A speech recognition method, device, equipment and computer storage medium

Abstract

The present application discloses a speech recognition method, device, equipment and computer storage medium, the method comprising: obtaining elevator voice command information; identifying the elevator voice command information, obtaining a speech recognition result of the elevator voice command information, the speech recognition result including at least a first floor information keyword; detecting whether there is a second floor information keyword corresponding to the first floor information keyword in the speech recognition result, the second floor information keyword including the first floor keyword and a keyword segment before the first floor information keyword; if the second floor keyword exists, determining the second floor information keyword as the final recognition result of the elevator voice command information. Through the present application, the problems caused by the interference factors such as pronunciation of the keywords in the user's elevator voice command information can be effectively overcome, so that the user can accurately and effectively control the elevator by voice, and improve the user's elevator satisfaction.

Description

Technical Field

[0001] The present application belongs to the field of audio processing technology, and in particular, relates to a speech recognition method, device, equipment and computer storage medium. Background Art

[0002] In the field of audio processing technology, the acquired voice commands are usually processed and recognized, and then the corresponding functions are executed. Existing applications of voice recognition technology include voice dialing, indoor elevator equipment control, voice document retrieval, simple dictation data entry, etc.

[0003] In the intelligent elevator application based on speech recognition, the acquired user's voice command for taking the elevator is processed and recognized through the corresponding audio processing module to obtain the corresponding score of the target floor keyword, so that the target floor information keyword with the highest score is used as the final recognition result of the user's voice command for taking the elevator.

[0004] However, since the voice command information issued by the user for taking the elevator is often interfered by factors such as the user's pronunciation or accent, the existing intelligent elevator system only outputs the target floor information keyword with the highest score when performing voice recognition, and is unable to overcome the problem caused by interference factors such as pronunciation or accent of the target floor keyword. As a result, according to the voice recognition method of the existing intelligent elevator system, the user's real target floor is usually unable to be correctly identified, resulting in the user being unable to accurately and effectively perform voice control of the elevator. Summary of the invention

[0005] The embodiments of the present application provide a speech recognition method, device, equipment and computer storage medium, which can effectively overcome the problems caused by interference factors such as pronunciation of keywords, so that users can accurately and effectively perform voice control on the elevator.

[0006] In a first aspect, an embodiment of the present application provides a speech recognition method, the method comprising:

[0007] Get the voice command information for taking the elevator;

[0008] Recognize the elevator voice command information, and obtain the voice recognition result of the elevator voice command information, wherein the voice recognition result of the elevator voice command information at least includes the first floor information keyword;

[0009] Detecting whether there is a second floor information keyword corresponding to the first floor information keyword in the voice recognition result of the elevator voice command information, where the second floor information keyword includes the first floor keyword and a keyword segment located before the first floor information keyword;

[0010] When there is a second floor keyword in the voice recognition result of the elevator voice command information, the second floor information keyword is determined as the final recognition result of the elevator voice command information.

[0011] In some embodiments, recognizing the elevator voice command information and obtaining the voice recognition result of the elevator voice command information includes:

[0012] Identify keywords in the elevator voice command information according to the target recognition model, and obtain corresponding scores of the keywords in the elevator voice command information;

[0013] According to the corresponding scores of the keywords, the speech recognition results of the elevator voice command information are obtained;

[0014] Among them, the first floor information keyword is the keyword with the highest score in the elevator voice command information.

[0015] In some embodiments, a difference between a score of the second floor information keyword and a score of the first floor information keyword is less than a preset threshold.

[0016] In some embodiments, recognizing the elevator voice command information and obtaining the voice recognition result of the elevator voice command information includes:

[0017] Using the acoustic model and the language model to respectively identify the keywords in the elevator voice command information, and obtaining a first score of the keyword output by the acoustic model and a second score of the keyword output by the language model;

[0018] According to the first score and the second score of the keyword, a speech recognition result of the elevator voice command information is obtained.

[0019] In some embodiments, determining the second floor information keyword as the final recognition result of the elevator voice command information includes:

[0020] When there are multiple second floor information keywords, the second floor information keyword with the highest score is determined as the final recognition result of the elevator voice instruction information.

[0021] In some embodiments, the speech recognition method further comprises:

[0022] When there is no second floor keyword in the voice recognition result of the elevator voice command information, the first floor information keyword is determined as the final recognition result of the elevator voice command information.

[0023] In a second aspect, an embodiment of the present application provides a speech recognition device, the speech recognition device comprising:

[0024] An acquisition module is used to obtain elevator voice command information;

[0025] A recognition module, used for recognizing the elevator voice command information, and obtaining a voice recognition result of the elevator voice command information, wherein the voice recognition result of the elevator voice command information at least includes a first floor information keyword;

[0026] A detection module, used to detect whether there is a second floor information keyword corresponding to the first floor information keyword in the voice recognition result of the elevator voice command information, the second floor information keyword including the first floor information keyword and a keyword segment located before the first floor information keyword;

[0027] The determination module is used to determine the second floor information keyword as the final recognition result of the elevator voice command information when there is a second floor keyword in the voice recognition result of the elevator voice command information.

[0028] In a third aspect, an embodiment of the present application provides a speech recognition device, characterized in that the device includes: a processor and a memory storing computer program instructions;

[0029] When the processor executes the computer program instructions, the speech recognition method provided in any one of the above-mentioned embodiments of the present application is implemented.

[0030] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, characterized in that computer program instructions are stored on the computer-readable storage medium, and when the computer program instructions are executed by a processor, a speech recognition method provided in any one of the above-mentioned embodiments of the present application is implemented.

[0031] The embodiments of the present application provide a speech recognition method, device, equipment and computer storage medium, which obtains the speech recognition result of the elevator voice command information by recognizing the user's elevator voice command information, and uses the target recognition model to recognize the keywords in the elevator voice command information, and obtains the corresponding score of the keywords in the elevator voice command information. Since the method takes into account the pronunciation of the keywords in the user's elevator voice command, it does not directly output the first floor information keyword as the final recognition result according to the prior art, but first detects whether there is a second floor information keyword corresponding to the first floor information keyword in the speech recognition result. If the second floor keyword exists in the speech recognition result of the elevator voice command information, the second floor information keyword is determined as the final recognition result, thereby effectively overcoming the problems caused by interference factors such as the pronunciation of the keywords, allowing users to accurately and effectively control the elevator by voice, and improving user satisfaction with the elevator. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0033] Figure 1 is a flowchart of a speech recognition method provided by an embodiment of the present application;

[0034] Figure 2 is a structural diagram of a speech recognition device provided by another embodiment of the present application;

[0035] Figure 3 It is a structural diagram of a speech recognition device provided in yet another embodiment of the present application. DETAILED DESCRIPTION

[0036] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0037] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0038] As described in the background technology section, conventional intelligent elevator systems generally obtain voice command information of the user to take the elevator and obtain a speech recognition result of the user's voice command information. Conventional intelligent elevator systems recognize keywords in the user's voice command information based on a target recognition model to obtain corresponding scores of the keywords in the user's voice command information, and use the keyword with the highest score as the final recognition result of the user's voice command information.

[0039] However, the inventors have found through research that when many users speak the voice command information for taking the elevator, due to problems such as pronunciation or accent, the keywords contained in the command information, that is, the specific floor information, will be interfered by pronunciation or accent. For example, the floor the user really wants to go to is the 16th floor, but because the actual keyword said by the user is "16th floor", there is a pronunciation problem. In this way, by only outputting the keyword with the highest score after recognition processing as the final recognition result, it is very likely that the final control instruction obtained by taking the elevator is to go to the "6th floor". In this case, the prior art cannot overcome the above-mentioned prior art problems.

[0040] After research, the inventors also found that, taking the above example as an example, if the real target floor contained in the user's elevator voice command information is "sixth floor", and "sixth floor" is the highest-scoring keyword, then the speech recognition results are unlikely to contain target floor keywords such as "sixteenth floor" and "twenty-sixth floor" with scores close to "sixth floor". The target floor keywords usually include "sixth floor" and the keyword segment before "sixth floor". That is to say, for example, when the highest-scoring keyword is "sixth floor", if the speech recognition results are tested and it is found that the recognition results also include the keyword "sixteenth floor" with a score close to "sixth floor", then "sixteenth floor" is often more likely to be the user's real target floor.

[0041] Thus, based on the research findings, in order to solve the problems of the prior art, the present application provides a speech recognition method, device, equipment and computer storage medium. The speech recognition method, device, equipment and computer storage medium of the embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. It should be noted that the embodiments of the present application are not intended to limit the scope of the present invention.

[0042] The following first introduces the speech recognition method provided in the embodiment of the present application.

[0043] Figure 1 FIG. 1 is a flow chart of a speech recognition method provided by an embodiment of the present application. Figure 1 As shown, the speech recognition method in the embodiment of the present invention includes the following steps S110 to S140:

[0044] S110, obtaining elevator voice command information.

[0045] S120, identifying the elevator voice command information and obtaining the corresponding voice recognition result.

[0046] S130, detecting the second floor information keyword in the voice recognition result of the elevator voice command information.

[0047] S140, determining the second floor information keyword as the final recognition result of the elevator voice command information.

[0048] The embodiment of the present application provides a speech recognition method, which obtains a speech recognition result of the elevator voice command information by recognizing the user's elevator voice command information, and uses a target recognition model to recognize the keywords in the elevator voice command information to obtain the corresponding score of the keywords in the elevator voice command information. Since the method takes into account the pronunciation of the keywords in the user's elevator voice command, it does not directly output the first floor information keyword as the final recognition result according to the prior art, but first detects whether there is a second floor information keyword corresponding to the first floor information keyword in the speech recognition result. If the second floor keyword exists in the speech recognition result of the elevator voice command information, the second floor information keyword is determined as the final recognition result, thereby effectively overcoming the problems caused by interference factors such as the pronunciation of the keywords, allowing users to accurately and effectively control the elevator by voice, and improving user satisfaction with the elevator.

[0049] In some embodiments, in S110, the voice information sent by the user in the elevator is received through the corresponding voice receiving device, that is, the user's elevator voice command information is obtained.

[0050] As an example, the voice command information for taking an elevator may be a voice command issued by a user using the elevator. For example, the voice command issued by the user may be "go to the sixteenth floor." The voice command contains a keyword, namely, the user's target floor information. In this example, "sixteenth floor" is the target floor information keyword contained in the user's voice command information. The intelligent elevator system receives the voice information issued by the user in the elevator through the corresponding voice receiving device, thereby obtaining the voice command information for taking the elevator.

[0051] In some embodiments, in order to improve the accuracy of the speech recognition result of the elevator voice command information, in S120, the following steps may be specifically included:

[0052] Identify keywords in the elevator voice command information according to the target recognition model, and obtain corresponding scores of the keywords in the elevator voice command information;

[0053] According to the corresponding scores of the keywords, the speech recognition results of the elevator voice command information are obtained;

[0054] Among them, the voice recognition result corresponding to the elevator voice command information includes at least the first floor information keyword.

[0055] The first floor information keyword is the keyword with the highest score in the elevator voice command information.

[0056] As an example, the target recognition model may specifically include at least one of an acoustic model and a language model.

[0057] In the case where the above-mentioned target recognition model includes an acoustic model and a language model, the first score of the target floor information keywords is obtained by outputting the elevator voice command information to the acoustic model and using the acoustic model to identify the target floor information keywords in the received user voice command information; the second score of the target floor information keywords is obtained by outputting the elevator voice command information to the language model and using the language model to identify the target floor information keywords in the received user voice command information.

[0058] Based on the first score and the second score of the target floor information keyword, specifically, the final score result may be: the sum of the first score and the second score, thereby obtaining the score results corresponding to the identified multiple target floor information keywords.

[0059] The following is a specific description in conjunction with the elevator scenario. For example, the elevator voice command information issued by the elevator user may be "go up to the sixteenth floor". The target floor information keywords in the received user voice command information are identified by utilizing the internally stored acoustic model and language model. There may be multiple identified target floor information keywords, such as "sixth floor", "sixteenth floor", "thirty-sixth floor" and "ninth floor, etc."

[0060] According to the above-mentioned acoustic model and language model, the scores of each possible target floor information keyword can be obtained. Taking the percentage system as an example, since the user's voice command is affected by his pronunciation or accent, the final score results are "sixth floor-90 points", "sixteenth floor-87 points", "thirty-sixth floor-60 points" and "ninth floor-50 points", etc. Among the above results, "sixth floor" has the highest score, that is, "sixth floor" is the corresponding first floor information keyword in one embodiment of the present application.

[0061] In some embodiments, in order to improve the accuracy of the speech recognition results, in S130, the second floor information keyword in the speech recognition results of the elevator voice command information is detected.

[0062] The second floor information keyword corresponds to the first floor information keyword, and the second floor information keyword includes the first floor keyword and a keyword segment before the first floor information keyword.

[0063] Specifically, according to the corresponding scores of the possible target floor information keywords in the user voice command information identified in the above step 120, the second floor information keywords in the recognition result are searched and detected. In the embodiment of the present application, the first floor information keyword determined by the above steps is "sixth floor". According to the definition of the second floor information keyword, in this example, the second floor information keyword corresponding to the first floor information keyword "sixth floor" can be "sixteenth floor", "twenty-sixth floor" and "thirty-sixth floor", etc. By searching and detecting the second floor information keywords in the above recognition result, it can be detected that "thirty-sixth floor" and "sixteenth floor" in the recognition result are the second floor information keywords corresponding to the above first floor information keywords.

[0064] As an example, in order to improve the accuracy of the speech recognition method and reduce elevator misoperation, step S130 may also include:

[0065] According to the difference between the score of the second floor information keyword and the score of the first floor information keyword, the difference is compared with a preset threshold.

[0066] For the second floor information keyword whose difference is less than the preset threshold, it is determined as the final second floor information keyword of the first floor information keyword.

[0067] Specifically, in the percentage system, the preset threshold may be preset to 10 points, that is, the score difference between the first floor information keyword and the corresponding second floor information keyword needs to be less than 10 points.

[0068] In an embodiment of the present application, the "thirty-sixth floor" and "sixteenth floor" detected in the recognition results may be the second floor information keywords corresponding to the above-mentioned first floor information keywords, but in order to ultimately obtain a more accurate speech recognition result, the above-mentioned second floor information keywords "thirty-sixth floor" and "sixteenth floor" are further screened.

[0069] By limiting the difference with the score "90 points" of the first floor information keyword "sixth floor" to no more than 10 points, the final second floor information keyword "sixteenth floor" is obtained based on the scores of "sixteenth floor - 87 points" and "thirty-sixth floor - 60 points".

[0070] It should be noted that the above embodiment only provides one possible situation and is not intended to limit the scope of the present invention.

[0071] In some embodiments, in order to improve the accuracy of elevator voice recognition results and enhance user satisfaction, in S140, the final second floor keyword is obtained through S110 to S130, and the obtained second floor information keyword is determined as the final recognition result of the recognized elevator voice command information.

[0072] Specifically, in an embodiment of the present application, the second floor information keyword is determined as the final recognition result of the elevator voice command information, and based on the determined voice recognition result, the user can control the elevator to the target floor corresponding to the second floor information keyword after issuing a voice command.

[0073] In a specific elevator scenario, the user's voice command information may be "go up to the sixteenth floor", the first floor information keyword is "sixth floor", and the corresponding second floor information keyword finally obtained is "sixteenth floor".

[0074] By determining the second floor information keyword "16th floor" as the final recognition result of the user's voice command information, and based on the determined final recognition result "16th floor", the elevator can be controlled to go to the user's real target floor "16th floor", instead of using the first floor information keyword "6th floor" with the highest keyword score as the final recognition result, thereby controlling the elevator to go to the "6th floor". In this way, the problem caused by interference factors such as pronunciation of keywords is effectively overcome, allowing users to accurately and effectively control the elevator by voice, and improving user satisfaction with the elevator.

[0075] As an example, in order to make the speech recognition result closest to the user's actual target floor information, step S140 may further include:

[0076] When there are multiple second floor information keywords finally obtained, the second floor information keyword with the highest score is determined as the final recognition result of the elevator voice instruction information.

[0077] Specifically, the user's voice command information may be "go up to the sixteenth floor", the first floor information keyword is "sixth floor", and the two second floor information keywords are "sixteenth floor" and "twenty-sixth floor", and the scores corresponding to the two second floor information keywords are "sixteenth floor -87 points" and "twenty-sixth floor -82 points", respectively.

[0078] At this time, the two second-floor keywords obtained are selected, that is, the second-floor keyword with a higher score is selected, and it is used as the final recognition result of the elevator voice command information. In this embodiment of the present application, the score of "the sixteenth floor" is higher than that of "the twenty-sixth floor", so "the sixteenth floor" is finally determined as the final voice recognition result, and according to the determined final recognition result "the sixteenth floor", the elevator is controlled to go to the user's actual target floor "the sixteenth floor".

[0079] As an example, in order to improve the elevator operation efficiency, step S140 may further include:

[0080] When it is detected that the second floor keyword does not exist in the voice recognition result of the elevator voice command information, the first floor information keyword is determined as the final recognition result of the elevator voice command information.

[0081] Specifically, in an actual elevator riding scenario, the possible target floor information keywords obtained after the user's elevator voice command information is recognized do not include the second floor keyword. For example, the user's elevator voice command information may be "go to the sixth floor", and "sixth floor" is the floor information keyword with the highest score in the recognition result, that is, the first floor information keyword. The second floor keyword corresponding to "sixth floor" is not detected in the recognition result. At this time, by determining "sixth floor" as the final voice recognition result, and based on the determined final recognition result "sixth floor", the elevator is controlled to go to the target floor "sixth floor".

[0082] Below through Figure 2 A speech recognition device according to an embodiment of the present application is described in detail. The speech recognition device corresponds to a speech recognition method.

[0083] Figure 2 A structural schematic diagram of a speech recognition device provided in yet another embodiment of the present application is shown.

[0084] Figure 2 The voice recognition device shown includes:

[0085] The acquisition module 210 is used to acquire the elevator voice command information.

[0086] The recognition module 220 is used to recognize the elevator voice command information and obtain the voice recognition result of the elevator voice command information. The voice recognition result of the elevator voice command information at least includes the first floor information keyword.

[0087] The detection module 230 is used to detect whether there is a second floor information keyword corresponding to the first floor information keyword in the voice recognition result of the elevator voice command information, and the second floor information keyword includes the first floor keyword and the keyword segment before the first floor information keyword.

[0088] The determination module 240 is used to determine the second floor information keyword as the final recognition result of the elevator voice command information when there is a second floor keyword in the voice recognition result of the elevator voice command information.

[0089] A speech recognition device provided in an embodiment of the present application recognizes the user's elevator voice command information through various functional modules to obtain a speech recognition result of the elevator voice command information, and uses a target recognition model to recognize keywords in the elevator voice command information to obtain corresponding scores of the keywords in the elevator voice command information. Since this method takes into account factors such as the pronunciation of keywords in the user's elevator voice command, it does not directly output the first floor information keyword as the final recognition result according to the prior art, but first detects whether there is a second floor information keyword corresponding to the first floor information keyword in the speech recognition result. If there is a second floor keyword in the speech recognition result of the elevator voice command information, the second floor information keyword is determined as the final recognition result, thereby effectively overcoming the problems caused by interference factors such as the pronunciation of keywords, allowing users to accurately and effectively control the elevator by voice, and improving user satisfaction with the elevator.

[0090] In some embodiments, in order to improve the accuracy of speech recognition results, the recognition module 220 may include:

[0091] The recognition submodule can be used to recognize keywords in the elevator voice command information according to the target recognition model and obtain corresponding scores of the keywords in the elevator voice command information;

[0092] The processing submodule can be used to obtain the speech recognition result of the elevator voice command information according to the corresponding scores of the keywords.

[0093] Among them, the first floor information keyword is the keyword with the highest score in the elevator voice command information.

[0094] In some embodiments, the recognition submodule may be specifically used to respectively recognize keywords in the elevator voice command information using an acoustic model and a language model, and obtain a first score of the keyword output by the acoustic model and a second score of the keyword output by the language model;

[0095] The processing submodule can be specifically used to obtain the speech recognition result of the elevator voice command information according to the first score and the second score of the keyword.

[0096] In some embodiments, in order to make the final recognition result closer to the user's actual target floor, the difference between the score of the second floor information keyword and the score of the first floor information keyword is less than a preset threshold.

[0097] In some embodiments, in order to improve the accuracy of elevator voice control and thus improve user satisfaction, the determination module 240 may include:

[0098] The first determination submodule can be used to determine the second floor information keyword with the highest score as the final recognition result of the elevator voice instruction information when there are multiple second floor information keywords.

[0099] In some embodiments, in order to improve the elevator operation efficiency, the determination module 240 may further include:

[0100] The second determination submodule may be used to determine the first floor information keyword as the final recognition result of the elevator voice command information when there is no second floor keyword in the voice recognition result of the elevator voice command information.

[0101] Figure 3 A structural schematic diagram of a speech recognition device provided in yet another embodiment of the present application is shown.

[0102] The speech recognition device may include a processor 301 and a memory 302 storing computer program instructions.

[0103] Specifically, the processor 301 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0104] The memory 302 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 302 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 302 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 302 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 302 is a non-volatile solid-state memory.

[0105] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of the present application.

[0106] The processor 301 implements any one of the speech recognition methods in the above embodiments by reading and executing computer program instructions stored in the memory 302 .

[0107] In one example, the speech recognition device may further include a communication interface 303 and a bus 310. Figure 3 As shown, the processor 301, the memory 302, and the communication interface 303 are connected via a bus 310 and communicate with each other.

[0108] The communication interface 303 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0109] Bus 310 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 310 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0110] The speech recognition device can execute the speech recognition method in the embodiment of the present application based on the acquired user's elevator voice command information, thereby realizing the combination Figure 1 and Figure 2 The described speech recognition method and device.

[0111] In addition, in combination with the speech recognition method in the above embodiment, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any speech recognition method in the above embodiment is implemented.

[0112] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0113] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0114] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0115] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0116] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0117] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A speech recognition method, characterized in that: include: Get the voice command information for taking the elevator; Identify the elevator voice command information and obtain a voice recognition result of the elevator voice command information, wherein the voice recognition result of the elevator voice command information at least includes a first floor information keyword; Detecting whether there is a second floor information keyword corresponding to the first floor information keyword in the voice recognition result of the elevator voice command information, where the second floor information keyword includes the first floor information keyword and a keyword segment located before the first floor information keyword; When the second floor information keyword exists in the voice recognition result of the elevator voice command information, the second floor information keyword is determined as the final recognition result of the elevator voice command information.

2. The method according to claim 1, characterized in that: The step of recognizing the elevator voice command information and obtaining a voice recognition result of the elevator voice command information includes: Identify keywords in the elevator voice command information according to the target recognition model, and obtain corresponding scores of the keywords in the elevator voice command information; Obtaining a speech recognition result of the elevator voice command information according to the corresponding score of the keyword; Among them, the first floor information keyword is the keyword with the highest score in the elevator voice command information.

3. The method according to claim 2, characterized in that A difference between the score of the second floor information keyword and the score of the first floor information keyword is less than a preset threshold.

4. The method according to claim 2, characterized in that: The step of recognizing the elevator voice command information and obtaining a voice recognition result of the elevator voice command information includes: Using an acoustic model and a language model to respectively identify keywords in the elevator voice command information, and obtaining a first score of the keyword output by the acoustic model and a second score of the keyword output by the language model; The speech recognition result of the elevator voice command information is obtained according to the first score and the second score of the keyword.

5. The method according to any one of claims 2-3, characterized in that: The step of determining the second floor information keyword as the final recognition result of the elevator voice command information includes: When there are multiple second floor information keywords, the second floor information keyword with the highest score is determined as the final recognition result of the elevator voice instruction information.

6. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: When the second floor information keyword does not exist in the voice recognition result of the elevator voice command information, the first floor information keyword is determined as the final recognition result of the elevator voice command information.

7. A speech recognition device, characterized in that: The device comprises: An acquisition module is used to obtain the elevator voice command information; A recognition module, used for recognizing the elevator voice command information, and obtaining a voice recognition result of the elevator voice command information, wherein the voice recognition result of the elevator voice command information at least includes a first floor information keyword; a detection module, configured to detect whether there is a second floor information keyword corresponding to the first floor information keyword in the voice recognition result of the elevator voice command information, wherein the second floor information keyword includes the first floor information keyword and a keyword segment located before the first floor information keyword; A determination module is used to determine the second floor information keyword as the final recognition result of the elevator voice command information when the second floor information keyword exists in the voice recognition result of the elevator voice command information.

8. A speech recognition device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the speech recognition method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the speech recognition method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the speech recognition method as described in any one of claims 1 to 6.

Images