Speech recognition methods, devices, household appliances and electronic devices

Abstract

This invention discloses a speech recognition method, apparatus, household appliance, and electronic device. The recognition method includes: acquiring speech information; recognizing the speech information to obtain a speech recognition result; and performing error correction processing on the speech recognition result based on the number of repetitions of the speech recognition result. The speech recognition method of this invention can perform error correction processing on the speech recognition result based on the number of repetitions of the speech recognition result, enabling error correction when the speech recognition result repeatedly fails, thereby improving the accuracy of speech recognition and enhancing the user experience.

Description

Technical Field

[0001] This invention relates to the field of home appliance technology, and in particular to a voice recognition method, device, home appliance, electronic device, and computer-readable storage medium. Background Technology

[0002] Currently, speech recognition technology is widely used in voice input, voice control, intelligent dialogue query and other fields. However, speech recognition results may be incorrect due to external factors, non-standard user pronunciation, or excessively fast user speech, which greatly affects the user experience. Summary of the Invention

[0003] The present invention aims to at least partially solve one of the technical problems in the aforementioned technologies. Therefore, one objective of the present invention is to propose a speech recognition method capable of correcting speech recognition results based on the number of repetitions. This method can correct errors when speech recognition results repeatedly fail, thereby improving the accuracy of speech recognition and enhancing the user experience.

[0004] The second objective of this invention is to provide a speech recognition device.

[0005] The third objective of this invention is to provide a household appliance.

[0006] The fourth objective of this invention is to provide an electronic device.

[0007] The fifth objective of this invention is to provide a computer-readable storage medium.

[0008] To achieve the above objectives, a first aspect of the present invention provides a speech recognition method, comprising: acquiring speech information; recognizing the speech information to obtain a speech recognition result; and performing error correction processing on the speech recognition result based on the number of repetitions of the speech recognition result.

[0009] The speech recognition method according to embodiments of the present invention can perform error correction processing on the speech recognition result based on the number of repetitions of the speech recognition result. It can perform error correction processing when the speech recognition result is repeatedly incorrect, thereby improving the accuracy of speech recognition and improving the user experience.

[0010] In addition, the speech recognition method proposed in the above embodiments of the present invention may also have the following additional technical features:

[0011] In one embodiment of the present invention, the step of correcting the speech recognition result based on the number of repetitions of the speech recognition result includes: if the speech recognition result is the same for a second set number of consecutive speech recognition results for a first set number of times, then the speech recognition result for the current time is corrected, wherein the second set number of times does not exceed the first set number of times.

[0012] In one embodiment of the present invention, the step of correcting the speech recognition result includes: obtaining a set of candidate household appliance names, a set of candidate operation types, and a set of candidate working modes; and performing error correction processing on the speech recognition result based on the set of candidate household appliance names, the set of candidate operation types, and the set of candidate working modes.

[0013] In one embodiment of the present invention, the step of correcting the speech recognition result based on the candidate set of household appliance names, the candidate set of operation types, and the candidate set of working modes includes: matching the candidate household appliance name with the highest similarity value that has not yet been matched in the candidate set of household appliance names as the household appliance name in the speech recognition result; if the household appliance name matching result is unsuccessful, then matching the candidate operation type with the highest similarity value that has not yet been matched in the candidate set of operation types as the operation type in the speech recognition result; if the operation type matching result is unsuccessful, then matching the candidate working mode with the highest similarity value that has not yet been matched in the candidate working modes as the working mode in the speech recognition result.

[0014] In one embodiment of the present invention, obtaining the candidate set of household appliance names includes: generating a first set based on the names of household appliances successfully recognized in the speech recognition results within a previously set time period; generating a second set based on the names of household appliances that the user has previously operated within the current time period; generating a third set based on the names of household appliances whose operation probability exceeds a set threshold within the current time period; generating a fourth set based on the names of household appliances that the user is currently online; and determining the candidate set of household appliance names based on the first set, the second set, the third set, and the fourth set.

[0015] In one embodiment of the present invention, determining the candidate set of household appliance names based on the first set, the second set, the third set, and the fourth set includes: determining the intersection or union of at least one or at least two of the first set, the second set, the third set, and the fourth set as the candidate set of household appliance names.

[0016] In one embodiment of the present invention, obtaining the candidate operation type set and / or the candidate working mode set includes: obtaining the name of the user's currently online home appliance; obtaining the authorization information corresponding to the currently online home appliance name; determining the currently online home appliance name that has been authorized as the target home appliance name; generating the candidate operation type set according to the preset operation type corresponding to the target home appliance name, and / or generating the candidate working mode set according to the preset working mode corresponding to the target home appliance name.

[0017] To achieve the above objectives, a second aspect of the present invention provides a speech recognition device, comprising: an acquisition module for acquiring speech information; a recognition module for recognizing the speech information to obtain a speech recognition result; and an error correction module for performing error correction processing on the speech recognition result based on the number of repetitions of the speech recognition result.

[0018] The speech recognition device of this invention can perform error correction processing on the speech recognition result based on the number of times the speech recognition result is repeated. It can perform error correction processing when the speech recognition result is repeatedly wrong, thereby improving the accuracy of speech recognition and improving the user experience.

[0019] In addition, the speech recognition device proposed in the above embodiments of the present invention may also have the following additional technical features:

[0020] In one embodiment of the present invention, the error correction module is specifically used to: if there are two sets of identical speech recognition results in a second set number of consecutive speech recognition results after a first set number of consecutive sets of results, then perform error correction processing on the current speech recognition result, wherein the second set number of consecutive sets of results does not exceed the first set number of consecutive sets of results.

[0021] In one embodiment of the present invention, the error correction module is specifically used to: obtain a set of candidate household appliance names, a set of candidate operation types, and a set of candidate working modes; and perform error correction processing on the speech recognition result based on the set of candidate household appliance names, the set of candidate operation types, and the set of candidate working modes.

[0022] In one embodiment of the present invention, the error correction module is further configured to: match the candidate household appliance name with the highest similarity value that has not yet been matched in the candidate household appliance name set as the household appliance name in the speech recognition result; if the household appliance name matching result is unsuccessful, then match the candidate operation type with the highest similarity value that has not yet been matched in the candidate operation type set as the operation type in the speech recognition result; if the operation type matching result is unsuccessful, then match the candidate working mode with the highest similarity value that has not yet been matched in the candidate working mode as the working mode in the speech recognition result.

[0023] In one embodiment of the present invention, the error correction module is further configured to: generate a first set based on the names of household appliances in the successfully recognized speech recognition results within a previously set time period; generate a second set based on the names of household appliances that the user has previously operated within the current time period; generate a third set based on the names of household appliances whose operation probability exceeds a set threshold within the current time period; generate a fourth set based on the names of household appliances that the user is currently online; and determine the candidate set of household appliance names based on the first set, the second set, the third set, and the fourth set.

[0024] In one embodiment of the present invention, the error correction module is further configured to: determine the intersection or union of at least one or at least two of the first set, the second set, the third set, and the fourth set as the candidate set of household appliance names.

[0025] In one embodiment of the present invention, the error correction module is further configured to: obtain the name of the user's currently online home appliance; obtain the authorization information corresponding to the currently online home appliance name; determine the currently online home appliance name that is authorized by the authorization information as the target home appliance name; generate the candidate operation type set according to the preset operation type corresponding to the target home appliance name, and / or generate the candidate working mode set according to the preset working mode corresponding to the target home appliance name.

[0026] To achieve the above objectives, a third aspect of the present invention provides a household appliance including the voice recognition device described in the second aspect of the present invention.

[0027] The household appliance of this invention can perform error correction processing on the speech recognition result based on the number of times the speech recognition result is repeated. It can perform error correction processing when the speech recognition result is repeatedly wrong, thereby improving the accuracy of speech recognition and improving the user experience.

[0028] To achieve the above objectives, a fourth aspect of the present invention provides an electronic device, including a memory and a processor; wherein the processor reads executable program code stored in the memory to run a program corresponding to the executable program code, so as to implement the speech recognition method described in the first aspect of the present invention.

[0029] The electronic device of this invention executes a computer program stored in a memory through a processor, which can perform error correction processing on the speech recognition result based on the number of times the speech recognition result is repeated. Error correction processing can be performed when the speech recognition result is repeatedly incorrect, thereby improving the accuracy of speech recognition and improving the user experience.

[0030] To achieve the above objectives, a fifth aspect of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the speech recognition method described in the first aspect of the present invention.

[0031] The computer-readable storage medium of this invention, by storing a computer program and having it executed by a processor, can perform error correction processing on the speech recognition results based on the number of repetitions of the speech recognition results. It can perform error correction processing when the speech recognition results repeatedly fail, thereby improving the accuracy of speech recognition and enhancing the user experience.

[0032] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0033] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0034] Figure 1 A flowchart of a speech recognition method according to an embodiment of the present invention;

[0035] Figure 2 This is a flowchart illustrating the error correction process for speech recognition results in a speech recognition method according to an embodiment of the present invention;

[0036] Figure 3 This is a flowchart illustrating the process of obtaining a set of candidate household appliance names in a speech recognition method according to an embodiment of the present invention.

[0037] Figure 4 This is a flowchart illustrating the error correction process performed on the speech recognition result based on a set of candidate household appliance names, a set of candidate operation types, and a set of candidate working modes in a speech recognition method according to an embodiment of the present invention.

[0038] Figure 5 This is a flowchart illustrating the process of obtaining a set of candidate operation types and / or a set of candidate working modes in a speech recognition method according to an embodiment of the present invention.

[0039] Figure 6 This is a block diagram of a speech recognition device according to an embodiment of the present invention;

[0040] Figure 7 A block diagram of a household appliance according to an embodiment of the present invention; and

[0041] Figure 8 This is a block diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0042] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0043] The following description, in conjunction with the accompanying drawings, outlines a speech recognition method, apparatus, household appliance, electronic device, and computer-readable storage medium according to embodiments of the present invention.

[0044] Figure 1 This is a flowchart of a speech recognition method according to an embodiment of the present invention.

[0045] like Figure 1 As shown, the speech recognition method of this invention includes the following steps:

[0046] S101, Obtain voice information.

[0047] Voice information refers to the original voice information emitted by the user.

[0048] Optionally, voice information can be acquired using an audio acquisition device, which may include a microphone.

[0049] S102, Recognize the speech information to obtain the speech recognition result.

[0050] Optionally, a speech recognition model can be used to recognize the speech information to obtain the speech recognition result.

[0051] S103, perform error correction processing on the speech recognition result based on the number of repetitions of the speech recognition result.

[0052] Optionally, after obtaining the speech recognition result, previous speech recognition results can also be obtained and compared with the previous results. The number of times the speech recognition result is repeated can be obtained based on the comparison result. If the comparison is consistent, it indicates that the speech recognition result is repeated.

[0053] Generally, when a speech recognition result is incorrect, the user will repeat the speech information. However, the speech recognition result may still be incorrect, resulting in a large number of repetitions. In other words, the number of repetitions of the speech recognition result can reflect whether the speech recognition result is incorrect, and the speech recognition result can be corrected based on the number of repetitions.

[0054] In summary, the speech recognition method according to the embodiments of the present invention can perform error correction processing on the speech recognition result based on the number of repetitions of the speech recognition result. It can perform error correction processing when the speech recognition result is repeatedly incorrect, thereby improving the accuracy of speech recognition and improving the user experience.

[0055] Optionally, step S103 may involve correcting the speech recognition result based on the number of repetitions of the speech recognition result. This may include correcting the speech recognition result if there are two sets of speech recognition results that are the same in a second set number of consecutive speech recognition results after a first set number of repetitions. The second set number of repetitions shall not exceed the first set number of repetitions.

[0056] The first set number of times and the second set number of times can be set according to the actual situation. For example, the first set number of times can be 10 times and the second set number of times can be 5 times.

[0057] Therefore, when the number of repetitions in the speech recognition results of the first set number of consecutive sets of results reaches the second set number of times, the method performs error correction processing on the speech recognition results of the current time.

[0058] Based on the above embodiments, step S103 performs error correction processing on the speech recognition results, such as... Figure 2 As shown, it may include:

[0059] S201, obtain the set of candidate household appliance names, the set of candidate operation types, and the set of candidate working modes.

[0060] It is understood that the voice recognition method of this invention can be applied to household appliances, and the voice recognition result may include the name, operation type, and working mode of the household appliance. Household appliances may include smart microwave ovens, fans, water heaters, washing machines, dishwashers, etc., without further limitation.

[0061] Optionally, the candidate set of household appliance names, the candidate set of operation types, and the candidate set of operating modes can all be specified according to actual conditions. For example, the candidate set of household appliance names may include {microwave oven, fan, water heater}, the candidate set of operation types may include {turn on, turn off, start, stop, increase speed, decrease speed}, and the candidate set of operating modes may include {microwave, light wave, energy saving, timer}.

[0062] S202, based on the set of candidate household appliance names, the set of candidate operation types, and the set of candidate working modes, perform error correction processing on the speech recognition results.

[0063] Optionally, the speech recognition results can be corrected based on the candidate set of household appliance names, the candidate set of operation types, and the candidate set of working modes. This can include selecting the household appliance name, operation type, and working mode from the candidate set of household appliance names, the candidate set of operation types, and the candidate set of working modes, and using the selected household appliance name, operation type, and working mode as the household appliance name, operation type, and working mode in the current speech recognition results, respectively, to correct the speech recognition results.

[0064] Therefore, this method can perform error correction processing on speech recognition results based on the set of candidate household appliance names, the set of candidate operation types, and the set of candidate working modes.

[0065] Based on the above embodiments, step S201 obtains a set of candidate household appliance names, such as... Figure 3 As shown, it may include:

[0066] S301, Generate the first set based on the names of household appliances in the successfully recognized speech recognition results within the previously set time period.

[0067] The previously set time period can include the time period of the previous n days. Optionally, n can be specified according to the actual situation; for example, n can be specified as 7.

[0068] The time period can be set according to the actual situation, for example, it can be set as (8:00-10:00), (16:00-16:30), etc., without too many restrictions here.

[0069] For example, if the current time is 9:00 and the set time period for recognizing 9:00 is (8:00-10:00), then the first set can be generated based on the names of household appliances in the successfully recognized speech recognition results within the time period (8:00-10:00) of the previous 7 days.

[0070] Understandably, the first set of data can reflect users' habits of using home appliances within a set time period.

[0071] S302, Generate a second set based on the names of the home appliances that the user has actually operated in the current time period.

[0072] The current time period refers to the time period of the day, which can be specified according to the actual situation. For example, it can be specified as (8:00-10:00), (16:00-16:30), etc. There are no further restrictions here.

[0073] For example, if the current time is 9:00 and the set time period identified as 9:00 is (8:00-10:00), then a second set can be generated based on the names of the home appliances that the user has actually operated during the time period of (8:00-9:00) on the same day.

[0074] Understandably, the second set reflects users' habits of using home appliances during the current time period.

[0075] S303, Generate a third set based on the names of home appliances whose user operation probability exceeds a set threshold within the current time period.

[0076] The probability of user operation within the current time period can be calibrated according to the actual situation. For example, the probability of user operation of the range hood during the time period (6:00-8:00) can be calibrated as 80%, and the probability of user operation of the water heater during the time period (6:00-8:00) can be calibrated as 30%.

[0077] The threshold can be set according to the actual situation; for example, it can be set to 60%.

[0078] Understandably, the third set reflects the probability that a user will use a household appliance during the current time period.

[0079] S304, Generate a fourth set based on the names of the user's currently online home appliances.

[0080] Among them, home appliances that are currently online can include those that are currently connected to a normal network.

[0081] It is understandable that users can use voice control to control home appliances that are currently online, but cannot use voice control to control home appliances that are not currently online. Therefore, the fourth set can reflect the reliability of the home appliances currently used by the user.

[0082] S305, determine the set of candidate household appliance names based on the first set, the second set, the third set, and the fourth set.

[0083] Optionally, the intersection or union of at least one or at least two of the first set, second set, third set and fourth set can be determined as the candidate set of household appliance names.

[0084] Therefore, this method can determine the candidate set of household appliance names based on the first set, the second set, the third set, and the fourth set, so that the candidate set of household appliance names can reflect the user's habits, probability, and reliability of using household appliances, making it more flexible and accurate.

[0085] Based on the above embodiments, in step S202, error correction processing is performed on the speech recognition results according to the candidate set of household appliance names, the candidate set of operation types, and the candidate set of working modes, such as... Figure 4 As shown, it may include:

[0086] S401, match the candidate household appliance name with the highest similarity value that has not yet been matched in the candidate household appliance name set to the household appliance name in the speech recognition result.

[0087] The similarity value refers to the similarity between the candidate household appliance name and the household appliance name in the current speech recognition result.

[0088] S402 If the matching result of the household appliance name is unsuccessful, then the candidate operation type with the highest similarity value that has not yet been matched in the candidate operation type set will be matched as the operation type in the speech recognition result.

[0089] Among them, "unsuccessful matching of household appliance name" means that there is no candidate household appliance name in the candidate household appliance name set that has not been matched yet, and "similar value" refers to the similarity value between the candidate operation type and the operation type in the current speech recognition result.

[0090] S403 If the operation type matching result is unsuccessful, then match the candidate working mode with the highest similarity value that has not yet been matched with the working mode in the speech recognition result.

[0091] Among them, "operation type matching failure" means that there is no candidate operation type in the candidate operation type set that has not been matched yet, and "similar value" refers to the similarity value between the candidate working mode and the working mode in the current speech recognition result.

[0092] Therefore, this method can select the data with the highest similarity that has not yet been matched from the candidate set of household appliance names, candidate set of operation types, and candidate set of working modes according to the order of "household appliance name - operation type - working mode", so as to perform error correction processing on the household appliance name, operation type, and working mode in the speech recognition result respectively.

[0093] Based on the above embodiments, a set of candidate operation types and / or a set of candidate working modes are obtained, such as... Figure 5 As shown, it may include:

[0094] S501 retrieves the names of the user's currently online home appliances.

[0095] Among them, home appliances that are currently online can include those that are currently connected to a normal network.

[0096] Understandably, users can use voice control to control home appliances that are currently online, but not those that are not currently online.

[0097] Optionally, before obtaining the names of the user's currently online home appliances, network configuration can be performed on the user's current home appliances. For example, network configuration can be performed through the corresponding application (APP) of the home appliance. This network configuration may include selecting a subset of the user's current home appliances for network configuration.

[0098] Understandably, after configuring the network for a user's home appliances, if the network configuration is successful, the appliances will be online and the user can control them via voice. If the home appliance's network module malfunctions or the network fails, resulting in network configuration failure, the appliances will be offline and the user will not be able to control them via voice.

[0099] In this invention, the names of currently online home appliances can be filtered from among the home appliances, which helps to improve the success rate of voice control.

[0100] S502, retrieve the authorization information corresponding to the name of the currently online home appliance.

[0101] In an embodiment of the present invention, after obtaining the name of the user's currently online home appliance, the authorization information corresponding to the name of the currently online home appliance can be obtained.

[0102] The authorization information may include whether the home appliances have been authorized for voice control.

[0103] Understandably, if a home appliance is authorized for voice control, the user can control it by voice; if the home appliance is not authorized for voice control, the user cannot control it by voice.

[0104] S503, the authorized information is the name of the currently online home appliance that has been authorized, and it is determined as the name of the target home appliance.

[0105] In this invention, the names of currently online and authorized home appliances can be filtered from among the home appliances, which helps to improve the success rate of voice control.

[0106] S504, generate a set of candidate operation types based on the preset operation type corresponding to the name of the target home appliance, and / or generate a set of candidate operating modes based on the preset operating mode corresponding to the name of the target home appliance.

[0107] It is understandable that there can be one or more target home appliance names, and a set of candidate operation types can be generated based on the preset operation types corresponding to one or more target home appliance names.

[0108] For example, if the target household appliance name includes microwave oven and washing machine, and the preset operation types corresponding to microwave oven include turn on, turn off, start, stop, increase speed, decrease speed, and the preset operation types corresponding to washing machine include turn on, turn off, start, stop, adjust speed, and adjust temperature, then the candidate operation type set may include {turn on, turn off, start, stop, increase speed, decrease speed, adjust speed, and adjust temperature}.

[0109] Optionally, a mapping relationship or mapping table between appliance names and preset operation types can be pre-established. After obtaining the target appliance name, the mapping relationship or mapping table can be queried to obtain the preset operation type corresponding to the target appliance name. It should be noted that the above mapping relationship or mapping table can be set according to the actual situation and pre-set in the server's storage space.

[0110] Correspondingly, there can be one or more target home appliance names, and a set of candidate working modes can be generated based on the preset working modes corresponding to one or more target home appliance names.

[0111] For example, if the target household appliance name includes microwave oven and washing machine, the candidate operating modes corresponding to microwave oven include microwave and light wave, and the preset operating modes corresponding to washing machine include bed sheet, underwear, extra wash, mixed wash, and spin dry, then the set of candidate operating modes may include {microwave, light wave, bed sheet, underwear, extra wash, mixed wash, and spin dry}.

[0112] Optionally, a mapping relationship or mapping table between appliance names and preset operating modes can be pre-established. After obtaining the name of the target appliance, the mapping relationship or mapping table can be queried to obtain the preset operating mode corresponding to the target appliance name. It should be noted that the above mapping relationship or mapping table can be set according to the actual situation and pre-set in the server's storage space.

[0113] Therefore, this method can filter out the names of currently online and authorized target home appliances from among the home appliances, generate a set of candidate operation types based on the preset operation types corresponding to the target home appliance names, and generate a set of candidate working modes based on the preset working modes corresponding to the target home appliance names, which helps to improve the success rate of voice control.

[0114] Figure 6 This is a block diagram of a speech recognition device according to an embodiment of the present invention.

[0115] like Figure 6 As shown, the speech recognition device 100 of this embodiment includes: an acquisition module 11, a recognition module 12, and an error correction module 13.

[0116] Module 11 is used to acquire voice information;

[0117] The recognition module 12 is used to recognize speech information and obtain speech recognition results.

[0118] The error correction module 13 is used to perform error correction processing on the speech recognition result based on the number of repetitions of the speech recognition result.

[0119] In one embodiment of the present invention, the error correction module 13 is specifically used to perform error correction processing on the current speech recognition result if there is a second set number of identical speech recognition results in a first set number of consecutive speech recognition results, wherein the second set number of identical speech recognition results does not exceed the first set number of identical speech recognition results.

[0120] In one embodiment of the present invention, the error correction module 13 is specifically used to obtain a set of candidate household appliance names, a set of candidate operation types, and a set of candidate working modes; and to perform error correction processing on the speech recognition result based on the set of candidate household appliance names, the set of candidate operation types, and the set of candidate working modes.

[0121] In one embodiment of the present invention, the error correction module 13 is further configured to match the candidate household appliance name with the highest similarity value that has not yet been matched in the candidate household appliance name set as the household appliance name in the speech recognition result; if the household appliance name matching result is unsuccessful, then the candidate operation type with the highest similarity value that has not yet been matched in the candidate operation type set is matched as the operation type in the speech recognition result; if the operation type matching result is unsuccessful, then the candidate working mode with the highest similarity value that has not yet been matched in the candidate working mode is matched as the working mode in the speech recognition result.

[0122] In one embodiment of the present invention, the error correction module 13 is further configured to generate a first set based on the names of household appliances in the successfully recognized speech recognition results within a previously set time period; generate a second set based on the names of household appliances that the user has actually operated in the current time period; generate a third set based on the names of household appliances whose operation probability exceeds a set threshold in the current time period; generate a fourth set based on the names of household appliances that the user is currently online; and determine the candidate set of household appliance names based on the first set, the second set, the third set, and the fourth set.

[0123] In one embodiment of the present invention, the error correction module 13 is further configured to determine the intersection or union of at least one or at least two of the first set, the second set, the third set and the fourth set as the candidate set of household appliance names.

[0124] In one embodiment of the present invention, the error correction module 13 is further configured to: obtain the name of the user's currently online home appliance; obtain the authorization information corresponding to the name of the currently online home appliance; determine the name of the currently online home appliance that is authorized by the authorization information as the target home appliance name; generate the candidate operation type set according to the preset operation type corresponding to the target home appliance name, and / or generate the candidate operation mode set according to the preset working mode corresponding to the target home appliance name.

[0125] It should be noted that for details not disclosed in the speech recognition device of the present invention, please refer to the details disclosed in the speech recognition method of the above embodiments of the present invention, which will not be repeated here.

[0126] In summary, the speech recognition device of this invention can perform error correction processing on the speech recognition result based on the number of times the speech recognition result is repeated. It can perform error correction processing when the speech recognition result is repeatedly incorrect, thereby improving the accuracy of speech recognition and improving the user experience.

[0127] To achieve the above embodiments, the present invention also proposes a household appliance 200, such as... Figure 7 As shown, it includes the aforementioned voice recognition device 100.

[0128] The household appliance of this invention can perform error correction processing on the speech recognition result based on the number of times the speech recognition result is repeated. It can perform error correction processing when the speech recognition result is repeatedly wrong, thereby improving the accuracy of speech recognition and improving the user experience.

[0129] To implement the above embodiments, the present invention also proposes an electronic device 300, such as... Figure 8 As shown, the electronic device 300 includes a memory 31 and a processor 32. The processor 32 reads executable program code stored in the memory 31 to run a program corresponding to the executable program code, so as to implement the above-mentioned speech recognition method.

[0130] The electronic device of this invention executes a computer program stored in a memory through a processor, which can perform error correction processing on the speech recognition result based on the number of times the speech recognition result is repeated. Error correction processing can be performed when the speech recognition result is repeatedly incorrect, thereby improving the accuracy of speech recognition and improving the user experience.

[0131] To implement the above embodiments, the present invention also proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described speech recognition method.

[0132] The computer-readable storage medium of this invention, by storing a computer program and having it executed by a processor, can perform error correction processing on the speech recognition results based on the number of repetitions of the speech recognition results. It can perform error correction processing when the speech recognition results repeatedly fail, thereby improving the accuracy of speech recognition and enhancing the user experience.

[0133] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0134] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0135] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0136] In this invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "over," and "on top" of the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0137] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0138] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A speech recognition method, characterized in that, include: Obtain voice information; The speech information is recognized to obtain the speech recognition result; The speech recognition result is corrected based on the number of repetitions. The step of correcting the speech recognition results includes: obtaining a set of candidate household appliance names, a set of candidate operation types, and a set of candidate working modes; and performing error correction on the speech recognition results based on the set of candidate household appliance names, the set of candidate operation types, and the set of candidate working modes. The step of performing error correction processing on the speech recognition result based on the candidate set of household appliance names, the candidate set of operation types, and the candidate set of working modes includes: matching the candidate household appliance name with the highest similarity value that has not yet been matched in the candidate set of household appliance names as the household appliance name in the speech recognition result; if the household appliance name matching result is unsuccessful, then matching the candidate operation type with the highest similarity value that has not yet been matched in the candidate set of operation types as the operation type in the speech recognition result; if the operation type matching result is unsuccessful, then matching the candidate working mode with the highest similarity value that has not yet been matched in the candidate working modes as the working mode in the speech recognition result.

2. The speech recognition method according to claim 1, characterized in that, The step of correcting the speech recognition result based on the number of repetitions of the speech recognition result includes: If a second set number of speech recognition results are identical among a first set number of consecutive speech recognition results, then the speech recognition result for this time will be corrected. The second set number of times shall not exceed the first set number of times.

3. The speech recognition method according to claim 1, characterized in that, The process of obtaining the candidate set of household appliance names includes: The first set is generated based on the names of household appliances from the successfully recognized speech recognition results within a previously set time period. A second set is generated based on the names of the home appliances that the user has actually operated in the current time period. A third set is generated based on the names of home appliances whose user operation probability exceeds a set threshold within the current time period. A fourth set is generated based on the names of the user's currently online home appliances; The candidate set of household appliance names is determined based on the first set, the second set, the third set, and the fourth set.

4. The speech recognition method according to claim 3, characterized in that, The step of determining the candidate set of household appliance names based on the first set, the second set, the third set, and the fourth set includes: The intersection or union of at least one or at least two of the first set, the second set, the third set, and the fourth set is determined as the candidate set of household appliance names.

5. The speech recognition method according to claim 1, characterized in that, Obtaining the candidate operation type set and / or the candidate working mode set includes: Get the names of the user's currently online home appliances; Obtain the authorization information corresponding to the name of the currently online home appliance; The authorized information is the name of the currently online home appliance that has been authorized, and it is determined as the name of the target home appliance. The candidate operation type set is generated based on the preset operation type corresponding to the name of the target home appliance, and / or the candidate operation mode set is generated based on the preset operation mode corresponding to the name of the target home appliance.

6. A voice recognition device, characterized in that, include: The acquisition module is used to acquire voice information; The recognition module is used to recognize speech information and obtain speech recognition results; The error correction module is used to perform error correction processing on the speech recognition result based on the number of repetitions of the speech recognition result; The step of correcting the speech recognition results includes: obtaining a set of candidate household appliance names, a set of candidate operation types, and a set of candidate working modes; and performing error correction on the speech recognition results based on the set of candidate household appliance names, the set of candidate operation types, and the set of candidate working modes. The step of performing error correction processing on the speech recognition result based on the candidate set of household appliance names, the candidate set of operation types, and the candidate set of working modes includes: matching the candidate household appliance name with the highest similarity value that has not yet been matched in the candidate set of household appliance names as the household appliance name in the speech recognition result; if the household appliance name matching result is unsuccessful, then matching the candidate operation type with the highest similarity value that has not yet been matched in the candidate set of operation types as the operation type in the speech recognition result; if the operation type matching result is unsuccessful, then matching the candidate working mode with the highest similarity value that has not yet been matched in the candidate working modes as the working mode in the speech recognition result.

7. A household appliance, characterized in that, include: The speech recognition device as described in claim 6.

8. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it implements the speech recognition method as described in any one of claims 1-5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the speech recognition method as described in any one of claims 1-5.

Images