Data acquisition method and device based on voice recognition, vehicle, medium and product

Abstract

The invention relates to the technical field of vehicles, in particular to a data acquisition method and device based on voice recognition, a vehicle, a medium and a product, and the method comprises the steps: recognizing a voice instruction of a user; determining a target data acquisition task based on the voice instruction; and the target acquisition task is sent to a target task module of the vehicle, and the target task module executes the target data acquisition task to complete data acquisition. Therefore, the problems that existing related manual data acquisition is tedious, the working efficiency is low, and the data acquisition quality and accuracy are low are solved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a data acquisition method, device, vehicle, medium and product based on speech recognition. Background Art

[0002] The collection of data from actual autonomous driving vehicles is one of the important links in promoting the development of autonomous driving technology. By collecting and analyzing various sensor data during the driving process of the actual vehicle, the autonomous driving system algorithm can be continuously improved and optimized to make it more intelligent, safe and reliable.

[0003] Currently, in the work of collecting data from autonomous driving vehicles, real-vehicle test engineers are responsible for driving vehicles equipped with various sensors along predetermined routes and speeds. At the same time, they need to record sensor data packets, test whether the various business functions of the system are normal, and record the test results and problems that arise during vehicle driving in detail.

[0004] When driving a vehicle, real-vehicle test engineers must not only pay attention to real-time traffic conditions, but also configure various sensor acquisition parameters and test business functions. When problems are discovered, they need to manually perform data marking and slicing, configure parameter switching, and record the problem content. This poses certain security risks, and manual operations are cumbersome and inconvenient. Data marking and slicing will also have certain delays and inaccuracies. Summary of the Invention

[0005] The present application provides a data collection method, device, vehicle, medium and product based on voice recognition to solve the problems of existing manual data collection being cumbersome, inefficient, and having low data collection quality and accuracy.

[0006] The first aspect of the present application provides a data collection method based on voice recognition, comprising the following steps: recognizing the user's voice instructions; determining the target data collection task based on the voice instructions; sending the target collection task to the target task module of the vehicle, wherein the target task module executes the target data collection task to complete the data collection.

[0007] Optionally, in one embodiment of the present application, recognizing a user's voice command includes: collecting the user's voice signal; and parsing the voice signal using a target voice model to obtain a voice command, wherein the target voice model is obtained based on deep learning training.

[0008] Optionally, in one embodiment of the present application, before using the target speech model to parse the speech signal to obtain the voice command, it also includes: preprocessing the speech signal, wherein the preprocessing includes at least one of format conversion, noise reduction, and audio segmentation; and performing feature extraction on the preprocessed speech signal to obtain a feature-extracted speech signal.

[0009] Optionally, in one embodiment of the present application, determining the target data collection task based on the voice instruction includes: obtaining a correspondence between the voice instruction and the data collection task; and determining the target data collection task based on the correspondence and the voice instruction.

[0010] Optionally, in one embodiment of the present application, before sending the target data acquisition task to the target task module of the vehicle, it includes: parsing the target data acquisition task to determine the identification parameters or task path of the target data acquisition task; and determining the target task module based on the identification parameters or task path.

[0011] Optionally, in one embodiment of the present application, the task module supports asynchronous execution.

[0012] The second aspect of the present application provides a data acquisition device based on voice recognition, including: a recognition module for recognizing the user's voice instructions; a determination module for determining the target data acquisition task based on the voice instructions; a sending module for sending the target acquisition task to the target task module of the vehicle, wherein the target task module executes the target data acquisition task to complete data acquisition.

[0013] Optionally, in one embodiment of the present application, the recognition module is further used to: collect the user's voice signal; and use the target voice model to parse the voice signal to obtain voice instructions, wherein the target voice model is obtained based on deep learning training.

[0014] Optionally, in one embodiment of the present application, it also includes: a processing module for preprocessing the voice signal before using the target voice model to parse the voice signal to obtain voice instructions, wherein the preprocessing includes at least one of format conversion, noise reduction, and audio segmentation; and performing feature extraction on the preprocessed voice signal to obtain a feature-extracted voice signal.

[0015] Optionally, in one embodiment of the present application, the determination module is further used to: obtain a correspondence between voice instructions and data collection tasks; and determine a target data collection task based on the correspondence and the voice instructions.

[0016] Optionally, in one embodiment of the present application, it also includes: a parsing module, which is used to parse the target data acquisition task to determine the identification parameters or task path of the target data acquisition task before sending the target acquisition task to the target task module of the vehicle; and determine the target task module based on the identification parameters or task path.

[0017] The third aspect of the present application provides a vehicle, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to perform the data collection method based on speech recognition as described in the above embodiment.

[0018] The fourth aspect of the present application provides a computer-readable storage medium on which a computer program or instruction is stored. The computer program or instruction is executed by a processor to perform the data acquisition method based on speech recognition as described in the above embodiment.

[0019] The fifth embodiment of the present application provides a computer program product, including a computer program or instructions. When the computer program or instructions are executed, the data collection method based on speech recognition as described in the above embodiment is implemented.

[0020] Therefore, this application has at least the following beneficial effects:

[0021] In an embodiment of the present application, a target data collection task can be determined based on a user's voice command, and the target collection task is sent to the vehicle's target task module. The target task module then executes the target data collection task to complete data collection. In other words, the user controls the vehicle to perform the corresponding data collection task based on voice, eliminating the need for manual operation. This reduces the user's operational burden and improves work efficiency. Furthermore, since manual data collection by the user may result in delays or errors, this improves the quality and accuracy of data collection to a certain extent. This solves the technical problems of existing manual data collection, such as being cumbersome, inefficient, and having low data collection quality and accuracy.

[0022] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0024] Figure 1 A flowchart of a data acquisition method based on speech recognition according to an embodiment of the present application;

[0025] Figure 2 This is a flowchart of the execution between modules of the data acquisition method based on speech recognition provided in an embodiment of the present application;

[0026] Figure 3 A flowchart of speech recognition and voice command processing according to an embodiment of the present application;

[0027] Figure 4 This is an example diagram of a data acquisition device based on speech recognition according to an embodiment of the present application;

[0028] Figure 5 A schematic structural diagram of a vehicle provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0029] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0030] The following describes a data collection method, device, vehicle, medium, and product based on voice recognition in the embodiments of the present application with reference to the accompanying drawings. In view of the fact that the actual vehicle test engineer mentioned in the above background technology, when driving a vehicle, must pay attention to real-time traffic conditions, configure various sensor acquisition parameters, test business functions, and manually perform data marking and slicing, configure parameter switching, and record the problem content in a timely manner when problems are found, there are certain safety risks, and manual operation is relatively cumbersome and inconvenient. Data marking and slicing will also have certain delays and inaccuracies. The present application provides a data collection method based on voice recognition, in which a target data collection task can be determined according to the user's voice command, and the target collection task is sent to the target task module of the vehicle. The target task module executes the target data collection task to complete the data collection. That is, the user controls the vehicle to perform the corresponding data collection task based on voice, without the need for manual operation by the user, reducing the user's operating burden and improving work efficiency. In addition, since the user manually collects data, there may be delays or errors, which improves the quality and accuracy of data collection to a certain extent. Thus, the existing manual data collection is solved, which is relatively cumbersome, has low work efficiency, and has the problems of low data collection quality and accuracy.

[0031] Specifically, Figure 1 A flow chart of a data acquisition method based on speech recognition provided in an embodiment of the present application.

[0032] like Figure 1 As shown, the data collection method based on speech recognition includes the following steps:

[0033] In step S101 , a user's voice command is recognized.

[0034] It is understandable that the embodiment of the present application can recognize the user's voice commands so that the task module of the vehicle can subsequently control the vehicle based on the voice commands to perform the data collection task.

[0035] It should be noted that the data collection method of the embodiment of the present application is mainly applicable to data collection during actual vehicle testing, but can also be extended to other application scenarios. The embodiment of the present application takes actual vehicle data collection as an example.

[0036] In an embodiment of the present application, recognizing a user's voice command includes: collecting the user's voice signal; and using a target voice model to analyze the voice signal to obtain a voice command, wherein the target voice model is obtained based on deep learning training.

[0037] Among them, the target speech model can be obtained based on deep learning training, such as using multiple speech samples to train the speech model.

[0038] It is understandable that the embodiments of the present application can collect the user's voice signal and use the target voice model to analyze the voice signal to obtain voice instructions.

[0039] For example, when a user says "collect vehicle speed data" in a noisy environment, the target speech recognition model recognizes the voice command "collect vehicle speed data".

[0040] In an embodiment of the present application, before using the target speech model to parse the speech signal to obtain the speech command, it also includes: preprocessing the speech signal, wherein the preprocessing includes at least one of format conversion, noise reduction, and audio segmentation; and performing feature extraction on the preprocessed speech signal to obtain a feature-extracted speech signal.

[0041] It can be understood that the embodiments of the present application can preprocess the voice signal, perform format conversion, noise reduction, audio segmentation, etc. to improve the instructions of the voice signal, and extract key features of the preprocessed voice signal to reduce the amount of data to increase the speed of subsequent recognition of voice instructions.

[0042] In step S102 , a target data collection task is determined based on the voice instruction.

[0043] Among them, the target data collection task is the data collection task issued by the user.

[0044] It is understandable that the embodiment of the present application can determine the target data collection task based on the voice instruction, so as to achieve the determination of the target data task according to the user's voice instruction.

[0045] In an embodiment of the present application, determining a target data collection task based on a voice instruction includes: obtaining a correspondence between the voice instruction and the data collection task; and determining the target data collection task based on the correspondence and the voice instruction.

[0046] It is understandable that the embodiment of the present application can obtain the correspondence between voice instructions and data collection tasks, and accurately match the current user's voice instructions to specific data collection tasks through the predefined correspondence.

[0047] In step S103, the target data collection task is sent to the target task module of the vehicle, wherein the target task module executes the target data collection task to complete data collection.

[0048] Among them, the target task module is equipped with the execution logic of the data collection task, which can automatically realize data collection.

[0049] It can be understood that the embodiment of the present application can send the target collection task to the target task module of the vehicle, and the target task module executes the target data collection task to complete the data collection, thereby realizing the control of the vehicle to perform the data collection task based on voice recognition, without the need for manual operation by the user, reducing the user's operating burden, and improving work efficiency. In addition, since there may be delays or errors when the user manually collects data, the quality and accuracy of data collection are improved to a certain extent.

[0050] In an embodiment of the present application, before sending the target data acquisition task to the target task module of the vehicle, it includes: parsing the target data acquisition task to determine the identification parameters or task path of the target data acquisition task; and determining the target task module based on the identification parameters or task path.

[0051] It is understandable that the embodiment of the present application can parse the target data collection task to obtain the corresponding representation parameters or task path, and then determine the target task module according to the identification parameters or task path.

[0052] In an embodiment of the present application, the task module supports asynchronous execution.

[0053] It is understandable that the task module of the embodiment of the present application supports asynchronous execution to improve the performance and concurrency of the program.

[0054] Among them, the task module is implemented using thread pool and blocking queue.

[0055] The following describes the data collection method based on speech recognition of the present application through a specific embodiment. Taking the real vehicle data collection as an example, the method is arranged on the system and implemented using the vehicle computer. It mainly includes a Web display module, an API interface module, a speech recognition and speech instruction set module, and a task execution module. The execution process between the modules is as follows: Figure 2 As shown, by using the web browser installed in the vehicle computer to access the voice recognition assistance system, users can control the system through different voice commands to automatically perform corresponding data collection tasks, which can reduce the operational burden of actual vehicle test engineers and improve work efficiency and data collection quality.

[0056] Step 1: Use an onboard computer with a microphone to access the voice recognition assistance system through a web browser to authorize the system to obtain the user's voice data.

[0057] Step 2: Start the voice recognition service. The system obtains the user's real-time voice stream as input and sends it to the API interface module.

[0058] Step 3: After receiving the request data, the API interface module pre-processes the voice data to form an audio file in the specified format, and then sends it to the voice recognition and voice instruction set module for processing.

[0059] Step 4: After receiving the audio file, the speech recognition and voice command set module converts the audio into text through the trained and tuned speech recognition model, and then performs function matching in the voice command set. After the matching is completed, the result will be returned to the API interface module.

[0060] Step 5: After receiving the result data, the API interface module performs internal data parsing to parse out the task identification parameter or path. Based on the task identification, the API interface determines which data collection task to execute and then sends the task request to the task execution module.

[0061] Step 6: After receiving the request, the task execution module automatically executes the corresponding data collection task logic, saves the task execution status and result records, and returns them to the Web display module through the API interface module.

[0062] The specific functions of the four modules are as follows:

[0063] 1. Web display module

[0064] The web display module is the user's interactive interface. Its main functions include: turning on and off the voice recognition function, a real-time scrolling window for voice-to-text conversion, a list of questions recorded through voice recognition and the generation of corresponding audio files, and the export of data points and data slices into Excel spreadsheets.

[0065] The web display module uses WebRTC (Web Real-Time Communication) technology to obtain the user's voice in the browser, requests the user to authorize the microphone, obtains the user's voice stream, and then submits the voice stream data to the API interface module in the form of an HTTP request for analysis and processing.

[0066] 2. API interface module

[0067] The API interface module mainly receives various data requests submitted by the Web display module. After internal logic processing, it returns the corresponding JSON format information to the Web display module. After the Web display module receives the JSON data, it displays the different states of the data in the user interaction interface.

[0068] After receiving the voice data, the API interface module will perform necessary pre-processing operations on the voice data, such as audio format conversion, noise reduction, audio segmentation, etc. After the pre-processing operation is completed, the data feature extraction is performed. After the feature extraction, the data is organized into a data packet in a specified format and sent to the speech recognition and voice instruction set module. After the speech recognition and voice instruction set module completes the processing, it will return the result data in the specified format. If the result requires data dot and data slicing tasks, the backend will submit the task to the task execution module, where the processing flow of speech recognition and voice instructions is as follows: Figure 3 shown.

[0069] 3. Speech Recognition and Voice Command Set Module

[0070] The speech recognition and voice command set module is a technology based on voice interaction that can understand and respond to user voice commands. It uses a trained and tuned voice model for speech recognition to improve accuracy and robustness, converting voice data into text data that can be understood and processed by computers. At the same time, it recognizes the corresponding voice commands and data acquisition task identifiers, organizes the result information in a specified format, and returns it to the API interface module.

[0071] Through the voice recognition and voice command set modules, users can operate devices or interact with applications by speaking commands, achieving a more convenient and intelligent user experience.

[0072] 4. Task execution module (i.e. task module)

[0073] After receiving the task identifier from the API module, the task execution module locates and executes the script corresponding to the data collection task, such as data dotting, configuration parameter switching, and data slicing. The type and number of tasks can be expanded based on demand. During task execution, the execution status and results of the task are monitored and saved, and the task status is returned to the web display module through the API module for user viewing.

[0074] The task execution module is implemented using thread pools and blocking queues. Its main purpose is to improve the performance and concurrency of the program by executing tasks asynchronously.

[0075] According to the data collection method based on voice recognition proposed in the embodiment of the present application, the target data collection task can be determined according to the user's voice command, and the target collection task can be sent to the target task module of the vehicle. The target task module executes the target data collection task to complete the data collection. That is, the user controls the vehicle to perform the corresponding data collection task based on voice, and no manual operation is required by the user, which reduces the user's operating burden and improves work efficiency. In addition, since there may be delays or errors when the user manually collects data, the quality and accuracy of data collection are improved to a certain extent.

[0076] Next, a data acquisition device based on speech recognition proposed in accordance with an embodiment of the present application will be described with reference to the accompanying drawings.

[0077] Figure 4 It is a block diagram of a data acquisition device based on speech recognition according to an embodiment of the present application.

[0078] like Figure 4 As shown, the data acquisition device 10 based on speech recognition includes: a recognition module 100 , a determination module 200 and a sending module 300 .

[0079] Among them, the recognition module 100 is used to recognize the user's voice instructions; the determination module 200 is used to determine the target data collection task based on the voice instructions; the sending module 300 is used to send the target collection task to the vehicle's target task module, wherein the target task module executes the target data collection task to complete data collection.

[0080] In an embodiment of the present application, the recognition module 100 is further used to: collect the user's voice signal; and use the target voice model to analyze the voice signal to obtain voice instructions, wherein the target voice model is obtained based on deep learning training.

[0081] In the embodiment of the present application, the device 10 of the embodiment of the present application further includes: a processing module.

[0082] Among them, the processing module is used to preprocess the voice signal before using the target voice model to parse the voice signal to obtain the voice command, wherein the preprocessing includes at least one of format conversion, noise reduction, and audio segmentation; and perform feature extraction on the preprocessed voice signal to obtain a feature-extracted voice signal.

[0083] In the embodiment of the present application, the determination module 200 is further used to: obtain the correspondence between the voice instruction and the data collection task; and determine the target data collection task based on the correspondence and the voice instruction.

[0084] In the embodiment of the present application, the device 10 of the embodiment of the present application further includes: a parsing module.

[0085] Among them, the parsing module is used to parse the target data acquisition task to determine the identification parameters or task path of the target data acquisition task before sending the target acquisition task to the target task module of the vehicle; and determine the target task module based on the identification parameters or task path.

[0086] It should be noted that the above explanation of the embodiment of the data acquisition method based on speech recognition is also applicable to the data acquisition device based on speech recognition in this embodiment, and will not be repeated here.

[0087] According to the voice recognition-based data acquisition device proposed in the embodiment of the present application, the target data acquisition task can be determined according to the user's voice command, and the target acquisition task can be sent to the target task module of the vehicle. The target task module executes the target data acquisition task to complete the data acquisition. That is, the user controls the vehicle to perform the corresponding data acquisition task based on voice, and no manual operation is required by the user, which reduces the user's operating burden and improves work efficiency. In addition, since there may be delays or errors when the user manually collects data, the quality and accuracy of data acquisition are improved to a certain extent.

[0088] Figure 5 This is a schematic diagram of the structure of a vehicle provided in an embodiment of the present application. The electronic device may include:

[0089] Memory 501 , processor 502 , and computer programs stored in the memory 501 and executable on the processor 502 .

[0090] When the processor 502 executes the program, the data collection method based on speech recognition provided in the above embodiment is implemented.

[0091] Furthermore, the vehicle further comprises:

[0092] The communication interface 503 is used for communication between the memory 501 and the processor 502 .

[0093] The memory 501 is used to store computer programs that can be run on the processor 502 .

[0094] The memory 501 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0095] If the memory 501, processor 502, and communication interface 503 are implemented independently, the communication interface 503, memory 501, and processor 502 can be interconnected via a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0096] Optionally, in a specific implementation, if the memory 501, the processor 502 and the communication interface 503 are integrated on a chip, the memory 501, the processor 502 and the communication interface 503 can communicate with each other through an internal interface.

[0097] The processor 502 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0098] An embodiment of the present application further provides a computer-readable storage medium having a computer program or instruction stored thereon. When the computer program or instruction is executed by a processor, the above-mentioned data collection method based on speech recognition is implemented.

[0099] An embodiment of the present application also provides a computer program product, including a computer program or instructions, which, when executed, implements the above-mentioned data collection method based on speech recognition.

[0100] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0101] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of this application, "N" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0102] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing a custom logical function or process step, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed in a different order than shown or discussed, including performing functions in a substantially simultaneous manner or in a reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application pertain.

[0103] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiment, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, it can be implemented using any one or a combination of the following technologies known in the art: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0104] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

Claims

1. A data collection method based on speech recognition, characterized in that: The following steps are involved: Recognize user's voice commands; Determine a target data collection task based on the voice command; The target acquisition task is sent to a target task module of the vehicle, wherein the target task module executes the target data acquisition task to complete data acquisition.

2. The data collection method based on speech recognition according to claim 1, characterized in that: The identifying the user's voice command comprises: Collecting user's voice signal; The voice signal is parsed using a target voice model to obtain a voice command, wherein the target voice model is obtained based on deep learning training.

3. The data collection method based on speech recognition according to claim 1 or 2, characterized in that: Before using the target speech model to analyze the speech signal to obtain the speech instruction, the method further includes: Preprocessing the speech signal, wherein the preprocessing includes at least one of format conversion, noise reduction, and audio segmentation; Perform feature extraction on the preprocessed speech signal to obtain a feature-extracted speech signal.

4. The data collection method based on speech recognition according to claim 1, characterized in that: The determining of the target data collection task based on the voice instruction comprises: Obtain the correspondence between voice commands and data collection tasks; The target data collection task is determined based on the corresponding relationship and the voice instruction.

5. The data collection method based on speech recognition according to claim 1, characterized in that: Before sending the target acquisition task to the target task module of the vehicle, it includes: Parsing the target data collection task to determine identification parameters or task path of the target data collection task; A target task module is determined based on the identification parameter or the task path.

6. The data collection method based on speech recognition according to claim 1, characterized in that: The task module supports asynchronous execution.

7. A data collection device based on speech recognition, characterized in that: include: A recognition module, used to recognize the user's voice command; A determination module, used to determine a target data collection task based on the voice instruction; A sending module is used to send the target acquisition task to a target task module of the vehicle, wherein the target task module executes the target data acquisition task to complete data acquisition.

8. A vehicle, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the data collection method based on speech recognition as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: The computer program or instruction is executed by a processor to implement the data collection method based on speech recognition as described in any one of claims 1 to 6.

10. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed, the data collection method based on speech recognition as described in any one of claims 1 to 6 is implemented.

Images