 6 is a sixth structural block diagram of the echo cancellation system provided by an embodiment of the present invention;

[0055] Figure 7 It is a flowchart of the echo cancellation method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0057] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, features defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the features.

[0058] In this application, the word "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described in this application as "exemplary" is not necessarily to be construed as being preferred or advantageous over other embodiments. The following description is given to enable any technician in the field to implement and use the present application. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present application can be implemented without using these specific details. In other instances, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present application with unnecessary details. Therefore, the present application is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0059] The embodiments of the present application provide an echo cancellation system, method, display device, and computer-readable storage medium, which are described in detail below.

[0060] See also Figure 1 , Figure 1The scene diagram of the echo cancellation system provided in the embodiment of the present application includes an audio signal generator 10, an audio signal processing module 20, a sound pickup module 30, a delay determination module 40 and an echo cancellation module 50. Among them, the audio signal generator 10 is used to generate a first calibration audio signal; the audio signal processing module 20 is used to transmit the first calibration audio signal to the speaker 60; the sound pickup module 30 is used to receive the first calibration audio signal output by the speaker 60 to obtain a second calibration audio signal; the delay determination module 40 is connected to the sound pickup module 30 and the audio signal processing module 20, and the delay determination module 40 is used to determine the target delay parameter based on the first calibration audio signal and the second calibration audio signal; the echo cancellation module 50 is connected to the delay determination module 40, the sound pickup module 30 and the audio signal processing module 20, and the echo cancellation module 50 is used to perform echo cancellation processing on the audio signal to be processed collected by the sound pickup module based on the target delay parameter and the original audio signal output by the audio signal processing module to obtain the target audio signal. In this embodiment, the audio signal generator 10 generates a first calibration audio signal, the pickup module 30 receives the first calibration audio signal output by the speaker 60 to obtain a second calibration audio signal, and then determines the target delay parameter based on the first calibration audio signal and the second calibration audio signal, so that the delay parameter can be accurately measured.

[0061] In a specific embodiment, the echo cancellation system is applied to a display device, such as a television, a projector, a computer, etc. The original audio signal is a sound signal actively emitted by the display device, and the audio signal to be processed is an ambient audio signal collected by the sound pickup module 30, which includes the original audio signal output by the display device through the speaker 60 and the voice signal sent by the user to the terminal device. This embodiment performs echo cancellation processing on the audio signal to be processed collected by the sound pickup module 30 based on the target delay parameter and the original audio signal, and can identify and eliminate the sound signal actively emitted by the display device in the audio signal to be processed collected by the sound pickup module 30, and only retain the audio signal that is not actively emitted by the display device (i.e., the voice signal sent by the user to the terminal device), which can improve the accuracy of echo cancellation and reduce the computational complexity compared to the traditional echo cancellation method that relies on adaptive filtering technology.

[0062] Optionally, the target delay parameter can be determined during the period from when the display device is powered on to when it is in normal operation, or can be determined during the normal operation of the display device. When the target delay parameter is determined during the period from when the display device is powered on to when it is in normal operation, the frequency range of the first calibration audio signal can be selected from any frequency range according to the response frequency range of the speaker 60 or the pickup module 30; when the target delay parameter is determined during the normal operation of the display device, in order to avoid the first calibration audio signal affecting the normal use of the display device, the frequency range of the first calibration audio signal is a frequency range that is inaudible to the human ear, for example, the frequency range of the first calibration audio signal is 20KHz to 25KHz.

[0063] In some embodiments, the display device may receive a target delay parameter determination instruction input by a user through a mouse, keyboard, etc., and determine the target delay parameter based on the target delay parameter determination instruction input by the user. In other embodiments, the display device may also automatically determine the target delay parameter at preset intervals during normal operation, so that the display device can regularly calibrate the delay parameter to ensure the accuracy of echo cancellation.

[0064] In a specific embodiment, the sound pickup module may be a microphone array. Figure 2 and Figure 3 As shown, the audio signal processing module 20 includes: an audio signal processing unit 21, an audio sampling unit 22 and an audio signal output unit 23. The audio signal processing unit 21 is connected to the audio signal generator 10, the audio sampling unit 22 and the audio signal output unit 23. The audio signal processing unit 21 is used to transmit the first calibration audio signal and the original audio signal to the audio sampling unit 22 and the audio signal output unit 23; the audio sampling unit 22 is connected to the delay determination module 40 and the echo cancellation module 50, and is used to transmit the first calibration audio signal to the delay determination module 40 and the original audio signal to the echo cancellation module 50; the audio signal output unit 23 is used to transmit the first calibration audio signal and the original audio signal to the speaker 60, so as to output the first calibration audio signal and the original audio signal through the speaker 60.

[0065] In a specific embodiment, continue to refer to Figure 2 As shown, the speaker 60 is built into the display device, and the echo cancellation system also includes: a first signal amplification module 70; the first signal amplification module 70 is connected to the audio signal output unit 23 and the speaker 60, and the first signal amplification module 70 is used to amplify the first calibrated audio signal and the original audio signal output by the audio signal output unit 23, and transmit the amplified first calibrated audio signal and the original audio signal to the speaker 60, so as to output the first calibrated audio signal and the original audio signal through the speaker 60.

[0066] In another specific embodiment, referring to Figure 3 As shown, the speaker 60 is arranged on the external active speaker 80, and the external active speaker 80 includes: an audio signal receiving module 81, a second signal amplifying module 82 and the speaker 60; the audio signal receiving module 81 is connected to the audio signal output unit 23 and the second signal amplifying module 82, and the second signal amplifying module 82 is connected to the speaker 60. Among them, the audio signal output unit 23 can transmit the first calibrated audio signal and the original audio signal to the external active speaker 80 in a wired or wireless manner; the audio signal receiving module 81 is used to receive the first calibrated audio signal and the original audio signal output by the audio signal output unit 23, and transmit the first calibrated audio signal and the original audio signal to the second signal amplifying module 82; the second signal amplifying module 82 is used to perform signal amplification processing on the first calibrated audio signal and the original audio signal, and transmit the amplified first calibrated audio signal and the original audio signal to the speaker 60, so as to output the first calibrated audio signal and the original audio signal through the speaker 60.

[0067] In a specific embodiment, referring to Figure 4 As shown, the delay determination module 40 includes a first filter unit 41, a second filter unit 42 and a delay determination unit 43; the first filter unit 41 is connected to the audio signal processing module 20, the second filter unit 42 is connected to the sound pickup module 30, and the delay determination unit 43 is connected to the first filter unit 41 and the second filter unit 42. Among them, the first filter unit 41 is used to filter the first calibration audio signal output by the audio signal processing module 20 to obtain a third calibration audio signal; the second filter unit 42 is used to filter the second calibration audio signal collected by the sound pickup module 30 to obtain a fourth calibration audio signal; the delay determination unit 43 is used to determine the target delay parameter based on the third calibration audio signal and the fourth calibration audio signal.

[0068] In this embodiment, the first filter unit 41 can select a filter in a bandpass filter mode, a filter in a high-pass filter mode, or a filter in a low-pass filter mode, etc. according to the frequency of the first calibration audio signal. When the first filter unit 41 performs filtering processing on the first calibration audio signal, the first calibration audio signal is filtered based on the frequency of the first calibration audio signal. In this embodiment, the first filter unit 41 performs filtering processing on the first calibration audio signal, and the interference signal in the first calibration audio signal can be filtered out, thereby improving the accuracy of the determined target delay parameter, and further improving the echo cancellation effect of the audio signal to be processed.

[0069] Furthermore, in this embodiment, the second filtering unit 42 may also select a filter in a bandpass filtering mode, a filter in a high-pass filtering mode, or a filter in a low-pass filtering mode, etc., according to the frequency of the first calibration audio signal. When the second filtering unit 42 performs filtering processing on the second calibration audio signal, the second calibration audio signal is filtered based on the frequency of the first calibration audio signal. In this embodiment, the second filtering unit 42 performs filtering processing on the second calibration audio signal, and the interference signal in the second calibration audio signal can be filtered out, thereby improving the accuracy of the determined target delay parameter, and further improving the echo cancellation effect of the audio signal to be processed.

[0070] In some embodiments, the target delay parameter can be determined by generating a first calibration audio signal by the audio signal generator 10, and the third calibration audio signal and the fourth calibration audio signal are both one. Accordingly, the delay determination unit 43 determines the target delay parameter based on the third calibration audio signal and the fourth calibration audio signal, including: performing phase comparison on the third calibration audio signal and the fourth calibration audio signal to obtain the target delay parameter.

[0071] In other embodiments, the target delay parameter can be determined by generating multiple first calibration audio signals by the audio signal generator 10, then the third calibration audio signal and the fourth calibration audio signal each include multiple, and the multiple third calibration audio signals and the multiple fourth calibration audio signals correspond one to one. Correspondingly, the delay determination unit 43 includes a first determination unit and a second determination unit. Among them, the first determination unit is used to perform phase comparison on each third calibration audio signal and the fourth calibration audio signal corresponding to each third calibration audio signal to obtain multiple first delay parameters; the second determination unit calculates and processes the multiple first delay parameters to obtain the target delay parameter. This embodiment obtains the target delay parameter by calculating and processing the multiple first delay parameters, which can further improve the accuracy of the obtained target delay parameter.

[0072] Among them, when the second determination unit calculates and processes multiple first delay parameters, it can average the multiple first delay parameters and determine the average value of the multiple first delay parameters as the target delay parameter; the second determination unit can also perform weighted summation on the multiple first delay parameters, and determine the weighted summation result of the multiple first delay parameters as the target delay parameter; of course, the second determination unit can also determine any one of the multiple first delay parameters as the target delay parameter, which is not limited in this embodiment.

[0073] In a specific embodiment, referring to Figure 5As shown, the echo cancellation module 50 includes a delay processing unit 51 and an echo cancellation unit 52; the delay processing unit 51 is connected to the delay determination module 40 and the audio signal processing module 20; the echo cancellation unit 52 is connected to the delay processing unit 51 and the sound pickup module 30. The delay processing unit 51 is used to perform delay processing on the original audio signal output by the audio signal processing module 20 based on the target delay parameter to obtain a first audio signal; the echo cancellation unit 52 is used to perform echo cancellation processing on the audio signal to be processed collected by the sound pickup module 30 based on the first audio signal to obtain a target audio signal.

[0074] In a specific embodiment, referring to Figure 6 As shown, the echo cancellation system further includes a human voice recognition module 90. The human voice recognition module 90 is connected to the echo cancellation module 50, and is used to recognize and process the target audio signal to obtain target recognition information. The target recognition information includes the user's control instructions for the display device, and voice control of the display device can be achieved based on the target recognition information.

[0075] In order to better implement the echo cancellation system in the embodiment of the present application, based on the echo cancellation system, the embodiment of the present application also provides an echo cancellation method, such as Figure 7 As shown, the echo cancellation method includes:

[0076] S10, generating a first calibration audio signal by an audio signal generator;

[0077] S20, transmitting the first calibration audio signal to the speaker;

[0078] S30, receiving a first calibration audio signal output by a speaker to obtain a second calibration audio signal;

[0079] S40, determining a target delay parameter based on the first calibration audio signal and the second calibration audio signal;

[0080] S50 , performing echo cancellation processing on the audio signal to be processed based on the target delay parameter and the original audio signal to obtain a target audio signal.

[0081] In a specific embodiment, the echo cancellation system is applied to a display device, such as a television, a projector, a computer, etc. The original audio signal is a sound signal actively emitted by the display device, and the audio signal to be processed is an ambient audio signal collected by the pickup module, which includes the original audio signal output by the display device through the speaker and the voice signal sent by the user to the terminal device. In this embodiment, a first calibration audio signal is generated by an audio signal generator, and the first calibration audio signal output by the speaker is received to obtain a second calibration audio signal, and then the target delay parameter is determined based on the first calibration audio signal and the second calibration audio signal, so that the delay time can be accurately measured. Furthermore, based on the target delay parameter and the original audio signal, the echo cancellation processing of the audio signal to be processed is performed, and the sound signal actively emitted by the display device in the audio signal to be processed can be identified and eliminated, and only the audio signal actively emitted by the non-local device (i.e., the voice signal sent by the user to the terminal device) is retained, which can improve the accuracy of echo cancellation, and compared with the traditional echo cancellation method relying on adaptive filtering technology, the computational complexity can be reduced.

[0082] Optionally, the target delay parameter can be determined during the period from when the display device is powered on to when it is in normal operation, or can be determined during the normal operation of the display device. When the target delay parameter is determined during the period from when the display device is powered on to when it is in normal operation, the frequency range of the first calibration audio signal can be selected from any frequency range based on the response frequency range of the speaker or the pickup module; when the target delay parameter is determined during the normal operation of the display device, in order to avoid the first calibration audio signal affecting the normal use of the display device, the frequency range of the first calibration audio signal is a frequency range that is inaudible to the human ear, for example, the frequency range of the first calibration audio signal is 20KHz to 25KHz.

[0083] In some embodiments, the display device may receive a target delay parameter determination instruction input by a user through a mouse, keyboard, etc., and determine the target delay parameter based on the target delay parameter determination instruction input by the user. In other embodiments, the display device may also automatically determine the target delay parameter at preset intervals during normal operation, so that the display device can regularly calibrate the delay parameter to ensure the accuracy of echo cancellation.

[0084] In specific implementation, the speaker can be built into the display device, or the speaker can be set on an external active speaker. When the speaker is set on the external active speaker, the display device can transmit the first calibration audio signal and the original audio signal to the speaker by wire or wireless means, so as to output the first calibration audio signal and the original audio signal through the speaker. The echo cancellation method provided in this embodiment can be applied to display devices with different speaker configurations such as built-in or external, and has strong applicability.

[0085] In some embodiments, the step of determining the target delay parameter based on the first calibration audio signal and the second calibration audio signal in the above-mentioned step S40 specifically includes: filtering the first calibration audio signal to obtain a third calibration audio signal; filtering the second calibration audio signal to obtain a fourth calibration audio signal; and determining the target delay parameter based on the third calibration audio signal and the fourth calibration audio signal.

[0086] In a specific embodiment, a filter in a bandpass filtering mode, a filter in a high-pass filtering mode, a filter in a low-pass filtering mode, etc. can be selected according to the frequency of the first calibration audio signal to filter the first calibration audio signal. By filtering the first calibration audio signal, this embodiment can filter out interference signals in the first calibration audio signal, thereby improving the accuracy of the determined target delay parameters, and further improving the echo elimination effect of the audio signal to be processed.

[0087] Furthermore, a bandpass filter mode filter, a high-pass filter mode filter, a low-pass filter mode filter, etc. can be selected according to the frequency of the first calibration audio signal to filter the second calibration audio signal. By filtering the second calibration audio signal, this embodiment can filter out interference signals in the second calibration audio signal, thereby improving the accuracy of the determined target delay parameters and further improving the echo elimination effect of the audio signal to be processed.

[0088] In some embodiments, a first calibration audio signal can be generated by an audio signal generator to determine the target delay parameter, and the third calibration audio signal and the fourth calibration audio signal are both one. Accordingly, the step of determining the target delay parameter based on the third calibration audio signal and the fourth calibration audio signal specifically includes: performing a phase comparison on the third calibration audio signal and the fourth calibration audio signal to obtain the target delay parameter.

[0089] In other embodiments, the target delay parameter can be determined by generating multiple first calibration audio signals through an audio signal generator, and the third calibration audio signal and the fourth calibration audio signal each include multiple ones, and the multiple third calibration audio signals and the multiple fourth calibration audio signals correspond one to one. Accordingly, the above-mentioned step of determining the target delay parameter based on the third calibration audio signal and the fourth calibration audio signal specifically includes: performing phase comparison on each third calibration audio signal and the fourth calibration audio signal corresponding to each third calibration audio signal to obtain multiple first delay parameters; performing calculation processing on the multiple first delay parameters to obtain the target delay parameter. This embodiment obtains the target delay parameter by calculating and processing the multiple first delay parameters, which can further improve the accuracy of the obtained target delay parameter.

[0090] In some embodiments, the step of calculating and processing a plurality of first delay parameters to obtain a target delay parameter specifically includes: averaging the plurality of first delay parameters, and determining the average value of the plurality of first delay parameters as the target delay parameter.

[0091] In other embodiments, the step of calculating and processing the multiple first delay parameters to obtain the target delay parameter specifically includes: performing weighted summation on the multiple first delay parameters, and determining the weighted summation result of the multiple first delay parameters as the target delay parameter.

[0092] Of course, this embodiment can also determine any one of the multiple first delay parameters as the target delay parameter, for example, determine the maximum value of the multiple first delay parameters as the target delay parameter, or determine the middle value of the multiple first delay parameters as the target delay parameter, or determine the minimum value of the multiple first delay parameters as the target delay parameter, etc.

[0093] In some embodiments, the step of performing echo cancellation processing on the audio signal to be processed based on the target delay parameter and the original audio signal in the above-mentioned step S50 to obtain the target audio signal specifically includes: performing delay processing on the original audio signal based on the target delay parameter to obtain a first audio signal; and performing echo cancellation processing on the audio signal to be processed based on the first audio signal to obtain the target audio signal.

[0094] In some embodiments, after performing echo cancellation processing on the audio signal to be processed based on the target delay parameter and the original audio signal in the above step S50 to obtain the target audio signal, the following steps are included: performing recognition processing on the target audio signal to obtain target recognition information. The target recognition information includes the user's control instructions for the display device, and voice control of the display device can be implemented based on the target recognition information.

[0095] An embodiment of the present application also provides a display device, which includes the above-mentioned echo cancellation system, that is, the display device includes: an audio signal generator, which is used to generate a first calibration audio signal; an audio signal processing module, which is used to transmit the first calibration audio signal to a speaker; a sound pickup module, which is used to receive the first calibration audio signal output by the speaker to obtain a second calibration audio signal; a delay determination module, which is connected to the sound pickup module and the audio signal processing module, and is used to determine a target delay parameter based on the first calibration audio signal and the second calibration audio signal; an echo cancellation module, which is connected to the delay determination module, the sound pickup module and the audio signal processing module, and is used to perform echo cancellation processing on the audio signal to be processed collected by the sound pickup module based on the target delay parameter and the original audio signal output by the audio signal processing module to obtain the target audio signal.

[0096] The display device provided in this embodiment generates a first calibration audio signal through an audio signal generator, receives the first calibration audio signal output by a speaker through a sound pickup module to obtain a second calibration audio signal, and then determines a target delay parameter based on the first calibration audio signal and the second calibration audio signal, so that the delay parameter can be accurately measured; based on the target delay parameter and the original audio signal, echo cancellation processing is performed on the audio signal to be processed output by the sound pickup module, so that the sound signal actively emitted by the display device in the audio signal to be processed collected by the sound pickup module can be identified and eliminated, and only the audio signal not actively emitted by the display device is retained, thereby improving the accuracy of echo cancellation.

[0097] In some embodiments, the speaker can be built into the display device, or the speaker can be set on an external active speaker. When the speaker is set on the external active speaker, the display device can transmit the first calibration audio signal and the original audio signal to the speaker via wired or wireless means to output the first calibration audio signal and the original audio signal through the speaker.

[0098] The embodiment of the present application also provides a computer-readable storage medium, which may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc. A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in any one of the echo cancellation methods provided in the embodiment of the present application. For example, the computer program loaded by the processor may execute the following steps:

[0099] generating a first calibration audio signal by an audio signal generator;

[0100] transmitting a first calibration audio signal to a speaker;

[0101] Receiving a first calibration audio signal output by a speaker to obtain a second calibration audio signal;

[0102] Determining a target delay parameter based on the first calibration audio signal and the second calibration audio signal;

[0103] The audio signal to be processed is subjected to echo cancellation processing based on the target delay parameter and the original audio signal to obtain a target audio signal.

[0104] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the detailed description of other embodiments above, and will not be repeated here.

[0105] In specific implementation, the above units or structures can be implemented as independent entities, or can be arbitrarily combined to be implemented as the same or several entities. The specific implementation of the above units or structures can refer to the previous method embodiments, which will not be repeated here.

[0106] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0107] The above is a detailed introduction to an echo cancellation system, method, computer device and computer-readable storage medium provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. An echo cancellation system, characterized in that: include: An audio signal generator, configured to generate a first calibration audio signal; An audio signal processing module, configured to transmit the first calibration audio signal to a speaker; A sound pickup module, used for receiving the first calibration audio signal output by the speaker to obtain a second calibration audio signal; a delay determination module, connected to the sound pickup module and the audio signal processing module, and configured to determine a target delay parameter based on the first calibration audio signal and the second calibration audio signal; The echo cancellation module is connected to the delay determination module, the sound pickup module and the audio signal processing module, and is used to perform echo cancellation processing on the audio signal to be processed collected by the sound pickup module based on the target delay parameter and the original audio signal output by the audio signal processing module to obtain the target audio signal.

2. The system according to claim 1, characterized in that The delay determination module comprises: A first filtering unit, connected to the audio signal processing module, configured to filter the first calibration audio signal to obtain a third calibration audio signal; A second filtering unit, connected to the sound pickup module, configured to filter the second calibration audio signal to obtain a fourth calibration audio signal; A delay determination unit is connected to the first filtering unit and the second filtering unit, and is used to determine a target delay parameter based on the third calibration audio signal and the fourth calibration audio signal.

3. The system according to claim 2, characterized in that The third calibration audio signal and the fourth calibration audio signal each include a plurality of third calibration audio signals and a plurality of fourth calibration audio signals respectively correspond to each other one by one, and the delay determination unit includes: A first determining unit, configured to perform phase comparison on each of the third calibration audio signals and a fourth calibration audio signal corresponding to each of the third calibration audio signals, to obtain a plurality of first delay parameters; The second determining unit is used to calculate and process the plurality of the first delay parameters to obtain a target delay parameter.

4. The system according to claim 1, characterized in that The echo cancellation module comprises: a delay processing unit, connected to the delay determination module and the audio signal processing module, and configured to perform delay processing on the original audio signal output by the audio signal processing module based on the target delay parameter to obtain a first audio signal; The echo cancellation unit is connected to the delay processing unit and the sound pickup module, and is used to perform echo cancellation processing on the audio signal to be processed collected by the sound pickup module based on the first audio signal to obtain a target audio signal.

5. The system according to claim 1, characterized in that The audio signal processing module includes: an audio signal processing unit, an audio sampling unit and an audio signal output unit; The audio signal processing unit is connected to the audio signal generator, the audio sampling unit and the audio signal output unit, and is used to transmit the first calibration audio signal and the original audio signal to the audio sampling unit and the audio signal output unit; The audio sampling unit is connected to the delay determination module and the echo cancellation module, and is used to transmit the first calibration audio signal to the delay determination module and transmit the original audio signal to the echo cancellation module; The audio signal output unit is used to transmit the first calibrated audio signal and the original audio signal to the speaker, so as to output the first calibrated audio signal and the original audio signal through the speaker.

6. The system according to any one of claims 1 to 5, characterized in that: Also includes: The audio recognition module is connected to the echo cancellation module and is used to perform recognition processing on the target audio signal to obtain target recognition information.

7. An echo cancellation method, characterized in that: include: generating a first calibration audio signal by an audio signal generator; transmitting the first calibration audio signal to a speaker; receiving the first calibration audio signal output by the speaker to obtain a second calibration audio signal; determining a target delay parameter based on the first calibration audio signal and the second calibration audio signal; The audio signal to be processed is subjected to echo cancellation processing based on the target delay parameter and the original audio signal to obtain a target audio signal.

8. The method according to claim 7, characterized in that The determining a target delay parameter based on the first calibration audio signal and the second calibration audio signal includes: Performing filtering processing on the first calibration audio signal to obtain a third calibration audio signal; Performing filtering processing on the second calibration audio signal to obtain a fourth calibration audio signal; A target delay parameter is determined based on the third calibration audio signal and the fourth calibration audio signal.

9. The method according to claim 8, characterized in that The third calibration audio signal and the fourth calibration audio signal each include a plurality of third calibration audio signals and a plurality of fourth calibration audio signals respectively correspond to each other one by one; The determining a target delay parameter based on the third calibration audio signal and the fourth calibration audio signal includes: Performing phase comparison on each of the third calibration audio signals and a fourth calibration audio signal corresponding to each of the third calibration audio signals to obtain a plurality of first delay parameters; Calculation is performed on a plurality of the first delay parameters to obtain a target delay parameter.

10. The method according to claim 7, characterized in that The performing echo cancellation processing on the audio signal to be processed based on the target delay parameter and the original audio signal to obtain the target audio signal includes: Performing delay processing on the original audio signal based on the target delay parameter to obtain a first audio signal; The audio signal to be processed is subjected to echo cancellation processing based on the first audio signal to obtain a target audio signal.

11. A display device, characterized in that: The display device comprises the echo cancellation system according to any one of claims 1-6.

12. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in the echo cancellation method according to any one of claims 7 to 10.

Images