Surround sound output method and device of translation earphone and storage medium

Abstract

The invention relates to the field of audio output, and discloses a surround sound output method and device of a translation earphone and a storage medium. The method comprises the following steps: a pickup translation system performs three-dimensional pickup to acquire a first language voice and a sound source space position corresponding to the first language voice; performing translation processing on the first language voice according to a preset translation algorithm to generate second language voice; sending the second language voice and the sound source space position to left and right earphone loudspeaking systems; the left and right earphone loudspeaking systems receive the second language voice and the sound source space position; and generating left and right playing volume settings according to the sound source spatial position, and playing and outputting the second language voice based on the left and right playing volume settings. In the embodiment of the invention, the sound source orientation can be distinguished by outputting the translation voice through the translation earphone, and the translation communication efficiency in a multi-person face-to-face scene is effectively improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of audio output, in particular to a surround sound output method, device and storage medium of a translation earphone. BACKGROUND

[0002] With the acceleration of globalization, the demand for cross-language communication is increasing, and the translation earphone, as a portable and real-time voice translation device, has been widely used in business negotiations, tourism, international conferences and other face-to-face communication scenarios. However, the existing translation earphone has a significant defect in sound output: both recording and sound output use monaural technology, lacking spatial orientation information. This monaural output method cannot restore the direction and position of the sound source, so that the user of the earphone cannot determine the actual orientation of the speaker through hearing.

[0003] In a face-to-face communication scenario, this defect is particularly prominent. For example, in a group discussion, multiple speakers may speak from different directions in turn or simultaneously. Since the translation earphone can only output mixed audio of a single channel, all translated voices are presented in the same way, lacking directionality. This "flat" sound experience not only reduces the naturalness and immersion of communication, but also may cause cognitive confusion, making it difficult for the listener to quickly correspond the translated voice with the actual speaker, thereby affecting the efficiency and accuracy of communication. Therefore, in view of the technical problem that the translated audio output by the current translation earphone cannot distinguish the direction of the sound source, a new technology is needed to solve the current problem. SUMMARY

[0004] The main purpose of the present application is to solve the technical problem that the translated audio output by the current translation earphone cannot distinguish the direction of the sound source.

[0005] The first aspect of the present application provides a surround sound output method of a translation earphone, which is applied to a surround sound output system of a translation earphone, and the surround sound output system of the translation earphone comprises a sound pickup translation system and a left and right earphone loudspeaker system. The surround sound output method of the translation earphone comprises the following steps: The sound pickup translation system stereophonically collects a first language voice and a sound source spatial position corresponding to the first language voice; According to a preset translation algorithm, the first language voice is translated and processed to generate a second language voice; The second language voice and the sound source spatial position are sent to the left and right earphone loudspeaker system; The left and right earphone loudspeaker system receives the second language voice and the sound source spatial position; According to the sound source spatial position, left and right playback volume settings are generated, and the second language voice is played out based on the left and right playback volume settings.

[0006] Optionally, in the first implementation manner of the first aspect, the step of stereophonic sound pickup of the sound pickup translation system collecting the first language voice and the sound source spatial position corresponding to the first language voice comprises: The sound pickup translation system collects the first language voice based on a preset microphone array; A time delay matrix is generated according to a collection time delay of the microphone array; The sound source spatial position corresponding to the first language voice is calculated based on the time delay matrix.

[0007] Optionally, in the second implementation manner of the first aspect, the microphone array is a first microphone, a second microphone and a third microphone arranged in a same straight line, a distance between the first microphone and the second microphone is equal to a distance between the second microphone and the third microphone, and the step of calculating the sound source spatial position corresponding to the first language voice based on the time delay matrix comprises: Based on the time delay matrix and the distance between the first microphone and the second microphone, distances between the first microphone, the second microphone and the third microphone and the sound source, and an included angle between the first microphone and the sound source are calculated; The sound source spatial position corresponding to the first language voice is generated based on the distances between the first microphone, the second microphone and the third microphone and the sound source, and the included angle between the first microphone and the sound source.

[0008] Optionally, in the third implementation manner of the first aspect, the step of calculating the distances between the first microphone, the second microphone and the third microphone and the sound source, and the included angle between the first microphone and the sound source based on the time delay matrix and the distance between the first microphone and the second microphone comprises: τ 12 = (r2-r1) / c; τ 13 = (r3-r1) / c; r2 2 = r1 2 +d 2 +2r1cosθ1; r2 2 = r1 2 +d 2 +2r1cosθ1; Wherein, τ 12 is the collection time delay of the first microphone and the second microphone, τ 13The first microphone and the third microphone are collected with a time delay, r1 is the distance between the first microphone and the sound source, r2 is the distance between the second microphone and the sound source, r3 is the distance between the third microphone and the sound source, θ1 is the angle between the first microphone and the sound source, d is the distance between the first microphone and the second microphone, and c is the sound speed constant.

[0009] Optionally, in the fourth implementation manner of the first aspect of the present application, the left and right earphone loudspeaker system comprises a gyroscope, and the generation of the left and right playing volume settings according to the sound source spatial position comprises: reading a rotation offset matrix of the gyroscope; transforming the sound source spatial position according to the rotation offset matrix to generate a spatial rotation transformed position; generating the left and right playing volume settings based on the spatial rotation transformed position.

[0010] Optionally, in the fifth implementation manner of the first aspect of the present application, before the step of collecting the first language voice and the sound source spatial position corresponding to the first language voice by the sound pickup translation system, the method further comprises: the left and right earphone loudspeaker system sends an infrared positioning signal to the sound pickup translation system; the sound pickup translation system receives the infrared positioning signal, generates a loudspeaker relative position, and sends the loudspeaker relative position to the left and right earphone loudspeaker system; the left and right earphone loudspeaker system receives the loudspeaker relative position.

[0011] Optionally, in the sixth implementation manner of the first aspect of the present application, the transformation of the sound source spatial position according to the rotation offset matrix to generate a spatial rotation transformed position comprises: performing relative spatial transformation processing on the sound source spatial position based on the loudspeaker relative position to generate a spatial relative transformed position; performing rotation transformation processing on the spatial relative transformed position based on the rotation offset matrix to generate a spatial rotation transformed position.

[0012] Optionally, in the seventh implementation manner of the first aspect of the present application, the step of performing translation processing on the first language voice based on a preset translation algorithm to generate a second language voice comprises: performing voiceprint recognition processing on the first language voice based on a preset voiceprint recognition algorithm to obtain an identity tag; judging whether the identity tag is a preset legal tag; when the identity tag is the preset legal tag, performing translation processing on the first language voice based on a preset translation algorithm to generate a second language voice; When not being the preset legal label, then the translation of the first language voice is suspended.

[0013] The second aspect of the present application provides a surround sound output device of a translation earphone, comprising: a memory and at least one processor, the memory has instructions stored therein, and the memory and the at least one processor are interconnected by a circuit; the at least one processor invokes the instructions in the memory to enable the surround sound output device of the translation earphone to perform the above-mentioned surround sound output method of the translation earphone.

[0014] The third aspect of the present application provides a computer-readable storage medium having instructions stored therein, which, when executed on a computer, cause the computer to perform the above-mentioned surround sound output method of the translation earphone.

[0015] In the embodiment of the present application, by determining the direction of the first language voice sound source to be translated by using the sound pickup translation system, after translating the first language voice into the second language voice, the second language voice is sent to the left and right earphone loudspeaker system with the sound source spatial position, the left and right earphone loudspeaker system generates the corresponding left and right earphone volume settings based on the sound source spatial position, and the second language voice is played based on the left and right playback audio settings, which realizes that the translation earphone output translation voice can distinguish the sound source direction, effectively improves the translation communication efficiency in the face-to-face scene of multiple people, and solves the technical problem that the translation audio output by the current translation earphone cannot distinguish the sound source direction. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 An embodiment schematic diagram of the surround sound output method of the translation earphone in the embodiment of the present application; Figure 2 An embodiment schematic diagram of the step 101 of the surround sound output method of the translation earphone in the embodiment of the present application; Figure 3 An embodiment schematic diagram of the microphone array acquiring the sound source spatial position in the embodiment of the present application; Figure 4 An embodiment schematic diagram of the step 1052 of the surround sound output method of the translation earphone in the embodiment of the present application; Figure 5 An embodiment schematic diagram of the surround sound output device of the translation earphone in the embodiment of the present application. DETAILED DESCRIPTION

[0017] The embodiment of the present application provides a surround sound output method, device and storage medium of a translation earphone.

[0018] Embodiments of the present disclosure will be described in more detail below with reference to the drawings. While certain embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be embodied in various forms and should not be construed as being limited to the embodiments set forth herein, but rather, the embodiments are provided so that the present disclosure can be more thoroughly and completely understood. It is understood that the drawings of the present disclosure and the embodiments are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0019] In the description of embodiments of the present disclosure, the term "comprising" and its conjugations are to be understood as open-ended, i.e., "including but not limited to". The term "based on" is to be understood as "based, at least in part, on". The term "one embodiment" or "an embodiment" is to be understood as "at least one embodiment". The terms "a first", "a second", etc. can refer to different or the same objects. Other explicit or implicit definitions can also be included below.

[0020] For ease of understanding, the specific process of the embodiments of the present disclosure is described below. Please refer to Figure 1 One embodiment of the surround sound output method of the translation earphone in the embodiments of the present disclosure is applied to a surround sound output system of the translation earphone, and the surround sound output system of the translation earphone includes a sound pickup translation system and a left and right earphone speaker system. The surround sound output method of the translation earphone includes: 101. The sound pickup translation system collects a first language voice and a sound source spatial position corresponding to the first language voice through stereo sound pickup; In this embodiment, the sound pickup translation system can be integrated in the translation earphone, or the sound pickup translation system can be an earphone storage bin for storing and charging the left and right translation earphones. The sound pickup translation system collects the first language voice through stereo sound pickup, and the sound source spatial position corresponding to the first language voice can be analyzed and generated during the collection of the first language voice.

[0021] Specifically, please refer to Figure 2 , Figure 2 A specific embodiment of step 101 of the surround sound output method of the translation earphone in the embodiments of the present disclosure is shown in the figure, and the following specific embodiments are included in step 101: 1011. The sound pickup translation system collects the first language voice based on a preset microphone array; 1012. A time delay matrix is generated according to the collection time delay of the microphone array; 1013. The sound source spatial position corresponding to the first language voice is calculated based on the time delay matrix.

[0022] In steps 1011-1013, the sound pickup translation system acquires the first language voice output externally based on a preset microphone array, and generates a time delay matrix about the time delay size based on the time delay between different microphones during the acquisition process. Finally, the sound source spatial position corresponding to the first language voice is generated based on the time delay matrix and the distance size data between the preset microphone array.

[0023] Specifically, please refer to Figure 3 , Figure 3 The embodiment shown in the figure is an embodiment of the microphone array acquiring the sound source spatial position in the embodiment of the application. The microphone array is a first microphone y1(k), a second microphone y2(k) and a third microphone y3(k) arranged on the same straight line. The distance d between the first microphone y1(k) and the second microphone y2(k) is equal to the distance between the second microphone y2(k) and the third microphone y3(k). The angle θ1 between the first microphone y1(k) and the sound source s(k), the angle θ2 between the second microphone y2(k) and the sound source s(k), and the angle θ3 between the third microphone y3(k) and the sound source s(k). In step 1013, the following specific implementation is included: 10131, based on the time delay matrix, the distance between the first microphone and the second microphone, the distance between the first microphone and the sound source, the distance between the second microphone and the sound source, the distance between the third microphone and the sound source, and the angle between the first microphone and the sound source, the angle between the second microphone and the sound source, the angle between the third microphone and the sound source, and the angle between the first microphone and the sound source, the sound source spatial position corresponding to the first language voice is generated. 10132, based on the distance between the first microphone and the sound source, the distance between the second microphone and the sound source, the distance between the third microphone and the sound source, and the angle between the first microphone and the sound source, the sound source spatial position corresponding to the first language voice is generated.

[0024] In steps 10131-10132, the time delay matrix contains the acquisition time delay τ 12 between the first microphone y1(k) and the second microphone y2(k), the acquisition time delay τ 13 between the first microphone y1(k) and the third microphone y3(k), the distance d between the first microphone y1(k) and the second microphone y2(k), and the following formula is obtained by combining the cosine theorem: τ 12 = (r2-r1) / c; τ 13 = (r3-r1) / c; r2 2 = r1 2 + d 2 + 2r1cosθ1; r2 2 = r1 2 + d 2 + 2r1cosθ1; where τ 12is the collection time delay of the first microphone and the second microphone, τ 13 is the collection time delay of the first microphone and the third microphone, r1 is the distance between the first microphone and the sound source, r2 is the distance between the second microphone and the sound source, r3 is the distance between the third microphone and the sound source, θ1 is the angle between the first microphone and the sound source, d is the distance between the first microphone and the second microphone, and c is the sound speed constant.

[0025] From the above formula, τ 12 , τ 13 is the collection time delay of the microphone array, d is the distance between the first microphone and the second microphone, which has been determined before collection, and c is the sound speed constant, which is known. Among the four linear formulas, there are four unknown parameters r1, r2, r3, and θ1. Solving the linear equation set can determine the four unknown parameters r1, r2, r3, and θ1.

[0026] Then, based on the distance r1 between the first microphone and the sound source, the distance r2 between the second microphone and the sound source, the distance r3 between the third microphone and the sound source, and the angle θ1 between the first microphone and the sound source, the spatial position s(k) of the sound source corresponding to the first language voice is generated.

[0027] In addition, to avoid errors in single calculation, the angle θ2 between the second microphone and the sound source and the angle θ3 between the third microphone and the sound source can also be used as the basis for calculation according to the cosine theorem to obtain the solution r1, r2, r3, θ, and then the mean value of r1, r2, and r3 is taken three times to generate the spatial position s(k) of the sound source.

[0028] 102. Translate the first language voice according to a preset translation algorithm to generate a second language voice; In this embodiment, the translation algorithm is used to translate the first language voice to generate a second language voice. The translation algorithm can be a neural network method such as mBART, ConvS2S, etc.

[0029] Specifically, the step 102 includes the following specific implementation: 1021. Perform voiceprint recognition on the first language voice based on a preset voiceprint recognition algorithm to obtain an identity tag; 1022. Determine whether the identity tag is a preset legal tag; 1023. When the identity tag is the preset legal tag, translate the first language voice according to the preset translation algorithm to generate a second language voice; 1024. When the identity tag is not the preset legal tag, terminate the translation of the first language voice.

[0030] In steps 1021-1024, before translating the first language speech, the voiceprint recognition algorithm is used to perform voiceprint recognition processing on the first language speech to obtain an identity tag. It is analyzed whether the identity of the first language speech is a pre-registered legal person, so as to avoid translating the speech of irrelevant persons and irrelevant persons in the environment. When it is a preset legal tag, the first language speech is translated according to the preset translation algorithm to generate the second language speech, and when it is not a preset legal tag, the translation of the first language speech is stopped.

[0031] 103、sending the second language speech and the sound source spatial position to the left and right earphone speaker systems; In this embodiment, the second language speech and the sound source spatial position are sent to the left and right earphone speaker systems. If the sound pickup translation system is integrated in the translation earphone, it is transmitted to the left and right earphone speaker systems through wired connection and chip interaction. If the sound pickup translation system is set as an earphone storage bin, the second language speech and the sound source spatial position are sent to the left and right earphone speaker systems through Bluetooth protocol or WiFi protocol.

[0032] 104、the left and right earphone speaker systems receiving the second language speech and the sound source spatial position; In this embodiment, the left and right earphone speaker systems receive the second language speech and the sound source spatial position based on different sound pickup translation system forms and different communication modes.

[0033] 105、generating left and right playback volume settings according to the sound source spatial position, and playing out the second language speech based on the left and right playback volume settings.

[0034] In this embodiment, the left and right playback volume settings are adjusted in the left and right earphone speaker systems based on the sound source spatial position. For example, when the left person speaks, the sound of the left earphone is louder than that of the right earphone, when the right person speaks, the sound of the right earphone is louder than that of the left earphone, and when the person in the middle position speaks, the sound of the left earphone and the right earphone is the same. The second language speech is played out based on the left and right playback volume settings to realize output of the translation speech with distinguishable direction.

[0035] Specifically, the left and right earphone speaker systems include a gyroscope, which includes the following specific embodiments in step 105: 1051、reading the rotation offset matrix of the gyroscope; 1052、transforming the sound source spatial position according to the rotation offset matrix to generate a spatial rotation transformation position; 1053、generating left and right playback volume settings based on the spatial rotation transformation position.

[0036] In the steps 1051-1053, the gyroscope can measure the rotation angle of the user's head, and based on the degree of head rotation offset, the rotation offset matrix containing the rotation information is generated. Based on the rotation offset matrix, the spatial position of the sound source is transformed to generate the spatial rotation transformation position. At this time, the spatial rotation transformation position is the relative position information of the user's ear relative to the sound source after the user's head rotation.

[0037] Based on the spatial rotation transformation position containing the user's head rotation number, the left and right playback volume settings are generated. For example, when the left person speaks, the left earphone sound is loud. When the user's head turns, the size of the left and right earphone sounds changes with the turning direction, realizing dynamic spatial sound effect. When the user's head turns to face the speaker, the left and right earphone sounds are the same. When the user's head turns to the right, the left sound is loud and the right sound is small.

[0038] Specifically, when the sound pickup translation system is set as the product form of earphone storage bin, the following specific embodiments are further included before the step 101: 1014、The left and right earphone loudspeaker system sends an infrared positioning signal to the sound pickup translation system; 1015、The sound pickup translation system receives the infrared positioning signal, generates a loudspeaker relative position, and sends the loudspeaker relative position to the left and right earphone loudspeaker system; 1016、The left and right earphone loudspeaker system receives the loudspeaker relative position.

[0039] In the steps 1014-1016, in the surround sound output system of the translation earphone, the left and right earphone loudspeaker system sends an infrared positioning signal to the sound pickup translation system before obtaining the audio signal, because the left and right earphone loudspeaker system and the sound translation system are spatially separated systems. The sound pickup translation system receives the infrared positioning signal and generates a loudspeaker relative position. The loudspeaker relative position is the spatial position of the left and right earphone loudspeaker system relative to the sound pickup translation system.

[0040] The loudspeaker relative position is sent to the left and right earphone loudspeaker system, and the left and right earphone loudspeaker system receives the loudspeaker relative position, so that the left and right earphone loudspeaker system transforms the loudspeaker relative position to transform the spatial position of the sound pickup translation system relative to the sound source into the spatial position of the left and right earphone loudspeaker system relative to the sound source.

[0041] Specifically, please refer to Figure 4 , Figure 4 A specific embodiment diagram for the step 1052 of the surround sound output method of the translation earphone in the embodiments of the present application is shown below. The step 1052 includes the following specific embodiments under the embodiments of the steps 1014-1016: 10521. Based on the relative position of the loudspeaker, perform relative spatial transformation processing on the spatial position of the sound source to generate a spatially relative transformed position; 10522. Based on the rotation offset matrix, perform rotation transformation processing on the spatial relative transformation position to generate a spatial rotation transformation position.

[0042] In steps 10521-10522, during the process of changing the spatial position, the relative position of the speakers is first changed, transforming the position of the sound pickup translation system relative to the sound source into the position of the left and right earphone speaker systems relative to the sound source, thus generating the spatial relative transformation position.

[0043] Then, based on the rotation offset matrix, the spatial relative transformation position is processed to adjust the change of the left and right headphone speaker systems relative to the sound source during the rotation of the human ear, generating the spatial rotation transformation position. After two changes, the volume output of the left and right headphones can still reflect the sound source position, which can help users locate the speaker in time.

[0044] In this embodiment of the invention, by using a sound pickup translation system to determine the direction of the first language speech source to be translated, and after translating the first language speech into the second language speech, the second language speech, along with the spatial location of the sound source, is sent to the left and right earphone speaker systems. The left and right earphone speaker systems generate corresponding volume settings for the left and right earphones based on the spatial location of the sound source, and play the second language speech based on the left and right playback audio settings. This enables the translation headphones to output translated speech that can identify the direction of the sound source, effectively improving the efficiency of translation communication in face-to-face scenarios with multiple people, and solving the technical problem that the translation audio output by current translation headphones cannot distinguish the direction of the sound source.

[0045] Figure 5 This is a schematic diagram of the surround sound output device 500 for a translation headset according to an embodiment of the present invention. The surround sound output device 500 can vary significantly depending on its configuration or performance, and may include one or more central processing units (CPUs) 510 (e.g., one or more processors) and a memory 520, and one or more storage media 530 (e.g., one or more mass storage devices) for storing application programs 533 or data 532. The memory 520 and storage media 530 can be temporary or persistent storage. The program stored in the storage media 530 may include one or more modules (not shown in the diagram), each module including a series of instruction operations on the surround sound output device 500 of the translation headset. Furthermore, the processor 510 may be configured to communicate with the storage media 530 and execute the series of instruction operations in the storage media 530 on the surround sound output device 500 of the translation headset.

[0046] The surround sound output device 500 based on translation headphones may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input / output interfaces 560, and / or one or more operating systems 531, such as Windows Server, Mac OS X, Unix, Linux, Free BSD, etc. Those skilled in the art will understand that... Figure 5 The surround sound output device structure of the translation headset shown does not constitute a limitation on surround sound output devices based on translation headsets, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0047] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the steps of the surround sound output method for the translation headphones.

[0048] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0049] Furthermore, although the operations are depicted in a specific order, this should be understood as requiring that such operations be performed in the specific order shown or in sequential order, or requiring that all illustrated operations be performed to achieve the desired result. In certain environments, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single implementation. Conversely, various features described in the context of a single implementation may also be implemented individually or in any suitable sub-combination in multiple implementations.

[0050] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A method for outputting surround sound in a translation headset, characterized in that, The surround sound output method of the translation headphones is applied to the surround sound output system of the translation headphones. The surround sound output system of the translation headphones includes: a voice pickup translation system and left and right earphone speaker systems. The surround sound output method of the translation headphones includes: The sound pickup translation system uses stereo sound pickup to collect the first language speech and the spatial location of the sound source corresponding to the first language speech; According to a preset translation algorithm, the first language speech is translated to generate the second language speech; The second language speech and the spatial location of the sound source are sent to the left and right earphone speaker systems; The left and right earphone speaker systems receive the second language speech and the spatial location of the sound source; Based on the spatial location of the sound source, left and right playback volume settings are generated, and based on the left and right playback volume settings, the second language speech is played and output.

2. The surround sound output method for translation headphones according to claim 1, characterized in that, The steps of the stereo sound pickup translation system for acquiring first language speech and the spatial location of the corresponding sound source in the first language speech include: The speech recognition and translation system is based on a preset microphone array and collects speech in the first language. A delay matrix is ​​generated based on the acquisition delay of the microphone array; Based on the time delay matrix, the spatial location of the sound source corresponding to the first language speech is calculated.

3. The surround sound output method for translation headphones according to claim 2, characterized in that, The microphone array consists of a first microphone, a second microphone, and a third microphone arranged in a straight line. The distance between the first microphone and the second microphone is equal to the distance between the second microphone and the third microphone. The calculation of the spatial location of the sound source corresponding to the first language speech based on the time delay matrix includes: Based on the time delay matrix and the distance between the first microphone and the second microphone, the distance between the first microphone and the sound source, the distance between the second microphone and the sound source, the distance between the third microphone and the sound source, and the angle between the first microphone and the sound source are calculated. Based on the distances between the first microphone and the sound source, the distances between the second microphone and the sound source, the distances between the third microphone and the sound source, and the angle between the first microphone and the sound source, the spatial location of the sound source corresponding to the first language speech is generated.

4. The surround sound output method for translation headphones according to claim 3, characterized in that, The step of calculating the distances between the first microphone and the sound source, the second microphone and the sound source, the third microphone and the sound source, and the angle between the first microphone and the sound source based on the time delay matrix and the distance between the first microphone and the second microphone includes: τ 12 =(r2-r1) / c; τ 13 =(r3-r1) / c; r2 2 =r1 2 +d 2 +2r1cosθ1; r2 2 =r1 2 +d 2 +2r1cosθ1; Where, τ 12 τ represents the acquisition delay between the first and second microphones. 13 Let r1 be the acquisition delay between the first microphone and the third microphone, r2 be the distance between the first microphone and the sound source, r3 be the distance between the second microphone and the sound source, θ1 be the angle between the first microphone and the sound source, d be the distance between the first microphone and the second microphone, and c be the sound speed constant.

5. The surround sound output method for translation headphones according to claim 1, characterized in that, The left and right earphone speaker system includes a gyroscope, and the step of generating left and right playback volume settings based on the spatial location of the sound source includes: Read the rotation offset matrix of the gyroscope; The spatial position of the sound source is transformed according to the rotation offset matrix to generate a spatial rotation transformation position; Based on the spatial rotation and position transformation, left and right playback volume settings are generated.

6. The surround sound output method for translation headphones according to claim 5, characterized in that, Before the step of stereo sound pickup and acquisition of the first language speech and the corresponding spatial location of the sound source in the sound pickup and translation system, the following is also included: The left and right earphone speaker systems send infrared positioning signals to the sound pickup and translation system; The sound pickup and translation system receives the infrared positioning signal, generates the relative position of the speaker, and sends the relative position of the speaker to the left and right earphone speaker systems. The left and right earphone speaker systems receive the relative positions of the speakers.

7. The surround sound output method for translation headphones according to claim 6, characterized in that, The step of transforming the spatial position of the sound source according to the rotation offset matrix to generate a spatial rotation transformation position includes: Based on the relative position of the loudspeaker, the spatial position of the sound source is subjected to relative spatial transformation processing to generate a spatial relative transformation position; Based on the rotation offset matrix, the spatial relative transformation position is subjected to rotation transformation processing to generate a spatial rotation transformation position.

8. The surround sound output method for translation headphones according to claim 1, characterized in that, The step of translating the first language speech according to a preset translation algorithm to generate the second language speech includes: Based on a preset voiceprint recognition algorithm, the first language speech is processed to obtain an identity tag. Determine whether the identity tag is a preset valid tag; When the preset legal label is used, the first language speech is translated according to the preset translation algorithm to generate the second language speech; If the label is not a preset valid label, the translation of the first language speech will be stopped.

9. A surround sound output device for translation headphones, characterized in that, The surround sound output device of the translation headset includes: a memory and at least one processor, wherein the memory stores instructions, and the memory and the at least one processor are interconnected via a line; The at least one processor invokes the instructions in the memory to cause the surround sound output device of the translation headset to perform the surround sound output method of the translation headset as described in any one of claims 1-8.

10. A computer-readable storage medium storing a computer program thereon, characterized in that, When the computer program is executed by the processor, it implements the surround sound output method of the translation headphones as described in any one of claims 1-8.

Images