A dual-link simultaneous interpretation system based on optical wireless and electromagnetic wave wireless

Abstract

The present application relates to simultaneous interpretation technical field, especially in a kind of based on optical path wireless and electromagnetic wave wireless double-link simultaneous interpretation system, comprising: simultaneous interpretation module, to the sound signal that the sound acquisition equipment collected is converted output as corresponding language sound signal;Interpretation state determination module, it is connected with the simultaneous interpretation module, it is by the corresponding operating parameter of simultaneous interpretation module to output simultaneous interpretation characteristic parameter, and according to the simultaneous interpretation characteristic parameter is determined to simultaneous interpretation state;Operating parameter adjustment module, it is connected with the simultaneous interpretation module and the interpretation state determination module respectively, to according to the simultaneous interpretation state determination result of interpretation state determination module the operating characteristic parameter of the simultaneous interpretation module is adjusted corresponding.This application has realized for the continuity and quality of simultaneous interpretation improvement.

Description

Technical Field

[0001] This invention relates to the field of simultaneous interpretation technology, and in particular to a dual-link simultaneous interpretation system based on optical wireless and electromagnetic wave wireless. Background Technology

[0002] In existing technologies, simultaneous interpreting is a method of interpretation in which the interpreter continuously translates the speaker's speech to the audience without interrupting the speaker's delivery. The greatest advantage of simultaneous interpreting is its high efficiency; it ensures a coherent speech, does not disrupt the speaker's train of thought, and facilitates the audience's overall comprehension of the speech. As an emerging system in the field of audio conferencing technology, it continues to play a crucial role in various important meetings. With the development of technology, our simultaneous interpreting technology is also constantly being updated. Existing dual-link simultaneous interpreting systems can receive simultaneous interpreting signals from different translation channels and distribute them to listeners with different language requirements. However, current simultaneous interpreting backends often only provide single-mode signal reception. When a single signal is interfered with, such as infrared signals being blocked or subject to other light wave interference, or electromagnetic signals potentially being unstable or subject to interference, the obstruction of a single signal directly affects the quality of the simultaneous interpreting.

[0003] Chinese Patent Publication No. CN114389763A discloses a dual-link simultaneous interpretation system based on optical wireless and electromagnetic wave wireless, comprising a dual-channel transmitting front-end for transmitting dual-channel carrier signals and a dual-channel receiving back-end for receiving dual-channel carrier signals; the dual-channel transmitting front-end includes several interpreter units, a simultaneous interpretation host, a multi-channel decoder, and the dual-channel transmitting host; the several interpreter units are electrically connected to the simultaneous interpretation host, and the simultaneous interpretation host is electrically connected to the multi-channel decoder; wherein, the interpreter units are responsible for collecting the speech translated by each simultaneous interpreter and converting it into input electrical signals; the simultaneous interpretation host is responsible for receiving the input electrical signals sent by each interpreter unit and obtaining multiple simultaneous interpretation signals; the multi-channel decoder is used to perform multi-channel simultaneous decoding on the multiple simultaneous interpretation signals to obtain multiple simultaneous data; the dual-channel transmitting host is used for... The system performs dual-channel simultaneous interpretation encoding and transmission of multiple simultaneous audio signals, including an optical transmission link and an electromagnetic wave transmission link. The optical transmission link generates optical carrier signals, and the electromagnetic wave transmission link generates electromagnetic carrier signals. The dual-channel receiving backend includes an optical receiving module, an electromagnetic wave receiving module, a processing unit, an encoding / decoding processing module, a link switching unit, and a power supply unit. The encoding / decoding processing module is a dual-channel module, forming optical carrier data links and electromagnetic carrier data links with the optical receiving module and the electromagnetic wave receiving module, respectively. The encoding / decoding processing module is electrically connected to the processing unit. The link switching unit and the power supply unit are also electrically connected to the processing unit. The processing unit includes a processor and a buffer, with the processor and buffer electrically connected. The buffer includes an optical buffer and an electromagnetic buffer. Therefore, the dual-link simultaneous interpretation system based on optical and electromagnetic wireless technologies suffers from problems such as inaccurate recognition fields due to excessively large granularity of sound signal filtering and insufficient matching of field information due to a limited number of basic sound template types, resulting in decreased continuity and quality of simultaneous interpretation. Summary of the Invention

[0004] To address this, the present invention provides a dual-link simultaneous interpretation system based on optical wireless and electromagnetic wave wireless, which overcomes the problems in the prior art where the recognition fields are inaccurate due to the excessively large granularity of the sound signal screening and the insufficient number of sound basic template types, resulting in insufficient field information matching and a decline in the continuity and quality of simultaneous interpretation.

[0005] To achieve the above objectives, this invention provides a dual-link simultaneous interpretation system based on optical wireless and electromagnetic wave wireless, comprising: a simultaneous interpretation module for converting and outputting sound signals acquired by a sound acquisition device into sound signals in the corresponding language; and an interpretation state determination module connected to the simultaneous interpretation module, which acquires and calculates corresponding operating parameters of the simultaneous interpretation module to output simultaneous interpretation feature parameters, and determines the simultaneous interpretation state based on the simultaneous interpretation feature parameters, including a continuity determination unit for determining the continuity of simultaneous interpretation based on the average difference in the translation duration of words with the same part of speech, and a speech synthesis state determination unit connected to the continuity determination unit for determining the speech synthesis state based on the proportion of words with pitch changes in the translated text. The system includes an information security risk determination unit connected to the speech synthesis state determination unit to determine information security risks based on the fitting degree between the number of network attacks and the screening length of the sound fields during the encoding process; and a signal interference degree determination unit connected to the information security risk determination unit to determine the degree of signal interference based on the frequency difference between the decoded sound signal and the original sound signal. An operating parameter adjustment module, connected to both the simultaneous interpretation module and the interpretation state determination module, adjusts the operating characteristic parameters of the simultaneous interpretation module according to the simultaneous interpretation state determination result from the interpretation state determination module. The operating characteristic parameters of the simultaneous interpretation module include the granularity of the sound signal screening, the number of basic sound template types, and the number of words called during the decoding process.

[0006] Furthermore, the corresponding operating parameters include the word translation time, the number of words with pitch mutations, the number of network attacks, the filtering length of the sound field during the encoding process, the frequency of the decoded sound signal, and the frequency of the original sound signal.

[0007] Furthermore, the simultaneous interpretation feature parameters include the average difference in the translation time of words with the same part of speech, the proportion of words with abrupt changes in tone in the translation, the fit between the number of network attacks and the screening length of the sound field in the encoding process, and the frequency difference between the decoded sound signal and the original sound signal.

[0008] Furthermore, the continuity determination unit includes a first invocation component connected to the simultaneous interpretation module and a first determination component connected to the first invocation component, wherein,

[0009] The first calling component is used to call the translation time of the word, and calculate the average difference in translation time of words with the same part of speech based on the calling result;

[0010] The first determination component is used to determine that the continuity of simultaneous interpretation is below the allowable range when a preset first average difference condition or a preset second average difference condition is triggered.

[0011] The first preset average difference condition is that the average difference in translation time of words with the same part of speech is greater than the first preset average difference and less than or equal to the second preset average difference; the second preset average difference condition is that the average difference in translation time of words with the same part of speech is greater than the second preset average difference; and the first preset average difference is less than the second preset average difference.

[0012] Furthermore, the speech synthesis state determination unit includes a second invocation component connected to the simultaneous interpretation module and a second determination component connected to the second invocation component, wherein,

[0013] The second calling component is used to collect the number of tone-altering characters and calculate the proportion of tone-altering characters in the translation based on the collection results;

[0014] The second determination component is used to initially determine that the effectiveness of speech synthesis is below the allowable range when the preset first average difference condition is triggered, and to determine a second time that the effectiveness of speech synthesis is below the allowable range when the preset percentage condition is triggered.

[0015] The preset percentage condition is that the percentage of characters with abrupt tonal changes in the translated text is greater than the preset percentage.

[0016] Furthermore, the information security risk assessment unit includes a third invocation component connected to the simultaneous interpretation module and a third assessment component connected to the third invocation component, wherein,

[0017] The third calling component is used to obtain the number of network attacks and the filtering length of the audio field in the encoding process, and to calculate the goodness of fit between the number of network attacks and the filtering length of the audio field in the encoding process based on the acquisition results.

[0018] The third determination component is used to determine that the information security risk is below the allowable range when the first condition and the preset first fit condition are triggered simultaneously or when the first condition and the preset second fit condition are triggered simultaneously.

[0019] The first preset goodness-of-fit condition is that the goodness-of-fit between the number of network attacks and the filtering length of the audio field during the encoding process is greater than the first preset goodness-of-fit and less than or equal to the second preset goodness-of-fit; the second preset goodness-of-fit condition is that the goodness-of-fit between the number of network attacks and the filtering length of the audio field during the encoding process is greater than the preset goodness-of-fit; the first preset goodness-of-fit is less than the second preset goodness-of-fit; the first condition is that the running parameter adjustment module completes the initial adjustment of the filtering granularity of the audio signal.

[0020] Furthermore, the signal interference level determination unit includes a fourth calling component connected to the simultaneous interpretation module and a fourth determination component connected to the fourth calling component, wherein,

[0021] The fourth calling component is used to retrieve the frequency of the decoded sound signal and the frequency of the original sound signal, and to calculate the frequency difference between the decoded sound signal and the original sound signal based on the retrieval result;

[0022] The fourth determination component is used to initially determine that the signal interference level exceeds the allowable range when the preset second fit condition is triggered, and to determine a second time that the signal interference level exceeds the allowable range when the preset frequency difference condition is triggered.

[0023] Furthermore, the preset frequency difference condition is that the frequency difference between the decoded audio signal and the original audio signal is greater than the preset frequency difference.

[0024] Furthermore, the operating parameter adjustment module includes a first parameter adjustment component connected to the first determination component and the third determination component, a second parameter adjustment component connected to the second determination component, and a third parameter adjustment component connected to the fourth determination component.

[0025] The first parameter adjustment component is used to initially adjust the screening granularity of the sound signal to output the screening granularity of the first sound signal when the preset second average difference condition is triggered, and to perform a second adjustment on the screening granularity of the sound signal to output the screening granularity of the second sound signal when the preset first fit condition is triggered.

[0026] The second parameter adjustment component is used to adjust the number of basic sound template types when the preset proportion condition is triggered;

[0027] The third parameter adjustment component is used to adjust the number of words called during the decoding process when the preset frequency difference condition is triggered.

[0028] Furthermore, the granularity of the first sound signal is inversely proportional to the difference between the average difference in translation time of words with the same part of speech and the preset second average difference; the number of the basic sound template types is directly proportional to the difference between the proportion of tone-altering characters in the translation and the preset proportion; the granularity of the second sound signal is directly proportional to the difference between the goodness of fit of the number of network attacks and the length of the sound field in the encoding process and the preset first goodness of fit; the number of words called in the decoding process is directly proportional to the difference between the frequency difference between the decoded sound signal and the original sound signal and the preset frequency difference.

[0029] Compared with existing technologies, the beneficial effects of this invention are as follows: The system of this invention, by setting up a simultaneous interpretation module, an interpretation status determination module, and an operating parameter adjustment module, performs an initial adjustment of the sound signal filtering granularity when the continuity of simultaneous interpretation falls below the allowable range. This reduces the impact of inaccurate adjustment of the sound signal filtering granularity leading to excessively large segmentation granularity and thus a decrease in the continuity of simultaneous interpretation. Furthermore, by adjusting the number of basic sound template types based on the proportion of text with tonal variations in the translated text, it reduces the impact of inaccurate adjustment of the number of basic sound template types leading to a insufficient number of sound template types. The impact of decreased simultaneous interpretation quality is mitigated by adjusting the granularity of the audio signal selection based on the fit between the number of network attacks and the selection length of the audio fields during the encoding process. This reduces the impact of inaccurate secondary adjustment of the audio signal selection granularity leading to excessively small segmentation granularity and thus decreased simultaneous interpretation continuity. Furthermore, by adjusting the number of words called during the decoding process based on the frequency difference between the decoded and original audio signals, the impact of inaccurate adjustment of the number of words called during the decoding process leading to insufficient decoding accuracy and thus decreased simultaneous interpretation quality is mitigated. This achieves an improvement in both the continuity and quality of simultaneous interpretation.

[0030] Furthermore, the system of the present invention determines the continuity of simultaneous interpretation by setting a preset first average difference amount and a preset second average difference amount, thereby reducing the impact of the decline in the quality of simultaneous interpretation caused by inaccurate determination of the continuity of simultaneous interpretation, and further improving the continuity and quality of simultaneous interpretation.

[0031] Furthermore, the system of the present invention sets a preset percentage and performs a secondary determination on the effectiveness of speech synthesis under the preset percentage condition. This reduces the impact of the discontinuity of the synthesized sound signal caused by the inaccurate secondary determination of the effectiveness of speech synthesis, which leads to a decrease in the quality of simultaneous interpretation. This further improves the continuity and quality of simultaneous interpretation.

[0032] Furthermore, the system of the present invention determines information security risks by setting a preset first degree of fit and a preset second degree of fit, thereby reducing the impact of inaccurate determination of information security risks on the continuity of simultaneous interpretation and further improving the continuity and quality of simultaneous interpretation.

[0033] Furthermore, the system described in this invention reduces the impact of inaccurate secondary determination of signal interference level caused by setting a preset frequency difference amount, thereby improving the continuity and quality of simultaneous interpretation.

[0034] Furthermore, the system of the present invention adjusts the granularity of the sound signal screening by setting a preset average difference value and under a preset second average difference value, thereby reducing the impact of inaccurate recognition fields caused by excessively large screening granularity of the sound signal, which leads to a decrease in the continuity of simultaneous interpretation, and further improves the continuity and quality of simultaneous interpretation.

[0035] Furthermore, the system of the present invention adjusts the number of basic sound template types under the preset ratio by setting a preset ratio difference, thereby reducing the impact of the decrease in the quality of simultaneous interpretation caused by the small number of basic sound template types, and further improving the continuity and quality of simultaneous interpretation.

[0036] Furthermore, the system of the present invention adjusts the granularity of the sound signal selection secondaryly under the preset first degree of fit by setting a preset fitting degree difference, thereby reducing the impact of the decrease in the continuity of simultaneous interpretation caused by the excessively small granularity of the sound signal selection, and further improving the continuity and quality of simultaneous interpretation.

[0037] Furthermore, the system of the present invention adjusts the number of words called in the decoding process under the preset frequency difference value by setting a preset frequency difference value, thereby reducing the impact of the decrease in the quality of simultaneous interpretation caused by the small number of words called in the decoding process, and further improving the continuity and quality of simultaneous interpretation. Attached Figure Description

[0038] Figure 1 This is an overall structural block diagram of a dual-link simultaneous interpretation system based on optical wireless and electromagnetic wave wireless according to an embodiment of the present invention;

[0039] Figure 2 This is a block diagram of the simultaneous interpretation module of the dual-link simultaneous interpretation system based on optical wireless and electromagnetic wave wireless according to an embodiment of the present invention.

[0040] Figure 3This is a detailed structural block diagram of the interpretation status determination module of the dual-link simultaneous interpretation system based on optical wireless and electromagnetic wave wireless according to an embodiment of the present invention.

[0041] Figure 4 This is a block diagram showing the connection structure of the operating parameter adjustment module of the dual-link simultaneous interpretation system based on optical wireless and electromagnetic wave wireless in an embodiment of the present invention, which is connected to the simultaneous interpretation module and the simultaneous interpretation module respectively. Detailed Implementation

[0042] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0043] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0044] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0045] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0046] Please see Figure 1 , Figure 2 , Figure 3 as well as Figure 4 The diagrams shown are, respectively, the overall structural block diagram of the dual-link simultaneous interpretation system based on optical wireless and electromagnetic wireless, the specific structural block diagram of the simultaneous interpretation module, the specific structural block diagram of the interpretation status determination module, and the connection structural block diagram of the operating parameter adjustment module connected to the simultaneous interpretation module and the simultaneous interpretation module, respectively. The present invention provides a dual-link simultaneous interpretation system based on optical wireless and electromagnetic wireless, comprising:

[0047] The simultaneous interpretation module is used to convert the sound signals collected by the sound acquisition device into sound signals in the corresponding language.

[0048] The simultaneous interpretation state determination module, connected to the simultaneous interpretation module, acquires and calculates the corresponding operating parameters of the simultaneous interpretation module to output simultaneous interpretation feature parameters, and determines the simultaneous interpretation state based on the simultaneous interpretation feature parameters. This includes a continuity determination unit for determining the continuity of simultaneous interpretation based on the average difference in the translation duration of words with the same part of speech; a speech synthesis state determination unit connected to the continuity determination unit for determining the speech synthesis state based on the proportion of tone-altering characters in the translation; an information security risk determination unit connected to the speech synthesis state determination unit for determining information security risks based on the fitting degree between the number of network attacks and the screening length of the sound field during the encoding process; and a signal interference degree determination unit connected to the information security risk determination unit for determining the signal interference degree based on the frequency difference between the decoded sound signal and the original sound signal.

[0049] The operating parameter adjustment module is connected to both the simultaneous interpretation module and the interpretation status determination module. It is used to adjust the operating characteristic parameters of the simultaneous interpretation module according to the simultaneous interpretation status determination result of the interpretation status determination module. The operating characteristic parameters of the simultaneous interpretation module include the granularity of the sound signal selection, the number of basic sound template types, and the number of words called in the decoding process.

[0050] Specifically, the simultaneous interpretation module includes:

[0051] Sound acquisition component, used to acquire sound signals;

[0052] An encoding component, which is connected to the sound acquisition component, is used to encode the acquired sound signal and convert it into a digital signal;

[0053] A transmission decoding component, which is connected to the encoding component, is used to transmit and decode the digital signal;

[0054] A speech synthesis component, connected to the transmission decoding component, is used to convert the decoded sound signal into speech information;

[0055] A translation output component, which is connected to the speech synthesis component, is used to translate the speech information into text in the corresponding language and output it.

[0056] Specifically, the interpretation status includes the continuity of simultaneous interpretation, the status of speech synthesis, information security risks, and the degree of signal interference.

[0057] Specifically, the basic audio template types include audio clarity, speech rate, and tone.

[0058] Specifically, the sound signal is transmitted wirelessly via optical path and electromagnetic wave wireless transmission.

[0059] Among them, optical wireless transmission is carried out through optical fiber or visible light communication; electromagnetic wave wireless transmission is carried out through wireless local area network or Bluetooth.

[0060] Specifically, the granularity of the sound signal filtering is the maximum filtering field length of the sound signal.

[0061] Specifically, the formula for calculating the average difference in translation time for words with the same part of speech is as follows:

[0062]

[0063] Where Z represents the average difference in translation time for words with the same part of speech, |X n -B n | represents the absolute value of the difference between the translation time of the first word and the translation time of the second word in the nth word group with the same part of speech, where n is the number of word groups with the same part of speech and is a natural number greater than or equal to 1.

[0064] Specifically, the goodness of fit between the number of network attacks and the filtering length of the audio field during the encoding process refers to the degree of fit between the number of network attacks in historical data and the filtering length of the audio field. Specifically, in a Cartesian coordinate system with the number of network attacks as the ordinate and the filtering length of the audio field during the encoding process as the abscissa, several periods of network attack counts are represented by the ordinate, and several periods of audio field filtering length during the encoding process are represented by the abscissa. These coordinates form several coordinate points, and MATLAB software is used to perform a linear function fitting on these coordinate points... When a linear function fitting image is obtained, the variance of the linear distance between each coordinate point not on the linear function image and the straight line of the fitting function, along with the proportion of coordinate points not on the linear function image, jointly reflect the goodness of fit. The smaller the variance, the greater the linear correlation between the number of network attacks and the selection length of the audio field in the encoding process; conversely, the smaller the variance, the smaller the linear correlation between the number of network attacks and the selection length of the audio field in the encoding process. Similarly, the smaller the proportion of coordinate points not on the linear function image, the higher the goodness of fit, and the greater the linear correlation between the number of network attacks and the selection length of the audio field in the encoding process.

[0065] Specifically, the formula for calculating the frequency difference between the decoded audio signal and the original audio signal is as follows:

[0066] S = |EF|

[0067] Where S is the frequency difference between the decoded audio signal and the original audio signal, E is the frequency of the decoded audio signal, and F is the frequency of the original audio signal.

[0068] The system described in this invention, by setting up a simultaneous interpretation module, an interpretation status determination module, and an operating parameter adjustment module, performs an initial adjustment on the granularity of the audio signal selection when the continuity of simultaneous interpretation falls below the allowable range. This reduces the impact of inaccurate adjustment of the audio signal selection granularity leading to excessively large segmentation granularity and thus a decrease in the continuity of simultaneous interpretation. The system further adjusts the number of basic audio template types based on the proportion of tonal abrupt changes in the translated text, reducing the impact of inaccurate adjustment leading to a small number of audio template types and thus a decrease in the quality of simultaneous interpretation. A second adjustment is made to the granularity of the audio signal selection based on the fit between the number of network attacks and the selection length of audio fields during the encoding process. This reduces the impact of inaccurate adjustment of the second adjustment leading to excessively small segmentation granularity and thus a decrease in the continuity of simultaneous interpretation. Finally, the system adjusts the number of words called during the decoding process based on the frequency difference between the decoded audio signal and the original audio signal, reducing the impact of inaccurate adjustment of the number of words called during the decoding process leading to insufficient decoding accuracy and thus a decrease in the quality of simultaneous interpretation. This achieves an improvement in both the continuity and quality of simultaneous interpretation.

[0069] Please continue reading. Figure 1 As shown, the corresponding operating parameters include the word translation time, the number of words with pitch mutations, the number of network attacks, the filtering length of the sound field during the encoding process, the frequency of the decoded sound signal, and the frequency of the original sound signal.

[0070] Please continue reading. Figure 1 As shown, the simultaneous interpretation feature parameters include the average difference in the translation time of words with the same part of speech, the proportion of words with abrupt changes in tone in the translation, the fit between the number of network attacks and the screening length of the sound field in the encoding process, and the frequency difference between the decoded sound signal and the original sound signal.

[0071] Please continue reading. Figure 2 As shown, the continuity determination unit includes a first invocation component connected to the simultaneous interpretation module and a first determination component connected to the first invocation component, wherein,

[0072] The first calling component is used to call the translation time of the word, and calculate the average difference in translation time of words with the same part of speech based on the calling result;

[0073] The first determination component is used to determine that the continuity of simultaneous interpretation is below the allowable range when a preset first average difference condition or a preset second average difference condition is triggered.

[0074] The first preset average difference condition is that the average difference in translation time of words with the same part of speech is greater than the first preset average difference and less than or equal to the second preset average difference; the second preset average difference condition is that the average difference in translation time of words with the same part of speech is greater than the second preset average difference; and the first preset average difference is less than the second preset average difference.

[0075] Specifically, the average difference in translation time for words with the same part of speech is denoted as Q. The first average difference is preset as Q1 = 0.02s, the second average difference is preset as Q2 = 0.03s, and the difference between the average difference in translation time for words with the same part of speech and the preset second average difference is denoted as △Q. △Q is set to Q - Q2.

[0076] The system described in this invention determines the continuity of simultaneous interpretation by setting a preset first average difference and a preset second average difference, thereby reducing the impact of inaccurate determination of the continuity of simultaneous interpretation that leads to a decline in the quality of simultaneous interpretation and further improving the continuity and quality of simultaneous interpretation.

[0077] Please continue reading. Figure 2 As shown, the speech synthesis state determination unit includes a second invocation component connected to the simultaneous interpretation module and a second determination component connected to the second invocation component, wherein,

[0078] The second calling component is used to collect the number of tone-altering characters and calculate the proportion of tone-altering characters in the translation based on the collection results;

[0079] The second determination component is used to initially determine that the effectiveness of speech synthesis is below the allowable range when the preset first average difference condition is triggered, and to determine a second time that the effectiveness of speech synthesis is below the allowable range when the preset percentage condition is triggered.

[0080] The preset percentage condition is that the percentage of characters with abrupt tonal changes in the translated text is greater than the preset percentage.

[0081] Specifically, the preset percentage is denoted as P1 = 0.3, the percentage of characters with abrupt changes in tone in the translation is denoted as P, the difference between the percentage of characters with abrupt changes in tone in the translation and the preset percentage is denoted as △P, and △P = P - P1 is set.

[0082] The system described in this invention sets a preset percentage and performs a secondary judgment on the effectiveness of speech synthesis under the preset percentage condition. This reduces the impact of the discontinuity of the synthesized sound signal caused by the inaccuracy of the secondary judgment on the effectiveness of speech synthesis, which leads to a decrease in the quality of simultaneous interpretation. This further improves the continuity and quality of simultaneous interpretation.

[0083] Please continue reading. Figure 2 As shown, the information security risk assessment unit includes a third calling component connected to the simultaneous interpretation module and a third assessment component connected to the third calling component, wherein,

[0084] The third calling component is used to obtain the number of network attacks and the filtering length of the audio field in the encoding process, and to calculate the goodness of fit between the number of network attacks and the filtering length of the audio field in the encoding process based on the acquisition results.

[0085] The third determination component is used to determine that the information security risk is below the allowable range when the first condition and the preset first fit condition are triggered simultaneously or when the first condition and the preset second fit condition are triggered simultaneously.

[0086] The first preset goodness-of-fit condition is that the goodness-of-fit between the number of network attacks and the filtering length of the audio field during the encoding process is greater than the first preset goodness-of-fit and less than or equal to the second preset goodness-of-fit; the second preset goodness-of-fit condition is that the goodness-of-fit between the number of network attacks and the filtering length of the audio field during the encoding process is greater than the preset goodness-of-fit; the first preset goodness-of-fit is less than the second preset goodness-of-fit; the first condition is that the running parameter adjustment module completes the initial adjustment of the filtering granularity of the audio signal.

[0087] Specifically, the first degree of fit is set as Y1 = 0.5, the second degree of fit is set as Y2 = 0.6, the degree of fit between the number of network attacks and the filtering length of the audio field in the encoding process is set as Y, the difference between the degree of fit between the number of network attacks and the filtering length of the audio field in the encoding process and the first degree of fit is set as ΔY, and ΔY = Y - Y1 is set.

[0088] The system described in this invention determines information security risks by setting a preset first degree of fit and a preset second degree of fit, thereby reducing the impact of inaccurate determination of information security risks on the continuity of simultaneous interpretation and further improving the continuity and quality of simultaneous interpretation.

[0089] Please continue reading. Figure 2 As shown, the signal interference level determination unit includes a fourth calling component connected to the simultaneous interpretation module and a fourth determination component connected to the fourth calling component, wherein,

[0090] The fourth calling component is used to retrieve the frequency of the decoded sound signal and the frequency of the original sound signal, and to calculate the frequency difference between the decoded sound signal and the original sound signal based on the retrieval result;

[0091] The fourth determination component is used to initially determine that the signal interference level exceeds the allowable range when the preset second fit condition is triggered, and to determine a second time that the signal interference level exceeds the allowable range when the preset frequency difference condition is triggered.

[0092] Specifically, the preset frequency difference is denoted as R0 = 30Hz, the frequency difference between the decoded audio signal and the original audio signal is denoted as R, the difference between the frequency difference between the decoded audio signal and the original audio signal and the preset frequency difference is denoted as ΔR, and ΔR is set to R - R0.

[0093] The system described in this invention reduces the impact of inaccurate secondary determination of signal interference level caused by setting a preset frequency difference amount, thereby improving the continuity and quality of simultaneous interpretation.

[0094] Please continue reading. Figure 3 As shown, the preset frequency difference condition is that the frequency difference between the decoded sound signal and the original sound signal is greater than the preset frequency difference.

[0095] Please continue reading. Figure 3 As shown, the operating parameter adjustment module includes a first parameter adjustment component connected to the first determination component and the third determination component, a second parameter adjustment component connected to the second determination component, and a third parameter adjustment component connected to the fourth determination component.

[0096] The first parameter adjustment component is used to initially adjust the screening granularity of the sound signal to output the screening granularity of the first sound signal when the preset second average difference condition is triggered, and to perform a second adjustment on the screening granularity of the sound signal to output the screening granularity of the second sound signal when the preset first fit condition is triggered.

[0097] The second parameter adjustment component is used to adjust the number of basic sound template types when the preset proportion condition is triggered;

[0098] The third parameter adjustment component is used to adjust the number of words called during the decoding process when the preset frequency difference condition is triggered.

[0099] Please continue reading. Figure 3As shown, the filtering granularity of the first sound signal is inversely proportional to the difference between the average difference in the translation time of words with the same part of speech and the preset second average difference.

[0100] Specifically, the operating parameter adjustment module adjusts the screening granularity of the sound signal to the first granularity under the condition of a preset first average difference value; the preset first average difference value condition is that the difference between the average difference value of the translation time of words with the same part of speech and the preset second average difference value is less than or equal to the preset average difference value.

[0101] The operating parameter adjustment module adjusts the screening granularity of the sound signal to the second granularity under the condition of a preset second average difference value; the preset second average difference value condition is that the difference between the average difference value of the translation time of words with the same part of speech and the preset second average difference value is greater than the preset average difference value.

[0102] Wherein, the preset first granularity adjustment coefficient is smaller than the preset second granularity adjustment coefficient.

[0103] Specifically, the preset average difference value is denoted as △Q0 = 0.02s, the preset first granularity adjustment coefficient is denoted as α1 = 0.8, the preset second granularity adjustment coefficient is denoted as α2 = 0.9, the granularity of the sound signal is denoted as V, where 0 < α1 < α2 < 1, the granularity of the adjusted first sound signal is denoted as V', and V' = V × (1 + αi) / 2 is set, where αi is the preset ith granularity adjustment coefficient, and i = 1, 2.

[0104] The system described in this invention adjusts the granularity of sound signal filtering under a preset average difference value and a preset second average difference value. This reduces the impact of inaccurate recognition fields caused by excessively large sound signal filtering granularity, which leads to a decrease in the continuity of simultaneous interpretation and further improves the continuity and quality of simultaneous interpretation.

[0105] Please continue reading. Figure 3 As shown, the number of the basic sound template types is directly proportional to the difference between the proportion of texts with abrupt changes in tone in the translation and the preset proportion.

[0106] Specifically, the operating parameter adjustment module adjusts the number of the basic sound template types to the number of the first type using a preset first type quantity adjustment coefficient under a preset first proportion difference condition; the preset first proportion difference condition is that the difference between the proportion of tone change texts in the translation and the preset proportion is less than or equal to the preset proportion difference.

[0107] The operating parameter adjustment module adjusts the quantity of the basic sound template type to the second type quantity using a preset second type quantity adjustment coefficient under a preset second proportion difference condition; the preset second proportion difference condition is that the difference between the proportion of tone change texts in the translation and the preset proportion is greater than the preset proportion difference.

[0108] Wherein, the preset first type quantity adjustment coefficient is less than the preset second type quantity adjustment coefficient.

[0109] Specifically, the preset percentage difference is denoted as △P0=0.1, the preset first type quantity adjustment coefficient is denoted as β1=1.2, the preset second type quantity adjustment coefficient is denoted as β2=1.3, the quantity of sound basic template types is denoted as H, where 1<β1<β2, the adjusted quantity of sound basic template types is denoted as H', and H'=H×(1+2βj) / 3 is set, where βj is the preset j-th type quantity adjustment coefficient, and j=1,2 is set.

[0110] The system described in this invention adjusts the number of basic sound template types under a preset ratio by setting a preset ratio difference. This reduces the impact of a decrease in the quality of simultaneous interpretation caused by an insufficient number of basic sound template types, and further improves the continuity and quality of simultaneous interpretation.

[0111] Please continue reading. Figure 4 As shown, the granularity of the second sound signal is proportional to the difference between the degree of fit between the number of network attacks and the length of the sound field in the encoding process and the preset first degree of fit.

[0112] Specifically, the operating parameter adjustment module uses a preset third granularity secondary adjustment coefficient to adjust the screening granularity of the first sound signal to the third granularity under the condition of a preset first fitting degree difference; the preset first fitting degree difference condition is that the difference between the fitting degree of the number of network attacks and the screening length of the sound field in the encoding process and the preset first fitting degree is less than or equal to the preset fitting degree difference.

[0113] The operating parameter adjustment module uses a preset fourth granularity secondary adjustment coefficient to adjust the screening granularity of the first sound signal to the fourth granularity under the preset second fitting degree difference condition; the preset second fitting degree difference condition is that the difference between the fitting degree of the number of network attacks and the screening length of the sound field in the encoding process and the preset first fitting degree is greater than the preset fitting degree difference.

[0114] Wherein, the preset third granularity secondary adjustment coefficient is less than the preset fourth granularity secondary adjustment coefficient.

[0115] Specifically, the preset fitting difference is denoted as ΔY = 0.2, the preset third granularity secondary adjustment coefficient is denoted as α3 = 1.3, the preset fourth granularity secondary adjustment coefficient is denoted as α4 = 1.4, where 1 < α3 < α4, the granularity of the adjusted second sound signal is denoted as V”, and V” = V' × (1 + αm) / 2 is set, where αm is the preset m-th granularity secondary adjustment coefficient, and m = 3, 4 is set.

[0116] The system described in this invention adjusts the granularity of the sound signal selection secondaryly under a preset first degree of fit by setting a preset fitting difference value. This reduces the impact of the decrease in the continuity of simultaneous interpretation caused by the excessively small granularity of the sound signal selection, and further improves the continuity and quality of simultaneous interpretation.

[0117] Please continue reading. Figure 4 As shown, the number of words called in the decoding process is proportional to the difference between the frequency difference between the decoded sound signal and the original sound signal and the preset frequency difference.

[0118] Specifically, the operating parameter adjustment module adjusts the number of words called in the decoding process to the first number of words under the condition of a preset first frequency difference difference. The preset first frequency difference difference condition is that the difference between the frequency difference between the decoded sound signal and the original sound signal and the preset frequency difference is less than or equal to the preset frequency difference difference.

[0119] The operating parameter adjustment module adjusts the number of words called in the decoding process to the second number of words under the condition of a preset second frequency difference difference. The preset second frequency difference difference condition is that the difference between the frequency difference between the decoded sound signal and the original sound signal and the preset frequency difference is greater than the preset frequency difference difference.

[0120] Wherein, the preset first word quantity adjustment coefficient is less than the preset second word quantity adjustment coefficient.

[0121] Specifically, the preset frequency difference is denoted as △R0 = 20Hz, the preset first word quantity adjustment coefficient is denoted as γ1 = 1.1, the preset second word quantity adjustment coefficient is denoted as γ2 = 1.2, the number of words called in the decoding process is denoted as L, where 1 < γ1 < γ2, the number of words called in the adjusted decoding process is denoted as L', and L' = L × (1 + 3γm) / 4 is set, where γw is the preset w-th word quantity adjustment coefficient, and w = 1, 2 is set.

[0122] The system described in this invention adjusts the number of words called during the decoding process by setting a preset frequency difference value. This reduces the impact of insufficient vocabulary used in the decoding process on the quality of simultaneous interpretation, and further improves the continuity and quality of simultaneous interpretation.

[0123] Example 1

[0124] In this embodiment, the parameter adjustment module adjusts the filtering granularity of the sound signal based on the difference between the average difference in the translation time of words with the same part of speech and the preset second average difference. The preset average difference is denoted as △Q0, the preset first granularity adjustment coefficient is denoted as α1, the preset second granularity adjustment coefficient is denoted as α2, and the filtering granularity of the sound signal is denoted as V. 0 < α1 < α2 < 1, and α1 = 0.8, α2 = 0.9, △Q0 = 0.02s, and V = 4 bytes.

[0125] In this embodiment 1, ΔQ = 0.03s is obtained. The running parameter adjustment module determines that ΔQ > ΔQ0 and uses the preset first granularity adjustment coefficient to adjust the screening granularity of the sound signal to the second granularity, and calculates V' = 4 bytes × (1 + 0.8) / 2 = 3 bytes.

[0126] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0127] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A dual-link simultaneous interpretation system based on optical path and electromagnetic wave wireless communication, characterized in that, include: The simultaneous interpretation module is used to convert the sound signals collected by the sound acquisition device into sound signals in the corresponding language. The simultaneous interpretation state determination module, connected to the simultaneous interpretation module, acquires and calculates the corresponding operating parameters of the simultaneous interpretation module to output simultaneous interpretation feature parameters, and determines the simultaneous interpretation state based on the simultaneous interpretation feature parameters. This includes a continuity determination unit for determining the continuity of simultaneous interpretation based on the average difference in the translation duration of words with the same part of speech; a speech synthesis state determination unit connected to the continuity determination unit for determining the speech synthesis state based on the proportion of tone-altering characters in the translation; an information security risk determination unit connected to the speech synthesis state determination unit for determining information security risks based on the fitting degree between the number of network attacks and the screening length of the sound field during the encoding process; and a signal interference degree determination unit connected to the information security risk determination unit for determining the signal interference degree based on the frequency difference between the decoded sound signal and the original sound signal. The operating parameter adjustment module is connected to both the simultaneous interpretation module and the interpretation status determination module. It is used to adjust the operating characteristic parameters of the simultaneous interpretation module according to the simultaneous interpretation status determination result of the interpretation status determination module. The operating characteristic parameters of the simultaneous interpretation module include the granularity of the sound signal selection, the number of basic sound template types, and the number of words called in the decoding process.

2. The dual-link simultaneous interpretation system based on optical path and electromagnetic wave wireless as described in claim 1, characterized in that, The corresponding operating parameters include the word translation time, the number of words with pitch changes, the number of network attacks, the filtering length of the sound field during the encoding process, the frequency of the decoded sound signal, and the frequency of the original sound signal.

3. The dual-link simultaneous interpretation system based on optical path and electromagnetic wave wireless as described in claim 2, characterized in that, The simultaneous interpreting feature parameters include the average difference in the translation time of words with the same part of speech, the proportion of words with abrupt changes in tone in the translation, the fit between the number of network attacks and the screening length of the sound field in the encoding process, and the frequency difference between the decoded sound signal and the original sound signal.

4. The dual-link simultaneous interpretation system based on optical path and electromagnetic wave wireless as described in claim 3, characterized in that, The continuity determination unit includes a first invocation component connected to the simultaneous interpretation module and a first determination component connected to the first invocation component, wherein... The first calling component is used to call the translation time of the word, and calculate the average difference in translation time of words with the same part of speech based on the calling result; The first determination component is used to determine that the continuity of simultaneous interpretation is below the allowable range when a preset first average difference condition or a preset second average difference condition is triggered. The first preset average difference condition is that the average difference in translation time of words with the same part of speech is greater than the first preset average difference and less than or equal to the second preset average difference; the second preset average difference condition is that the average difference in translation time of words with the same part of speech is greater than the second preset average difference; and the first preset average difference is less than the second preset average difference.

5. The dual-link simultaneous interpretation system based on optical path and electromagnetic wave wireless as described in claim 4, characterized in that, The speech synthesis state determination unit includes a second invocation component connected to the simultaneous interpretation module and a second determination component connected to the second invocation component, wherein... The second calling component is used to collect the number of tone-altering characters and calculate the proportion of tone-altering characters in the translation based on the collection results; The second determination component is used to initially determine that the effectiveness of speech synthesis is below the allowable range when the preset first average difference condition is triggered, and to determine a second time that the effectiveness of speech synthesis is below the allowable range when the preset percentage condition is triggered. The preset percentage condition is that the percentage of characters with abrupt tonal changes in the translated text is greater than the preset percentage.

6. The dual-link simultaneous interpretation system based on optical path and electromagnetic wave wireless as described in claim 5, characterized in that, The information security risk assessment unit includes a third calling component connected to the simultaneous interpretation module and a third assessment component connected to the third calling component, wherein, The third calling component is used to obtain the number of network attacks and the filtering length of the audio field in the encoding process, and to calculate the goodness of fit between the number of network attacks and the filtering length of the audio field in the encoding process based on the acquisition results. The third determination component is used to determine that the information security risk is below the allowable range when the first condition and the preset first fit condition are triggered simultaneously or when the first condition and the preset second fit condition are triggered simultaneously. The first preset goodness-of-fit condition is that the goodness-of-fit between the number of network attacks and the filtering length of the audio field during the encoding process is greater than the first preset goodness-of-fit and less than or equal to the second preset goodness-of-fit; the second preset goodness-of-fit condition is that the goodness-of-fit between the number of network attacks and the filtering length of the audio field during the encoding process is greater than the second preset goodness-of-fit; the first preset goodness-of-fit is that the running parameter adjustment module completes the initial adjustment of the filtering granularity of the audio signal.

7. The dual-link simultaneous interpretation system based on optical path and electromagnetic wave wireless as described in claim 6, characterized in that, The signal interference level determination unit includes a fourth calling component connected to the simultaneous interpretation module and a fourth determination component connected to the fourth calling component, wherein, The fourth calling component is used to retrieve the frequency of the decoded sound signal and the frequency of the original sound signal, and to calculate the frequency difference between the decoded sound signal and the original sound signal based on the retrieval result; The fourth determination component is used to initially determine that the signal interference level exceeds the allowable range when the preset second fit condition is triggered, and to determine a second time that the signal interference level exceeds the allowable range when the preset frequency difference condition is triggered.

8. The dual-link simultaneous interpretation system based on optical path and electromagnetic wave wireless as described in claim 7, characterized in that, The preset frequency difference condition is that the frequency difference between the decoded audio signal and the original audio signal is greater than the preset frequency difference.

9. The dual-link simultaneous interpretation system based on optical path and electromagnetic wave wireless as described in claim 8, characterized in that, The operating parameter adjustment module includes a first parameter adjustment component connected to the first determination component and the third determination component, a second parameter adjustment component connected to the second determination component, and a third parameter adjustment component connected to the fourth determination component. The first parameter adjustment component is used to initially adjust the screening granularity of the sound signal to output the screening granularity of the first sound signal when the preset second average difference condition is triggered, and to perform a second adjustment on the screening granularity of the sound signal to output the screening granularity of the second sound signal when the preset first fit condition is triggered. The second parameter adjustment component is used to adjust the number of basic sound template types when the preset proportion condition is triggered; The third parameter adjustment component is used to adjust the number of words called during the decoding process when the preset frequency difference condition is triggered.

10. The dual-link simultaneous interpretation system based on optical path and electromagnetic wave wireless as described in claim 9, characterized in that, The granularity of the first sound signal is inversely proportional to the difference between the average difference in translation time of words with the same part of speech and the preset second average difference; the number of the basic sound template types is directly proportional to the difference between the proportion of tone-altering characters in the translation and the preset proportion; the granularity of the second sound signal is directly proportional to the difference between the goodness of fit of the number of network attacks and the length of the sound field in the encoding process and the preset first goodness of fit; the number of words called in the decoding process is directly proportional to the difference between the frequency difference between the decoded sound signal and the original sound signal and the preset frequency difference.

Images