Continuous voice recognition method, device and intelligent switch panel

Abstract

The present application relates to the field of smart home technology and discloses a method for continuous speech recognition. The method includes: the processor's REE applies for a cache, all REE processes are frozen, and the REE enters sleep mode; the processor's TEE responds to an SMC interrupt and executes a VAD detection routine; wherein the REE and TEE are divided by TrustZone; the TEE reads the voice data of the sound collection device; when the voice data is non-environmental noise, the TEE caches the voice data to the cache applied for by the REE; the TEE calls the SMC interrupt to wake up the Kernel; the Kernel executes the Resume operation; the REE calls the application to read the voice data in the applied cache and parses it to obtain the parsing result. The use of this method for continuous speech recognition can reduce system energy consumption. The present application also discloses a continuous speech recognition device and a smart switch panel.

Description

Technical Field

[0001] The present application relates to the field of smart home technology, for example, to a method and device for continuous voice recognition and a smart switch panel. Background Art

[0002] With the rapid development of the smart home industry, a large number of smart network device nodes have been deployed in homes (common ones include light strips, sensors, door locks, etc.). Smart switch panels refer to unit devices that use a combination and programming of control boards and electronic components to achieve circuit smart switch control of each smart terminal node. They are the entrance to the control of local node devices in the home.

[0003] The smart switch panel has a screen, and the voice interaction function is a high-frequency application scenario. As a quick interactive entrance to the smart home scene, it is necessary to detect the voice signal in the environment through sound detection equipment, which will cause the main processor to be unable to enter the low-power (sleep) state.

[0004] To resolve the conflict between system power consumption and VAD detection, the following two methods are commonly used: 1. Attach a dedicated Voice Activation Detection (VAD) chip specifically for voice detection. This chip is a dedicated microcontroller unit (MCU) chip with its own central processing unit (CPU), random access memory (RAM), flash memory (FLASH), and audio subsystem. 2. Use software to extract ambient voice information for judgment. The audio module on the smart switch panel system is used to pick up the signal, and the CPU / RAM resources on the main control are used for local calculations.

[0005] During the implementation of the embodiments of the present application, it was found that at least the following problems exist in the related art:

[0006] Due to the size limitations of the 86 panel (smart switch panel model) and the fact that voice recognition requires real-time and continuous detection of voice signals, the system cannot go into sleep mode, resulting in excessive power consumption and high temperatures in panels of products currently on the market that use soft solution algorithms, leading to a poor user experience. Summary of the Invention

[0007] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical elements or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0008] The embodiments of the present application provide a method, device, and intelligent switch panel for continuous speech recognition to reduce energy consumption during the continuous speech recognition process, thereby improving the user experience.

[0009] In some embodiments, the method for continuous speech recognition includes:

[0010] The processor's Rich Execution Environment (REE) applies for a cache, freezes all processes of the REE, and puts the REE into hibernation; the processor's Trusted Execution Environment (TEE) responds to an SMC interrupt and executes a VAD detection routine; wherein the REE and the TEE are divided by TrustZone; the TEE reads the voice data of the sound collection device; when the voice data is non-environmental noise, the TEE caches the voice data in the cache applied for by the REE; the TEE calls an SMC interrupt to wake up the kernel; the kernel executes a resume operation; the REE calls an application to read the voice data in the applied cache and parses it to obtain a parsing result.

[0011] Optionally, before the REE enters sleep mode, the method for continuous speech recognition further includes: reducing the operating frequency of the processor and reducing the operating frequency of the memory.

[0012] Optionally, after waking up the Kernel, the continuous speech recognition method further includes: increasing the operating frequency of the processing and increasing the operating frequency of the memory.

[0013] In some embodiments, the method for continuous speech recognition includes: the REE of the processor freezes all processes; in response to the SMC interrupt, the TEE of the processor executes a VAD detection routine; wherein, the REE and the TEE are divided by TrustZone; the TEE reads the sound data detected by the sound collection device; when the sound data is non-environmental noise, the TEE parses the sound data and obtains the parsing result; the TEE calls the SMC interrupt to wake up the Kernel; the Kernel executes the Resume operation; the REE calls the application to read the parsing result of the sound data.

[0014] Optionally, while the TEE executes the VAD detection routine, the method for continuous speech recognition also includes: real-time monitoring of wake-up source interrupts; when a wake-up source interrupt is detected, the TEE executes an SMC interrupt to wake up the Kernel; the Kernel executes a Resume operation; and the REE calls a related application to execute the source interrupt.

[0015] Optionally, before the TEE reads the sound data detected by the sound collection device, the method for continuous speech recognition further includes: the TEE configuring relevant parameters of the speech detection device; or the REE configuring relevant parameters of the speech detection device.

[0016] Optionally, the voice detection device is configured with a hardware switch; the TEE configures relevant parameters of the voice detection device, including: connecting the hardware switch; the REE configures relevant parameters of the voice detection device, including: connecting the hardware switch.

[0017] Optionally, after the REE executes the VAD detection routine, the method for continuous speech recognition further includes: adjusting GATEI / Dcache to improve the detection performance of the VAD detection routine.

[0018] Optionally, before the REE freezes all processes, the method for continuous speech recognition further includes: the Kernel executing a suspend process.

[0019] In some embodiments, the continuous speech recognition apparatus includes a processor and a memory storing program instructions, and the processor is configured to execute the continuous speech recognition method provided in the aforementioned embodiments when executing the program instructions.

[0020] In some embodiments, the intelligent switch panel includes the continuous voice recognition device provided in the aforementioned embodiments.

[0021] The continuous speech recognition method, device, and intelligent switch panel provided in the embodiments of the present application can achieve the following technical effects:

[0022] In the two parts of the processor divided by TrustZone, REE has higher energy consumption and TEE has lower energy consumption. This application uses TEE to execute VAD detection routine to realize the function of continuous voice detection. In the process of TEE executing VAD detection routine, REE is dormant, which reduces system energy consumption and improves user experience.

[0023] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] One or more embodiments are exemplarily described by corresponding drawings. These exemplary descriptions and drawings do not limit the embodiments. Elements with the same reference numerals in the drawings are considered similar elements, and wherein:

[0025] Figure 1This is a flow chart of a method for continuous speech recognition provided by an embodiment of the present application;

[0026] Figure 2 This is a flow chart of a method for continuous speech recognition provided by an embodiment of the present application;

[0027] Figure 3 This is a flow chart of a method for continuous speech recognition provided by an embodiment of the present application;

[0028] Figure 4 This is a flow chart of a method for continuous speech recognition provided by an embodiment of the present application;

[0029] Figure 5 Schematic diagram of a continuous speech recognition device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to be able to understand the features and technical contents of the embodiments of the present application in more detail, the implementation of the embodiments of the present application is described in detail below with reference to the accompanying drawings. The accompanying drawings are for reference only and are not used to limit the embodiments of the present application. In the following technical description, for the sake of convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0031] In the description and claims of the embodiments of the present application and the accompanying drawings, the terms "first," "second," and the like are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate for the purposes of describing the embodiments of the present application. In addition, the terms "including," "having," and any variations thereof are intended to cover non-exclusive inclusions.

[0032] Unless otherwise stated, the term "plurality" means more than two.

[0033] In the embodiments of the present application, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B means: A or B.

[0034] The term "and / or" describes an association between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or A and B.

[0035] Figure 1 This is a flow chart of a method for continuous speech recognition provided in an embodiment of the present application.

[0036] Combine Figure 1 As shown, the continuous speech recognition method includes:

[0037] S101: The processor's REE applies for cache, all REE processes are frozen, and the REE enters sleep mode.

[0038] REE freezes all threads, which helps reduce processor energy consumption.

[0039] Optionally, before the REE freezes all processes, the continuous speech recognition method further includes the following steps: the kernel executes a suspend process, and the suspend process is executed to put the REE into hibernation.

[0040] Optionally, before the REE enters sleep mode, the method for continuous speech recognition further includes: reducing the operating frequency of the processor and reducing the operating frequency of the memory, thereby reducing processor energy consumption.

[0041] Optionally, before the REE enters sleep mode, the method for continuous voice recognition further includes: powering off the peripheral Vcc, thereby reducing processor energy consumption.

[0042] Then PSCI / SMC falls into TEE.

[0043] S102 : The TEE of the processor executes a VAD detection routine in response to the SMC interrupt.

[0044] Among them, REE and TEE are divided by TrustZone.

[0045] Optionally, after REE executes the VAD detection routine, the method for continuous voice detection also includes the following steps: adjusting GATEI / Dcache to improve the detection performance of the VAD detection routine, such as response time, so that the performance of the VAD detection routine reaches the level of external VAD detection, for example, the response time of the VAD detection routine of TEE is less than or equal to the response time of the external VAD detection routine, thereby maintaining or even improving the user experience.

[0046] S103. TEE reads the voice data from the sound collection device.

[0047] Optionally, before the TEE reads the sound data detected by the sound collection device, the continuous speech recognition method further includes: the TEE configuring relevant parameters of the speech detection device; or the REE configuring relevant parameters of the speech detection device.

[0048] Furthermore, the voice detection device is equipped with a hardware switch; the TEE configures the relevant parameters of the voice detection device, including: connecting the hardware switch; and the REE configures the relevant parameters of the voice detection device, including: connecting the hardware switch. This can improve the security of the system at the hardware level.

[0049] S104: When the voice data is not ambient noise, the TEE caches the voice data in the cache requested by the REE.

[0050] In this step, other existing technologies can be used to determine whether the voice data is environmental noise, which will not be described in detail in the embodiment of the present application.

[0051] S105. TEE calls the SMC interrupt to wake up the Kernel.

[0052] At this point REE exits the dormant state.

[0053] After waking up the kernel, the continuous speech recognition method further includes the following steps: increasing the processing frequency and the memory frequency, so that the REE can read and parse the speech data at a faster speed to obtain the parsing result.

[0054] S106. Kernel executes the Resume operation.

[0055] S107 , REE calls the application to read the voice data in the requested buffer, and parses the voice data to obtain a parsing result.

[0056] In the two parts of the processor divided by TrustZone, the energy consumption of REE is higher and the energy consumption of TEE is lower. This application uses TEE to execute the VAD detection routine to realize the function of continuous voice detection. In the process of TEE executing the VAD detection routine, the REE is dormant, which reduces the system energy consumption.

[0057] Figure 2 This is a flow chart of a method for continuous speech recognition provided in an embodiment of the present application.

[0058] Combine Figure 2 As shown, the continuous speech recognition method includes:

[0059] S201: Kernel executes the suspend process.

[0060] S202: REE configures relevant parameters of the voice detection device.

[0061] S203, REE applies for cache.

[0062] S204, REE all processes are frozen, peripheral Vcc is powered off, and the operating frequency of the processor and memory is reduced.

[0063] S205, REE is dormant.

[0064] S206 . In response to the SMC interrupt, the TEE executes a VAD detection routine.

[0065] S207. Adjust GATEI / Dcache to improve the detection performance of the VAD detection routine.

[0066] S208. TEE reads the voice data from the sound collection device.

[0067] S209: Determine whether the voice data is environmental noise; if so, execute S208; otherwise, execute S210.

[0068] S210. TEE caches the voice data in the cache requested by REE.

[0069] S211. TEE calls the SMC interrupt to wake up the Kernel.

[0070] S212. Kernel executes the Resume operation.

[0071] S213: REE calls the application to read the voice data from the requested buffer and parses the data to obtain a parsing result.

[0072] Figure 3 This is a flow chart of a method for continuous speech recognition provided in an embodiment of the present application.

[0073] Combine Figure 3 As shown, the continuous speech recognition method includes:

[0074] S301. The processor's REE freezes all processes.

[0075] Optionally, before the REE freezes all processes, the continuous speech recognition method further includes the following steps: the kernel executes a suspend process, and the suspend process is executed to put the REE into hibernation.

[0076] Optionally, before the REE enters sleep mode, the method for continuous voice recognition further includes: powering off the peripheral Vcc, thereby reducing processor energy consumption.

[0077] Then PSCI / SMC falls into TEE.

[0078] S302 : In response to the SMC interrupt, the TEE of the processor executes a VAD detection routine.

[0079] Among them, REE and TEE are divided by TrustZone.

[0080] Optionally, after REE executes the VAD detection routine, the method for continuous voice detection also includes the following steps: adjusting GATEI / Dcache to improve the detection performance of the VAD detection routine, such as response time, so that the performance of the VAD detection routine reaches the level of external VAD detection, for example, the response time of the VAD detection routine of TEE is less than or equal to the response time of the external VAD detection routine, thereby maintaining or even improving the user experience.

[0081] S303. TEE reads the sound data detected by the sound collection device.

[0082] Optionally, before the TEE reads the sound data detected by the sound collection device, the continuous speech recognition method further includes: the TEE configuring relevant parameters of the speech detection device; or the REE configuring relevant parameters of the speech detection device.

[0083] Furthermore, the voice detection device is equipped with a hardware switch; the TEE configures the relevant parameters of the voice detection device, including: connecting the hardware switch; and the REE configures the relevant parameters of the voice detection device, including: connecting the hardware switch. This can improve the security of the system at the hardware level.

[0084] S304: When the sound data is not environmental noise, the TEE analyzes the sound data and obtains an analysis result.

[0085] In this step, other existing technologies can be used to determine whether the voice data is environmental noise, which will not be described in detail in the embodiment of the present application.

[0086] After TEE obtains the parsing result, it caches the parsing result.

[0087] S305. TEE calls the SMC interrupt to wake up the Kernel.

[0088] At this point REE exits the dormant state.

[0089] S306. Kernel executes the Resume operation.

[0090] S307 , REE calls the application to read the analysis result of the sound data.

[0091] In the two parts of the processor divided by TrustZone, the energy consumption of REE is higher and the energy consumption of TEE is lower. This application uses TEE to execute the VAD detection routine to realize the function of continuous voice detection. In the process of TEE executing the VAD detection routine, the REE is dormant, which reduces the system energy consumption.

[0092] In addition, while the TEE executes the VAD detection routine, the continuous speech recognition method also includes: real-time monitoring of wakeup source interrupts; if a wakeup source interrupt is detected, the TEE executes an SMC interrupt to wake up the kernel; the kernel executes the Resume operation; and the REE calls the relevant application to execute the source interrupt. This allows the REE to respond to and handle other work at any time.

[0093] Figure 4 This is a flow chart of a method for continuous speech recognition provided in an embodiment of the present application.

[0094] Combine Figure 4 As shown, the continuous speech recognition method includes:

[0095] S401: Kernel executes the suspend process.

[0096] S402: REE configures relevant parameters of the voice detection device.

[0097] S403, all REE processes are frozen and the peripheral Vcc is powered off.

[0098] S404, REE is dormant.

[0099] S405 . In response to the SMC interrupt, the TEE executes a VAD detection routine.

[0100] S406 , adjust GATEI / Dcache to improve the detection performance of the VAD detection routine.

[0101] S407. TEE reads the voice data from the sound collection device.

[0102] S408: Determine whether the voice data is environmental noise; if so, execute S407; otherwise, execute S409.

[0103] S409. TEE analyzes the sound data and obtains the analysis results.

[0104] S410. TEE calls the SMC interrupt to wake up the Kernel.

[0105] S411. Kernel executes the Resume operation.

[0106] S412: REE calls an application to read the analysis result of the sound data, or calls a related application to process the wake-up source interrupt.

[0107] S413: Determine whether a wake-up source interrupt occurs; if so, execute S410; otherwise, continue to execute S405.

[0108] In some embodiments, the continuous speech recognition apparatus includes a processor and a memory storing program instructions, and the processor is configured to execute the continuous speech recognition method provided in the aforementioned embodiments when executing the program instructions.

[0109] Figure 5 Schematic diagram of a continuous speech recognition device provided by an embodiment of the present application. Figure 5 As shown, the speech continuous recognition device includes:

[0110] The processor 51 and memory 52 may also include a communication interface 53 and a bus 54. The processor 51, communication interface 53, and memory 52 may communicate with each other via the bus 54. The communication interface 53 may be used for information transmission. The processor 51 may invoke the logic instructions in the memory 52 to execute the continuous speech recognition method provided in the aforementioned embodiment.

[0111] In addition, the logic instructions in the memory 52 can be implemented in the form of software functional units and stored in a computer-readable storage medium when sold or used as an independent product.

[0112] The memory 52 is a computer-readable storage medium that can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of the present application. The processor 51 executes the software programs, instructions, and modules stored in the memory 52 to perform functional applications and data processing, thereby implementing the methods in the above-mentioned method embodiments.

[0113] The memory 52 may include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function; the data storage area may store data generated based on the use of the terminal device. Furthermore, the memory 52 may include high-speed random access memory and non-volatile memory.

[0114] An embodiment of the present application provides an intelligent switch panel, comprising the continuous voice recognition device provided in the aforementioned embodiment.

[0115] An embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to execute the continuous speech recognition method provided in the aforementioned embodiment.

[0116] An embodiment of the present application provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the continuous speech recognition method provided by the aforementioned embodiment.

[0117] The aforementioned computer-readable storage medium may be a transient computer-readable storage medium or a non-transitory computer-readable storage medium.

[0118] The technical solutions of the embodiments of the present application can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method of the embodiments of the present application. The aforementioned storage medium can be a non-transitory storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program code, or a transient storage medium.

[0119] The above description and accompanying drawings sufficiently illustrate the embodiments of the present application to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, process, and other changes. The embodiments represent only possible variations. Unless expressly required, individual components and functions are optional, and the order of operations may vary. Portions and features of some embodiments may be included in or substituted for portions and features of other embodiments. Furthermore, the terms used in this application are intended only to describe the embodiments and are not intended to limit the claims. As used in the embodiments and in the claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. In addition, when used in this application, the terms "comprise" and its variations "comprises" and / or "comprising" refer to the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. In the absence of further limitations, the phrase "comprising a..." does not preclude the presence of other identical elements in the process, method, or apparatus comprising the elements. In this document, each embodiment may focus on the differences from other embodiments, and similar portions between the embodiments may refer to each other. For methods, products, etc. disclosed in the embodiments, if they correspond to the method portion disclosed in the embodiments, the relevant portions may refer to the description of the method portion.

[0120] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. Technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the embodiments of the present application. Technicians can clearly understand that for the convenience and brevity of description, the specific working process of the above-described systems, devices and units can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0121] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units can be merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, the functional units in the embodiments of the present application may be integrated into a processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.

[0122] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the system, method and computer program product according to the embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a part of a module, program segment or code, and a part of a module, program segment or code comprises one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a special hardware-based system that performs the function or action of the specification, or can be implemented by a combination of special hardware and computer instructions.

Claims

1. A method for continuous speech recognition, characterized in that: include: The processor's REE application cache is used, and all processes of the REE are frozen, so that the REE enters sleep mode; The TEE of the processor executes a VAD detection routine in response to an SMC interrupt; wherein the REE and the TEE are divided by a Trust Zone; The TEE reads the voice data of the sound collection device; When the voice data is non-environmental noise, the TEE caches the voice data in the cache applied for by the REE; The TEE calls the SMC interrupt to wake up the Kernel; The Kernel executes the Resume operation; The REE calls the application to read the voice data in the applied buffer and parses the voice data to obtain a parsing result.

2. The method for continuous speech recognition according to claim 1, wherein: Before the REE enters sleep mode, the method for continuous speech recognition further includes: reducing the operating frequency of the processor and reducing the operating frequency of the memory; After waking up the Kernel, the continuous speech recognition method further includes: increasing the operating frequency of the processing and increasing the operating frequency of the memory.

3. A method for continuous speech recognition, characterized in that: include: The processor's REE freezes all processes; In response to an SMC interrupt, the TEE of the processor executes a VAD detection routine; wherein the REE and the TEE are divided by a Trust Zone; TEE reads the sound data detected by the sound collection device; When the sound data is non-environmental noise, the TEE analyzes the sound data and obtains an analysis result; The TEE calls the SMC interrupt to wake up the Kernel; The Kernel executes the Resume operation; The REE calls an application to read the parsing result of the sound data.

4. The method for continuous speech recognition according to claim 3, wherein: While the TEE performs the VAD detection routine, it also includes: Monitor wakeup source interrupts in real time; When a wakeup source interrupt is detected, the TEE executes an SMC interrupt to wake up the Kernel. The Kernel executes the Resume operation; The REE calls a related application to execute the source interrupt.

5. The method for continuous speech recognition according to any one of claims 1 to 4, characterized in that: Before the TEE reads the sound data detected by the sound collection device, the method further includes: The TEE configures relevant parameters of the voice detection device; or the REE configures relevant parameters of the voice detection device.

6. The method for continuous speech recognition according to claim 5, wherein: The voice detection device is configured with a hardware switch; The TEE configures relevant parameters of the voice detection device, including: connecting the hardware switch; The REE configures relevant parameters of the voice detection device, including: connecting the hardware switch.

7. The method for continuous speech recognition according to any one of claims 1 to 4, characterized in that: After the REE performs the VAD detection routine, it also includes: Adjust the GATE I / D cache to improve the detection performance of the VAD detection routine.

8. The method for continuous speech recognition according to any one of claims 1 to 4, characterized in that: Before said REE freezes all processes, also includes: The Kernel executes the suspend process.

9. A continuous speech recognition device comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to perform the method for continuous speech recognition according to any one of claims 1 to 8 when executing the program instructions.

10. An intelligent switch panel, characterized in that: It comprises the continuous speech recognition device as claimed in claim 9.

Images