Voice test method, device, system, electronic equipment and storage medium

Abstract

This disclosure provides a voice testing method, apparatus, system, electronic device, and storage medium, relating to artificial intelligence fields such as intelligent voice, AI chips, and natural language processing. The method may include: a main control chip acquiring and storing audio data from a voice chip, wherein the main control chip and the voice chip are located in the same product; the main control chip determining test data based on the stored audio data, sending the test data to the voice chip, and obtaining the algorithm processing results generated from the test data returned by the voice chip; and the main control chip determining test indicators based on the algorithm processing results. Applying the solution described in this disclosure can reduce implementation costs and improve testing efficiency.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and in particular to voice testing methods, devices, systems, electronic devices and storage media in the fields of intelligent voice, artificial intelligence chips and natural language processing. Background Technology

[0002] For intelligent voice products that use a main control chip and a voice chip, voice testing usually requires setting up different test environments for different products to simulate different real-world scenarios, which increases implementation costs and reduces testing efficiency. Summary of the Invention

[0003] This disclosure provides voice testing methods, apparatus, systems, electronic devices, and storage media.

[0004] A voice testing method, comprising:

[0005] The main control chip acquires and saves audio data from the voice chip, and the main control chip and the voice chip are located in the same product;

[0006] The main control chip determines the puncturing data based on the stored audio data, sends the puncturing data to the voice chip, and obtains the algorithm processing result generated by the voice chip based on the puncturing data.

[0007] The main control chip determines the test indicators based on the algorithm processing results.

[0008] A voice testing method, comprising:

[0009] The voice chip acquires audio data and outputs the acquired audio data to the main control chip, wherein the main control chip and the voice chip are located in the same product;

[0010] The voice chip acquires the perfusion test data from the main control chip, generates an algorithm processing result based on the perfusion test data, and outputs the algorithm processing result to the main control chip. The main control chip uses the algorithm processing result to determine the test indicators. The perfusion test data is the perfusion test data determined by the main control chip based on the stored audio data.

[0011] A voice testing device includes: a data acquisition module, a first phonation testing module, and a second phonation testing module;

[0012] The data acquisition module is used to acquire and save audio data from the voice chip. The main control chip of the voice testing device and the voice chip are located in the same product.

[0013] The first perfusion module is used to determine perfusion data based on the stored audio data, send the perfusion data to the voice chip, and obtain the algorithm processing result generated by the voice chip based on the perfusion data.

[0014] The second irrigation module is used to determine the test indicators based on the algorithm processing results.

[0015] A voice testing device includes: a data acquisition module and a third recording module;

[0016] The data acquisition module is used to acquire audio data and output the acquired audio data to the main control chip. The main control chip and the voice chip of the voice testing device are located in the same product.

[0017] The third perfusion testing module is used to acquire perfusion testing data from the main control chip, generate algorithm processing results based on the perfusion testing data, and output the algorithm processing results to the main control chip, so that the main control chip can determine test indicators based on the algorithm processing results. The perfusion testing data is the perfusion testing data determined by the main control chip based on the stored audio data.

[0018] A voice testing system includes: the two voice testing devices as described above.

[0019] An electronic device, comprising:

[0020] At least one processor; and

[0021] A memory communicatively connected to the at least one processor; wherein,

[0022] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described above.

[0023] A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the methods described above.

[0024] A computer program product includes a computer program / instructions that, when executed by a processor, implement the method described above.

[0025] One embodiment disclosed above has the following advantages or beneficial effects: the main control chip and the voice chip can interact through information and realize voice testing through a percussion test, thereby eliminating the need to build a test environment, thus reducing implementation costs and improving test efficiency.

[0026] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0027] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0028] Figure 1 This is a flowchart of the first embodiment of the voice testing method described in this disclosure;

[0029] Figure 2 This is a flowchart of the second embodiment of the voice testing method described in this disclosure;

[0030] Figure 3 This is a schematic diagram illustrating the data flow of the audio data acquisition described in this disclosure;

[0031] Figure 4 This is a schematic diagram illustrating the flow direction of the irrigation data described in this disclosure;

[0032] Figure 5 This is a schematic diagram of the composition structure of the first embodiment 500 of the voice testing device described in this disclosure;

[0033] Figure 6 This is a schematic diagram of the composition structure of the second embodiment 600 of the voice testing device described in this disclosure;

[0034] Figure 7 This is a schematic diagram of the composition structure of embodiment 700 of the voice testing system described in this disclosure;

[0035] Figure 8 A schematic block diagram of an electronic device 800 that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation

[0036] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0037] Furthermore, it should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0038] Figure 1 This is a flowchart of the first embodiment of the voice testing method described in this disclosure. Figure 1 As shown, the specific implementation methods are as follows.

[0039] In step 101, the main control chip acquires and saves audio data from the voice chip, and the main control chip and the voice chip are located in the same product.

[0040] In step 102, the main control chip determines the puncturing data based on the stored audio data, sends the puncturing data to the voice chip, and obtains the algorithm processing result generated based on the puncturing data returned by the voice chip.

[0041] In step 103, the main control chip determines the test indicators based on the obtained algorithm processing results.

[0042] As can be seen, in the above-described method embodiments, the main control chip and the voice chip can interact through information and achieve voice testing through a percussion test, thereby eliminating the need to build a test environment, which reduces implementation costs and improves testing efficiency.

[0043] Preferably, the product can be an intelligent voice product. In traditional intelligent voice products, algorithms and application processes are implemented in the main control chip. However, in intelligent voice products that use a main control chip + voice chip, the processing of algorithms can be ported to the voice chip, thereby reducing the computing power burden on the main control chip.

[0044] Preferably, the solution described in this disclosure can be used on Android or Unix-like operating system (Linux) platforms. Unix is ​​an operating system that emerged in the early 1970s and can be used as a network operating system as well as a standalone operating system.

[0045] In one embodiment of this disclosure, the main control chip can send configuration information to the voice chip and acquire and save audio data collected by the voice chip according to the configuration information. The configuration information can be pre-generated, such as manually pre-configured. The required audio data to be collected can be flexibly set through the configuration information.

[0046] Furthermore, the specific content included in the configuration information can be determined according to actual needs. In one embodiment of this disclosure, the configuration information may include: the number of configured microphones (MICs), the data sources corresponding to different microphones, the number of configured back-collection signals, and the data sources corresponding to different back-collection signals.

[0047] For example, the number of microphones can be 2, 3, 4, 6, or 8, and the data source for different microphones can be an integrated circuit built-in audio bus (I2S, Inter-IC Sound), pulse density modulation (PDM), or time division multiplexing (TDM), etc. Additionally, the number of back-sampled signals can be 1, 2, 3, or 4, and the data source for different back-sampled signals can be I2S or TDM, etc.

[0048] Different microphones can be connected to the voice chip separately.

[0049] Accordingly, in one embodiment of this disclosure, the main control chip can acquire and store a first type of audio data and a second type of audio data from the voice chip. The first type of audio data is audio data acquired through a microphone, and the second type of audio data is re-acquired audio data. The re-acquired audio data typically refers to the audio data played by the main control chip, such as the audio data corresponding to a song played by the user, and can also be called reference data.

[0050] In practical applications, the audio data acquired and stored by the main control chip from the voice chip may include not only the first and second types of audio data mentioned above, but may also include other audio data, and there is no limitation on which audio data is specifically included.

[0051] The above processing method can achieve the acquisition of the required audio data in a simple and efficient way, thus laying a good foundation for subsequent processing.

[0052] Based on the stored audio data, the main control chip can determine the sampling data and send it to the voice chip. In one embodiment of this disclosure, the main control chip can send the stored first type of audio data and second type of audio data as sampling data to the voice chip.

[0053] Furthermore, the main control chip can obtain the algorithm processing results returned by the voice chip, which are generated based on the sampling data. In one embodiment of this disclosure, the main control chip can obtain the algorithm processing results returned by the voice chip after performing algorithm processing on the first type of audio data in combination with the second type of audio data.

[0054] In practical applications, the stored audio data can be used to train the algorithm model, and the trained algorithm model can be applied to the speech chip to test the correctness of the algorithm model. Accordingly, the speech chip can use the algorithm model to process the first type of audio data to obtain the algorithm processing result.

[0055] In addition, the first type of audio data can be processed by denoising using the second type of audio data, and then the processed first type of audio data can be processed by algorithms, thereby improving the accuracy of the obtained algorithm processing results.

[0056] In one embodiment of this disclosure, the configuration information may further include: the type and order of the configured output data. Accordingly, when the main control chip obtains the algorithm processing result returned by the voice chip and generated based on the perfusion data, it can obtain the algorithm processing result output by the voice chip that conforms to the type and order of the output data.

[0057] The voice chip can include many algorithms. Configuration information can be used to tell the voice chip which data needs to be output to the main control chip and in what order. The output algorithm processing results can include the final algorithm processing result, intermediate data (i.e., the algorithm processing results of intermediate processes), or the algorithm processing results of all algorithms in the voice chip, or only the algorithm processing results of some algorithms.

[0058] By configuring the type and order of output data, useless data output is avoided and the correct output order is ensured, thereby avoiding resource waste and improving output efficiency.

[0059] In addition to the information described above, the configuration information may also include other information if needed, such as control information for starting and stopping data acquisition.

[0060] In addition, the main control chip can also determine test indicators based on the obtained algorithm processing results. There are no restrictions on how the test indicators are determined based on the obtained algorithm processing results.

[0061] For example, recognition performance indicators (i.e., the test indicators) can be obtained: the main control chip can send the algorithm processing results obtained from the voice chip to the cloud for recognition, and can obtain the recognition results from the cloud. Then, for the process from sending the test data to the voice chip to obtaining the recognition results, the required performance indicators, such as algorithm processing speed, network latency, and the accuracy of the recognition results, can be statistically obtained.

[0062] For example, wake-up performance metrics can be obtained: the main control chip can obtain the wake-up information returned by the voice chip after processing the wake-up algorithm, and then the wake-up speed and wake-up rate can be statistically analyzed.

[0063] The above mainly describes the solution described in this disclosure from the perspective of the main control chip. The following further describes the solution described in this disclosure from the perspective of the voice chip.

[0064] Figure 2This is a flowchart of a second embodiment of the voice testing method described in this disclosure. Figure 2 As shown, the specific implementation methods are as follows.

[0065] In step 201, the voice chip acquires audio data and outputs the acquired audio data to the main control chip. The main control chip and the voice chip are located in the same product.

[0066] In step 202, the voice chip acquires the saturation test data from the main control chip, generates an algorithm processing result based on the saturation test data, and outputs the algorithm processing result to the main control chip. The main control chip uses the algorithm processing result to determine the test indicators. The saturation test data is the saturation test data determined by the main control chip based on the stored audio data.

[0067] In the above-described method embodiments, the main control chip and the voice chip can interact through information exchange and achieve voice testing through a percussion test, thereby eliminating the need to build a test environment, which reduces implementation costs and improves testing efficiency.

[0068] In one embodiment of this disclosure, the voice chip can obtain configuration information from the main control chip and perform audio data acquisition based on the configuration information.

[0069] In one embodiment of this disclosure, the configuration information may include: the number of configured microphones, the data sources corresponding to different microphones, the number of configured back-collection signals, and the data sources corresponding to different back-collection signals. Accordingly, a first type of audio data and a second type of audio data can be collected. The first type of audio data is the audio data collected through the microphones, and the second type of audio data is the back-collected audio data. That is, for different microphones, the first type of audio data can be collected according to the corresponding data source, and for different back-collection signals, the second type of audio data can be collected according to the corresponding data source.

[0070] The above processing method can achieve the acquisition of the required audio data in a simple and efficient way, thus laying a good foundation for subsequent processing.

[0071] Based on the stored audio data, the main control chip can determine the sampling data and output it to the speech chip. In one embodiment of this disclosure, the sampling data may include: a first type of audio data and a second type of audio data. Accordingly, the speech chip can combine the second type of audio data with the first type of audio data to perform algorithmic processing to obtain the algorithm processing result, and can output the algorithm processing result to the main control chip, so that the main control chip can determine the test indicators based on the algorithm processing result.

[0072] For example, noise reduction and other processing can be performed on the first type of audio data using the second type of audio data, and then the processed first type of audio data can be processed by algorithms, thereby improving the accuracy of the obtained algorithm processing results.

[0073] In one embodiment of this disclosure, the configuration information may further include: the type and order of the configured output data. Accordingly, the voice chip may output the algorithm processing result that conforms to the type and order of the output data to the main control chip.

[0074] The voice chip can include many algorithms. Configuration information can be used to tell the voice chip which data needs to be output to the main control chip and in what order. The output algorithm processing results can include the final algorithm processing result, intermediate data (i.e., the algorithm processing results of intermediate processes), or the algorithm processing results of all algorithms in the voice chip, or only the algorithm processing results of some algorithms.

[0075] By configuring the type and order of output data, useless data output is avoided and the correct output order is ensured, thereby avoiding resource waste and improving output efficiency.

[0076] In one embodiment of this disclosure, the voice chip can also monitor the computing power of the algorithm in real time, and can issue an alarm when it is determined that the computing power is overflowing.

[0077] The above procedures ensure that anomalies are detected and addressed promptly, thus guaranteeing the smooth progress of testing.

[0078] In summary, Figure 3 This is a schematic diagram illustrating the data flow of the audio data acquisition described in this disclosure.

[0079] like Figure 3 As shown, the main control chip can send configuration information to the voice chip, which may include: the number of microphones configured and the data source corresponding to each microphone, the number of back sampling signals configured and the data source corresponding to each back sampling signal, and the type and order of the output data configured.

[0080] like Figure 3 As shown, the voice chip can collect audio data based on the acquired configuration information, thereby obtaining a first type of audio data and a second type of audio data. The first type of audio data is the audio data collected through the microphone, and the second type of audio data is the audio data that is retried.

[0081] like Figure 3As shown, the voice chip can output the collected audio data to the main control chip. Specifically, the voice chip can put the collected audio data into the output data buffer, which is then read and saved by the main control chip.

[0082] exist Figure 3 During the audio data acquisition stage shown, the voice chip may not perform algorithmic processing on the acquired first type of audio data.

[0083] In summary, Figure 4 This is a schematic diagram illustrating the flow direction of the irrigation data described in this disclosure.

[0084] like Figure 4 As shown, the main control chip can read the first type of audio data and the second type of audio data from the stored audio data, and send them to the voice chip as test data. The audio data can be stored in network files, local files or disk files, etc.

[0085] like Figure 4 As shown, the voice chip can generate algorithm processing results based on the acquired perfusion data, and can output the algorithm processing results to the main control chip. Specifically, the voice chip can obtain the first type of audio data and the second type of audio data from the input data buffer, and can combine the second type of audio data to perform algorithm processing on the first type of audio data to obtain the algorithm processing results. Then, the algorithm processing results that meet the type and order of the output data required by the configuration information can be put into the output data buffer, which is then read and saved by the main control chip.

[0086] Furthermore, the main control chip can also determine test indicators based on the obtained algorithm processing results, such as recognition performance indicators and wake-up performance indicators.

[0087] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this disclosure is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this disclosure. Secondly, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this disclosure. Furthermore, for parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0088] In summary, by adopting the scheme described in the embodiments of the present invention, the main control chip and the voice chip can interact through information and achieve voice testing through a percussion method, thereby eliminating the need to build a test environment, which reduces implementation costs and improves test efficiency. Moreover, various data can be flexibly configured according to actual needs, which means it has strong configurability and is very flexible and convenient.

[0089] The above is an introduction to the method embodiments. The following describes the solution described in this disclosure further through device embodiments.

[0090] Figure 5 This is a schematic diagram of the structural composition of the first embodiment 500 of the voice testing device described in this disclosure. Figure 5 As shown, it includes: a data acquisition module 501, a first irrigation module 502, and a second irrigation module 503.

[0091] The data acquisition module 501 is used to acquire and save audio data from the voice chip. The main control chip and the voice chip of the voice testing device 500 are located in the same product.

[0092] The first puncturing module 502 is used to determine puncturing data based on the stored audio data, send the puncturing data to the speech chip, and obtain the algorithm processing results generated based on the puncturing data returned by the speech chip.

[0093] The second irrigation test module 503 is used to determine the test indicators based on the algorithm processing results.

[0094] In the above-described device embodiment, the main control chip and the voice chip can interact through information exchange and achieve voice testing through a percussion test method, thereby eliminating the need to build a test environment, which reduces implementation costs and improves testing efficiency.

[0095] In one embodiment of this disclosure, the data acquisition module 501 can send configuration information to the voice chip and acquire and save the audio data collected by the voice chip according to the configuration information.

[0096] In one embodiment of this disclosure, the configuration information may include: the number of microphones configured, the data sources corresponding to different microphones, the number of back-collection signals configured, and the data sources corresponding to different back-collection signals. Accordingly, the data acquisition module 501 can acquire and save a first type of audio data and a second type of audio data from the voice chip, wherein the first type of audio data is audio data collected by the microphone, and the second type of audio data is back-collected audio data.

[0097] For the stored audio data, the first sampling module 502 can determine the sampling data and send the sampling data to the voice chip. In one embodiment of this disclosure, the first sampling module 502 can send the stored first type of audio data and second type of audio data as sampling data to the voice chip.

[0098] Furthermore, the first irradiation module 502 can obtain the algorithm processing result generated based on the irradiation data returned by the voice chip. In one embodiment of this disclosure, the first irradiation module 502 can obtain the algorithm processing result returned by the voice chip after performing algorithm processing on the first type of audio data in combination with the second type of audio data.

[0099] In one embodiment of this disclosure, the configuration information may further include: the type and order of the configured output data. Accordingly, when the first perfusion module 502 obtains the algorithm processing result returned by the voice chip and generated based on the perfusion data, it may obtain the algorithm processing result output by the voice chip that conforms to the type and order of the output data.

[0100] In addition, the second irrigation module 503 can also determine test indicators based on the obtained algorithm processing results. There are no restrictions on how the test indicators are determined based on the obtained algorithm processing results.

[0101] Figure 6 This is a schematic diagram of the structural composition of the second embodiment 600 of the voice testing device described in this disclosure. Figure 6 As shown, it includes: a data acquisition module 601 and a third irrigation measurement module 602.

[0102] The data acquisition module 601 is used to acquire audio data and output the acquired audio data to the main control chip. The main control chip and the voice chip in the voice testing device 600 are located in the same product.

[0103] The third perfusion testing module 602 is used to acquire perfusion testing data from the main control chip, generate algorithm processing results based on the perfusion testing data, and output the algorithm processing results to the main control chip. The main control chip determines the test indicators based on the algorithm processing results. The perfusion testing data is the perfusion testing data determined by the main control chip based on the stored audio data.

[0104] In the above-described device embodiment, the main control chip and the voice chip can interact through information exchange and achieve voice testing through a percussion test method, thereby eliminating the need to build a test environment, which reduces implementation costs and improves testing efficiency.

[0105] In one embodiment of this disclosure, the data acquisition module 601 can obtain configuration information from the main control chip and perform audio data acquisition based on the configuration information.

[0106] In one embodiment of this disclosure, the configuration information may include: the number of microphones configured, the data sources corresponding to different microphones, the number of back-collection signals configured, and the data sources corresponding to different back-collection signals. Accordingly, the data acquisition module 601 can acquire a first type of audio data and a second type of audio data. The first type of audio data is audio data acquired through the microphones, and the second type of audio data is back-collected audio data. That is, for different microphones, the first type of audio data can be acquired according to the corresponding data source, and for different back-collection signals, the second type of audio data can be acquired according to the corresponding data source.

[0107] Based on the stored audio data, the main control chip can determine the puncturing data and output it to the voice chip. In one embodiment of this disclosure, the puncturing data may include: a first type of audio data and a second type of audio data. Accordingly, the third puncturing module 602 can combine the second type of audio data to perform algorithmic processing on the first type of audio data to obtain the algorithmic processing result, and can output the algorithmic processing result to the main control chip for the main control chip to determine the test indicators based on the algorithmic processing result.

[0108] In one embodiment of this disclosure, the configuration information may further include: the type and order of the configured output data. Accordingly, the third irrigation module 602 may output the algorithm processing result that conforms to the type and order of the output data to the main control chip.

[0109] In one embodiment of this disclosure, the third irrigation module 602 can also monitor the computing power of the algorithm in real time, and can perform alarm processing when it is determined that the computing power overflows.

[0110] Figure 7 This is a schematic diagram of the structural composition of embodiment 700 of the voice testing system described in this disclosure. Figure 7 As shown, it includes: Figure 5 The voice testing device 500 shown and Figure 6 The voice testing device 600 shown is referred to as the first voice testing device 500 and the second voice testing device 600 for easy distinction.

[0111] The specific workflow of the above-described apparatus and system embodiments can be found in the relevant descriptions in the foregoing method embodiments.

[0112] In summary, by adopting the solution described in the embodiments of the device and system disclosed herein, the main control chip and the voice chip can interact through information and achieve voice testing through a percussion method, thereby eliminating the need to build a test environment, which reduces implementation costs and improves test efficiency. Furthermore, various data can be flexibly configured according to actual needs, which means it has strong configurability and is very flexible and convenient.

[0113] The solutions described in this disclosure can be applied to the field of artificial intelligence, particularly in areas such as intelligent speech, AI chips, and natural language processing. Artificial intelligence is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It encompasses both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies mainly include computer vision, speech recognition, natural language processing, machine learning / deep learning, big data processing, and knowledge graph technologies.

[0114] The audio data in the embodiments described in this disclosure is not audio data specific to a particular user and does not reflect the personal information of a particular user. In addition, the entity executing the voice testing method can obtain the audio data through various public, legal and compliant means, such as obtaining it from the user with the user's authorization.

[0115] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0116] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0117] Figure 8 A schematic block diagram of an electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0118] like Figure 8As shown, device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 802 or a computer program loaded from storage unit 808 into random access memory (RAM) 803. RAM 803 may also store various programs and data required for the operation of device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via bus 804. Input / output (I / O) interface 805 is also connected to bus 804.

[0119] Multiple components in device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of monitors, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0120] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as those described in this disclosure. For example, in some embodiments, the methods described in this disclosure can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed on device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the methods described in this disclosure can be performed. Alternatively, in other embodiments, the computing unit 801 can be configured to perform the methods described in this disclosure by any other suitable means (e.g., by means of firmware).

[0121] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0122] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0123] 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.

[0124] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0125] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0126] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0127] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0128] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A voice testing method, comprising: The main control chip acquires and saves audio data from the voice chip, and the main control chip and the voice chip are located in the same product; The main control chip determines the sampling data based on the stored audio data, including: using the stored first type of audio data and second type of audio data as the sampling data, where the first type of audio data is audio data collected through a microphone and the second type of audio data is re-collected audio data; sending the sampling data to the voice chip; and obtaining the following algorithm processing result returned by the voice chip: the algorithm processing result obtained by performing algorithm processing on the processed first type of audio data after performing predetermined processing on the first type of audio data using the second type of audio data; The main control chip determines the test indicators based on the algorithm processing results.

2. The method according to claim 1, wherein, The acquisition and storage of audio data from the voice chip includes: The configuration information is sent to the voice chip, and the audio data collected by the voice chip according to the configuration information is acquired and saved.

3. The method according to claim 2, wherein, The configuration information includes: the number of microphones configured, the data sources corresponding to different microphones, the number of back-collection signals configured, and the data sources corresponding to different back-collection signals; The acquisition and storage of audio data from the voice chip includes: acquiring and storing the first type of audio data and the second type of audio data from the voice chip.

4. The method according to claim 3, wherein, The configuration information further includes: the type and order of the configured output data; The step of obtaining the following algorithm processing results returned by the voice chip includes: obtaining the algorithm processing results output by the voice chip that conform to the type and order of the output data.

5. A voice testing method, comprising: The voice chip acquires audio data and outputs the acquired audio data to the main control chip. The main control chip and the voice chip are located in the same product. The voice chip acquires sampling data from the main control chip. The sampling data includes: a first type of audio data and a second type of audio data. The first type of audio data is audio data collected through a microphone, and the second type of audio data is re-collected audio data. An algorithm processing result is generated based on the sampling data, and the algorithm processing result is output to the main control chip. The main control chip determines test indicators based on the algorithm processing result. The sampling data is the sampling data determined by the main control chip based on the stored audio data. The algorithm processing result includes: an algorithm processing result obtained by performing algorithm processing on the processed first type of audio data after performing predetermined processing on the first type of audio data using the second type of audio data.

6. The method according to claim 5, wherein, The audio data acquisition includes: The configuration information from the main control chip is obtained, and audio data is collected according to the configuration information.

7. The method according to claim 6, wherein, The configuration information includes: the number of microphones configured, the data sources corresponding to different microphones, the number of back-collection signals configured, and the data sources corresponding to different back-collection signals; The audio data acquisition based on the configuration information includes: acquiring the first type of audio data and the second type of audio data.

8. The method according to claim 7, wherein, The configuration information further includes: the type and order of the configured output data; The step of outputting the algorithm processing result to the main control chip includes: outputting the algorithm processing result that conforms to the type and order of the output data to the main control chip.

9. The method according to any one of claims 5-8, further comprising: The voice chip monitors the computing power of the algorithm in real time, and issues an alarm when it determines that the computing power is overflowing.

10. A voice testing device, comprising: Data acquisition module, first irrigation test module, and second irrigation test module; The data acquisition module is used to acquire and save audio data from the voice chip. The main control chip of the voice testing device and the voice chip are located in the same product. The first perfusion module is used to determine perfusion data based on the stored audio data, including: using the stored first type of audio data and second type of audio data as the perfusion data, wherein the first type of audio data is audio data collected by a microphone and the second type of audio data is audio data collected back, sending the perfusion data to the voice chip, and obtaining the following algorithm processing result returned by the voice chip: the algorithm processing result obtained by performing algorithm processing on the processed first type of audio data after performing predetermined processing on the first type of audio data using the second type of audio data; The second irrigation module is used to determine the test indicators based on the algorithm processing results.

11. The apparatus according to claim 10, wherein, The data acquisition module sends configuration information to the voice chip, and acquires and saves the audio data collected by the voice chip according to the configuration information.

12. The apparatus according to claim 11, wherein, The configuration information includes: the number of microphones configured, the data sources corresponding to different microphones, the number of back-collection signals configured, and the data sources corresponding to different back-collection signals; The data acquisition module acquires and saves the first type of audio data and the second type of audio data from the voice chip.

13. The apparatus according to claim 12, wherein, The configuration information further includes: the type and order of the configured output data; The first perfusion module obtains the algorithm processing results of the voice chip outputting data that conform to the type and order of the output data.

14. A voice testing device, comprising: Data acquisition module and third irrigation measurement module; The data acquisition module is used to acquire audio data and output the acquired audio data to the main control chip. The main control chip and the voice chip of the voice testing device are located in the same product. The third sampling module is used to acquire sampling data from the main control chip. The sampling data includes: a first type of audio data and a second type of audio data. The first type of audio data is audio data collected through a microphone, and the second type of audio data is re-acquired audio data. The module generates an algorithm processing result based on the sampling data and outputs the algorithm processing result to the main control chip. The main control chip determines test indicators based on the algorithm processing result. The sampling data is the sampling data determined by the main control chip based on the stored audio data. The algorithm processing result includes: an algorithm processing result obtained by performing algorithm processing on the processed first type of audio data after performing predetermined processing on the first type of audio data using the second type of audio data.

15. The apparatus according to claim 14, wherein, The data acquisition module obtains configuration information from the main control chip and performs audio data acquisition based on the configuration information.

16. The apparatus according to claim 15, wherein, The configuration information includes: the number of microphones configured, the data sources corresponding to different microphones, the number of back-collection signals configured, and the data sources corresponding to different back-collection signals; The data acquisition module acquires the first type of audio data and the second type of audio data.

17. The apparatus according to claim 16, wherein, The configuration information further includes: the type and order of the configured output data; The third irrigation module outputs the algorithm processing results that conform to the type and order of the output data to the main control chip.

18. The apparatus according to any one of claims 14-17, wherein, The third monitoring module is further used to monitor the computing power of the algorithm in real time, and to issue an alarm when it is determined that the computing power is overflowing.

19. A voice testing system, comprising: The voice testing apparatus as claimed in any one of claims 10-13, and the voice testing apparatus as claimed in any one of claims 14-18.

20. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9.

21. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-9.

22. A computer program product comprising a computer program / instructions that, when executed by a processor, implement the method of any one of claims 1-9.

Images