Speech recognition method, device and equipment and computer readable storage medium

Abstract

The embodiment of the invention provides a voice recognition method, device and equipment and a computer readable storage medium. The method comprises the following steps: acquiring a voice instruction; identifying the voice instruction through a preset acoustic model to obtain a corresponding pinyin and a score of the pinyin; judging whether the score of the pinyin is greater than a preset score threshold value or not; if the score of the pinyin is greater than the preset score threshold value, judging whether a text corresponding to the pinyin is found in a cache or not; and if the text corresponding to the pinyin is found in the cache, outputting the text corresponding to the pinyin. In this way, the speech recognition rate can be increased, the recognition efficiency can be improved, and the speech instruction corresponding to the cached pinyin does not need to be re-recognized by calling a decoder, so that the resource consumption can be reduced.

Description

Technical Field

[0001] The present disclosure relates to the field of speech, and in particular to the field of speech recognition technology. Background Art

[0002] Existing speech recognition solutions all use acoustic models to recognize the pinyin of the voice command and the score of the pinyin (such as probability), and then use a decoder to correct the pinyin and score to obtain the final text and score of the voice command, and then output the result. However, no matter what kind of voice command the user enters, it will go through this process before the final sentence can be recognized, which leads to low recognition efficiency and the possibility of repeated recognition problems, thus consuming a lot of resources. Summary of the invention

[0003] The present disclosure provides a speech recognition method, apparatus, device, storage medium and vehicle.

[0004] According to a first aspect of the present disclosure, a speech recognition method is provided. The method comprises:

[0005] Get voice commands;

[0006] Recognize the voice command by using a preset acoustic model to obtain the corresponding pinyin and the score of the pinyin;

[0007] Determine whether the score of the pinyin is greater than a preset score threshold;

[0008] If the score of the pinyin is greater than the preset score threshold, determining whether the text corresponding to the pinyin is found in the cache;

[0009] If the text corresponding to the pinyin is found in the cache, the text corresponding to the pinyin is output.

[0010] According to the above aspects and any possible implementation manner, an implementation manner is further provided, wherein the method further includes:

[0011] If the score of the pinyin is less than or equal to the preset score threshold, or the text corresponding to the pinyin is not found in the cache, calling a preset decoder to correct the pinyin and / or the score of the pinyin, and identifying a final text, wherein the final text is the text corresponding to the pinyin with the highest score;

[0012] The final text is output.

[0013] According to the above aspects and any possible implementation manner, an implementation manner is further provided, wherein the method further includes:

[0014] Count the texts corresponding to the voice commands collected by each vehicle computer;

[0015] Selecting texts with a higher appearance frequency than a preset frequency from the texts corresponding to the voice commands collected by the vehicle computers;

[0016] Determine the pinyin corresponding to the text whose appearance frequency is higher than a preset frequency;

[0017] The text with a frequency of appearance higher than a preset frequency and the pinyin corresponding to the text with a frequency of appearance higher than a preset frequency are stored in the cache correspondingly.

[0018] According to the above aspects and any possible implementation manner, an implementation manner is further provided, wherein the method further includes:

[0019] Count the texts corresponding to the voice commands collected by each vehicle computer;

[0020] Determine the number of occurrences of each text and the total number of occurrences of the texts corresponding to the voice commands collected by each vehicle computer;

[0021] Calculate the ratio of the number of occurrences of each of the texts to the total number of occurrences;

[0022] Calculating the weight of each text according to the proportion of each text;

[0023] Selecting a target text with a weight higher than a preset weight from the texts;

[0024] The target text, the weight of the target text, and the pinyin corresponding to the target text are stored in the cache.

[0025] According to the above aspects and any possible implementation manner, an implementation manner is further provided, wherein the weight of each text is calculated according to the proportion of each text, including:

[0026] Get the corresponding relationship between text proportion and text weight;

[0027] The proportion of each text is matched with the corresponding relationship to determine the weight of each text.

[0028] According to the above aspects and any possible implementation, there is further provided an implementation, wherein the method further comprises: determining the polyphonetic characters in the cache and the pinyin corresponding to the polyphonetic characters;

[0029] Using a preset pronunciation dictionary to determine whether the polyphonetic character and the pinyin corresponding to the polyphonetic character match; wherein the preset pronunciation dictionary records the polyphonetic character and the corresponding correct pinyin;

[0030] If there is no match, the pinyin corresponding to the polyphonetic character is updated to the correct pinyin corresponding to the polyphonetic character recorded in the preset pronunciation dictionary.

[0031] According to the above aspects and any possible implementation manner, an implementation manner is further provided, wherein the method further comprises: determining each text in the cache, the pinyin corresponding to each text, and the weight of each text;

[0032] Using a preset pronunciation dictionary to determine whether the texts and the pinyin corresponding to the texts match, and using the texts corresponding to the voice commands collected by the vehicle computer at different time periods to recalculate the new weights of the texts; wherein the preset pronunciation dictionary records the texts and the corresponding correct pinyin;

[0033] If any text does not match the corresponding pinyin, the pinyin corresponding to the text is updated to the correct pinyin corresponding to the text recorded in the preset pronunciation dictionary;

[0034] If the difference between the new weight of any text and the weight in the cache is greater than a preset threshold, the weight of any text is updated to the new weight.

[0035] According to a second aspect of the present disclosure, a speech recognition device is provided. The device comprises:

[0036] An acquisition module, used to acquire voice commands;

[0037] A recognition module, used to recognize the voice command through a preset acoustic model to obtain the corresponding pinyin and the score of the pinyin;

[0038] A first judging module, used to judge whether the score of the pinyin is greater than a preset score threshold;

[0039] A second judgment module is used to judge whether the text corresponding to the pinyin is found in the cache if the score of the pinyin is greater than the preset score threshold;

[0040] The output module is used to output the text corresponding to the pinyin if the text corresponding to the pinyin is found in the cache.

[0041] According to a third aspect of the present disclosure, an electronic device is provided, which includes a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the program, the method described above is implemented.

[0042] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the method according to the first aspect of the present disclosure is implemented.

[0043] According to a fifth aspect of the present disclosure, a vehicle is provided, the vehicle comprising the speech recognition device as described in the second aspect and / or the electronic device as described in the third aspect.

[0044] In the present disclosure, the voice instruction is recognized through the preset acoustic model, and the pinyin corresponding to the voice instruction and the score of the pinyin can be obtained, and then it is automatically determined whether the score of the pinyin is greater than the preset score threshold. If the score of the pinyin is greater than the preset score threshold, it means that the accuracy rate of the pinyin is very high. Therefore, it can be further determined whether the text corresponding to the pinyin is found in the cache. If the text of the pinyin is found in the cache, the text corresponding to the pinyin can be output. In this way, for the pinyin with a relatively high score, an attempt can be made to directly find the corresponding text in the cache. If it is found, there is no need to call the decoder to obtain the final text. This speeds up the voice recognition rate, which is beneficial to improving the recognition efficiency. There is no need to call the decoder for re-recognition of the voice instruction corresponding to the cached pinyin, which is beneficial to reducing resource consumption.

[0045] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, among which:

[0047] Figure 1 A flow chart of a speech recognition method according to an embodiment of the present disclosure is shown;

[0048] Figure 2 A flowchart of another speech recognition method according to an embodiment of the present disclosure is shown;

[0049] Figure 3A A flow chart of a method for storing text in a cache according to an embodiment of the present disclosure is shown;

[0050] Figure 3B A flowchart of another method for storing text in a cache according to an embodiment of the present disclosure is shown;

[0051] Figure 4 A block diagram of a speech recognition device according to an embodiment of the present disclosure is shown;

[0052] Figure 5 A block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0054] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0055] Figure 1 The flowchart of the speech recognition method 100 according to the embodiment of the present disclosure is shown. The execution subject of the method 100 may be a vehicle computer, and the method may include:

[0056] Step 110, obtaining a voice command;

[0057] Voice commands are sound commands issued by the user.

[0058] Step 120, recognizing the voice command by using a preset acoustic model to obtain corresponding pinyin and a score of the pinyin;

[0059] The acoustic model is one of the most important parts of the speech recognition system. Most mainstream systems use the hidden Markov model for modeling. The acoustic model is used to recognize the voice command to obtain the pinyin and the score of the pinyin of the voice command. The higher the score, the higher the accuracy of the corresponding pinyin. The score is essentially a probability.

[0060] Step 130, determining whether the score of the pinyin is greater than a preset score threshold;

[0061] Step 140, if the score of the pinyin is greater than the preset score threshold, determine whether the text corresponding to the pinyin is found in the cache;

[0062] If the score of a certain pinyin is greater than the preset score threshold, it means that the accuracy rate of the pinyin is very high.

[0063] In an optional embodiment, the pinyin and corresponding text stored in the cache may be pinyin and corresponding text with relatively high usage frequency, and the storage method of high-frequency text may be as follows: count the texts collected by each vehicle computer and the frequency of occurrence of each text, and then select the text with higher frequency of occurrence as the high-frequency text, and confirm the pinyin corresponding to the high-frequency text, and then store the high-frequency text and the pinyin corresponding to the high-frequency text in the cache.

[0064] and / or

[0065] In an optional embodiment, the pinyin and the corresponding text stored in the cache may be the pinyin and the corresponding text that are used more frequently. The storage method of the high-frequency text may be as follows: count the texts collected by each vehicle computer and the number of occurrences of each text, and then assign weights according to the proportion of the number of occurrences of each text to the total number of occurrences of all texts. The larger the proportion, the larger the weight, and the smaller the proportion, the smaller the weight. Then, the text with a large weight is selected as the high-frequency text, and the pinyin corresponding to the high-frequency text is confirmed, and then the high-frequency text and the pinyin corresponding to the high-frequency text are stored in the cache.

[0066] Step 150: If the text corresponding to the pinyin is found in the cache, the text corresponding to the pinyin is output.

[0067] In the present disclosure, the text corresponding to the pinyin is the recognition result corresponding to the voice command. The structure of the pinyin cache is similar to that of the dictionary, and both are one-to-one correspondences. For example, the text corresponding to the pinyin 'wo3 yao2 kan4 dian4 shi4' (the numbers in the pinyin are tones) is 'I want to watch TV', and each pinyin with tone corresponds to a word.

[0068] By recognizing the voice command through the preset acoustic model, the pinyin corresponding to the voice command and the score of the pinyin can be obtained, and then it is automatically determined whether the score of the pinyin is greater than the preset score threshold. If the score of the pinyin is greater than the preset score threshold, it means that the accuracy rate of the pinyin is very high. Therefore, it can be further determined whether the text corresponding to the pinyin is found in the cache. If the text of the pinyin is found in the cache, the text corresponding to the pinyin can be output. In this way, for pinyin with relatively high scores, an attempt can be made to directly find the corresponding text in the cache. If it is found, there is no need to call the decoder to obtain the final text. This speeds up the voice recognition rate, which is beneficial to improving the recognition efficiency. There is no need to call the decoder for re-recognition of the voice command corresponding to the cached pinyin, which is beneficial to reducing resource consumption.

[0069] In some optional embodiments of the present disclosure, if the score of the pinyin is less than or equal to the preset score threshold, or the text corresponding to the pinyin is not found in the cache, the preset decoder is called to correct the pinyin and / or the score of the pinyin, and the final text is identified, wherein the final text is the text corresponding to the pinyin with the highest score; and the final text is output.

[0070] In an optional embodiment of the present disclosure, after the preset decoder is called, the associated or built-in language model can be automatically called, and the pinyin and the score of the pinyin can be corrected by using the language model, and the final text can be generated based on the pinyin.

[0071] Specifically, the acoustic model is trained using sound, and the output is pinyin and the score of the pinyin, while the language model is trained using pinyin, and the output is the final text corresponding to the pinyin. Therefore, after the decoder calls the language model, the language model uses the semantic logic obtained during training to re-recognize the pinyin given by the acoustic model (such as identifying incorrect pinyin and incoherent pinyin), and corrects the score of each pinyin based on the recognition results, and then outputs the text corresponding to the pinyin with the highest score as the final text.

[0072] It can be understood that if the score of the pinyin is less than or equal to the preset score threshold, it means that the pinyin is not accurate and needs to be modified. If the text corresponding to the pinyin is not found in the cache, it means that the text corresponding to the pinyin needs to be re-identified. Therefore, in both cases, it is necessary to call the preset decoder to correct the pinyin and / or the score of the pinyin and identify the final text.

[0073] like Figure 3A As shown, in some optional embodiments of the present disclosure, the method further includes:

[0074] Step A1, counting the texts corresponding to the voice commands collected by each vehicle computer;

[0075] The texts corresponding to the voice commands collected by each vehicle computer during a period of time can be counted online, such as the texts corresponding to the voice commands collected by vehicle computer A, the texts corresponding to the voice commands collected by vehicle computer B, and the texts corresponding to the voice commands collected by vehicle computer C.

[0076] Step A2, selecting texts with a frequency of appearance higher than a preset frequency from the texts corresponding to the voice commands collected by the vehicle computers;

[0077] The text that appears more frequently than the preset frequency is the text with a higher usage frequency, which is the text corresponding to the voices frequently uttered by different users in the vehicle computer.

[0078] Step A3, determining the pinyin corresponding to the text whose appearance frequency is higher than a preset frequency;

[0079] Step A4, storing the text with a frequency higher than a preset frequency and the pinyin corresponding to the text with a frequency higher than a preset frequency in the cache.

[0080] By counting the texts corresponding to the voice commands collected by each vehicle computer, the texts with an appearance frequency higher than a preset frequency can be selected from the texts corresponding to the voice commands collected by each vehicle computer, and then the pinyin corresponding to the texts with an appearance frequency higher than the preset frequency can be determined, and then the texts with an appearance frequency higher than the preset frequency and the pinyin corresponding to the texts with an appearance frequency higher than the preset frequency can be correspondingly stored in the cache. In this way, when the pinyin corresponding to a voice command is recognized again as the pinyin in the cache, the corresponding text can be directly called as the final recognition result.

[0081] like Figure 3B As shown, in some optional embodiments of the present disclosure, the method further includes:

[0082] Step B1, counting the texts corresponding to the voice commands collected by each vehicle computer;

[0083] Step B2, determining the number of occurrences of each text and the total number of occurrences of the texts corresponding to the voice commands collected by each vehicle computer;

[0084] The number of occurrences of each text is the number of occurrences of each text in the texts corresponding to the voice commands collected by all vehicle computers, and the total number of occurrences of the texts corresponding to the voice commands collected by each vehicle computer is the total number of occurrences of the texts corresponding to the voice commands collected by all vehicle computers.

[0085] Step B3, calculating the ratio of the number of occurrences of each of the texts to the total number of occurrences;

[0086] The proportion of each text is the quotient of the number of occurrences of each text and the total number of occurrences.

[0087] Step B4, calculating the weight of each text according to the proportion of each text; different proportions correspond to different weights.

[0088] Step B5, selecting a target text having a weight higher than a preset weight from the texts;

[0089] Step B6, storing the target text, the weight of the target text and the pinyin corresponding to the target text in the cache.

[0090] For example, you can count the sentences that users use frequently online. For example, if the command text "I want to listen to songs" appears frequently in the online recognition results, then add the pinyin, text and weight of "I want to listen to songs" to the pinyin cache. At the same time, the proportion is calculated based on the number of occurrences and all sentences, and the weight is assigned. The structure is as follows:

[0091] wo3 yao4 ting1 ge1 I want to listen to music 0.56 (weight).

[0092] By counting the texts corresponding to the voice commands collected by each vehicle computer, the proportion of each text can be calculated, and then the weight of each text can be automatically calculated based on the proportion of each text, so as to select a target text with a weight higher than a preset weight from each text, and then the target text, the weight of the target text and the pinyin corresponding to the target text are stored in the cache. In this way, the text with a high weight and the corresponding pinyin can be stored in the cache. In this way, when the pinyin corresponding to a voice command is recognized as the pinyin in the cache again, the corresponding text can be directly called as the final recognition result.

[0093] In some embodiments, the step of calculating the weight of each text according to the proportion of each text includes:

[0094] Get the corresponding relationship between text proportion and text weight;

[0095] The proportion of each text is matched with the corresponding relationship to determine the weight of each text.

[0096] Different file proportions may correspond to different text weights. For example, the higher the proportion, the higher the weight. Therefore, there is a corresponding relationship between the text proportion and the text weight. In this way, the weight of each text can be automatically determined by matching the proportion of each text with the corresponding relationship.

[0097] In some embodiments, determining the polyphonetic characters in the cache and the pinyin corresponding to the polyphonetic characters;

[0098] Using a preset pronunciation dictionary to determine whether the polyphonetic character and the pinyin corresponding to the polyphonetic character match; wherein the preset pronunciation dictionary records the polyphonetic character and the corresponding correct pinyin;

[0099] The method for determining whether there is a match can be: searching for the correct pinyin corresponding to the polyphonetic character in a preset pronunciation dictionary, and then determining whether the pinyin corresponding to the polyphonetic character is consistent with the correct pinyin. If they are consistent, it means that the polyphonetic character and the pinyin corresponding to the polyphonetic character match.

[0100] If there is no match, the pinyin corresponding to the polyphonetic character is updated to the correct pinyin corresponding to the polyphonetic character recorded in the preset pronunciation dictionary.

[0101] Since the preset pronunciation dictionary records each polyphone and the correct pinyin corresponding to each polyphone, the preset pronunciation dictionary can be used to automatically determine whether the polyphone and the pinyin corresponding to the polyphone match. If they do not match, it means that the pinyin corresponding to the polyphone is not accurate. Therefore, the pinyin corresponding to the polyphone can be automatically updated to the correct pinyin corresponding to the polyphone recorded in the preset pronunciation dictionary. In this way, the correctness of the pinyin corresponding to the polyphone can be ensured.

[0102] In some embodiments, determining each text in the cache, the pinyin corresponding to each text, and the weight of each text;

[0103] Using a preset pronunciation dictionary to determine whether the texts and the pinyin corresponding to the texts match, and using the texts corresponding to the voice commands collected by the vehicle computer at different time periods to recalculate the new weights of the texts; wherein the preset pronunciation dictionary records the texts and the corresponding correct pinyin;

[0104] The new weights of the texts corresponding to the voice commands collected by the vehicle computer at different time periods are recalculated:

[0105] If the weight of each text in the cache is the text corresponding to the voice command collected by the car computer in time period A, the new weight can be calculated using the text corresponding to the voice command collected by the car computer in time period B. The method for calculating the new weight is the same as the method for calculating the weight of each text in the cache.

[0106] If any text does not match the corresponding pinyin, the pinyin corresponding to the text is updated to the correct pinyin corresponding to the text recorded in the preset pronunciation dictionary;

[0107] If the difference between the new weight of any text and the weight in the cache is greater than a preset threshold, the weight of any text is updated to the new weight.

[0108] Since the preset pronunciation dictionary records each text and the pinyin corresponding to each text, the preset pronunciation dictionary can be used to automatically determine whether each text and the pinyin corresponding to each text match. If any text and the corresponding pinyin do not match, it means that the text and the corresponding pinyin are not accurate. Therefore, the text and the corresponding pinyin can be automatically updated to any text and the corresponding correct pinyin recorded in the preset pronunciation dictionary. In this way, the correctness of the pinyin corresponding to each text can be ensured. At the same time, the text corresponding to the voice command collected by the vehicle computer in different time periods can be used to recalculate the new weight of each text. If the difference between the new weight of any text and the weight in the cache is greater than the preset threshold, it means that the difference between the new weight of any text and the weight in the cache is too large. Therefore, the weight of any text can be automatically updated to the new weight to ensure the correctness of the weight of any text.

[0109] The following will be combined Figure 2 The technical solution of the present disclosure is further described in detail:

[0110] The overall structure of the present disclosure adds a pinyin cache mechanism based on the existing acoustic model, language model and decoder, as follows Figure 2 As shown, when audio is input into the recognition system, the acoustic model first outputs the pinyin result and score of the audio recognition. When the score exceeds a certain threshold and the corresponding text result is found in the pinyin cache, the decoder and language model calculations are skipped and the recognition result is output directly.

[0111] The structure of the pinyin cache is similar to that of the dictionary, and both are one-to-one correspondences. For example, the text corresponding to 'wo3 yao2 kan4dian4shi4' is 'I want to watch TV', and each pinyin with tone corresponds to a character.

[0112] We count the sentences that users use frequently online. For example, if the command sentence "I want to listen to songs" appears frequently in the online recognition results, we will add the pinyin and text of "I want to listen to songs" to the pinyin cache. At the same time, we will calculate the proportion based on the number of occurrences and all sentences, and assign weights. For example, the following is the structure:

[0113] wo3 yao4 ting1 ge1 I want to listen to music 0.56

[0114] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present disclosure is not limited by the order of the actions described, because according to the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present disclosure.

[0115] The above is an introduction to the method embodiment. The following is a further explanation of the scheme disclosed in the present invention through an apparatus embodiment.

[0116] Figure 4 FIG. 3 shows a block diagram of a speech recognition device 300 according to an embodiment of the present disclosure. As shown in FIG. 3 , the device 300 includes:

[0117] An acquisition module 410 is used to acquire a voice command;

[0118] The recognition module 420 is used to recognize the voice instruction through a preset acoustic model to obtain the corresponding pinyin and the score of the pinyin;

[0119] A first judging module 430 is used to judge whether the score of the pinyin is greater than a preset score threshold;

[0120] The second judgment module 440 is used to judge whether the text corresponding to the pinyin is found in the cache if the score of the pinyin is greater than the preset score threshold;

[0121] The output module 450 is used to output the text corresponding to the pinyin if the text corresponding to the pinyin is found in the cache.

[0122] According to the above aspects and any possible implementation manner, there is further provided an implementation manner, wherein the apparatus further includes:

[0123] A first processing module is used for calling a preset decoder to correct the pinyin and / or the score of the pinyin if the score of the pinyin is less than or equal to the preset score threshold, or the text corresponding to the pinyin is not found in the cache, and identifying a final text, wherein the final text is the text corresponding to the pinyin with the highest score;

[0124] An output module is used to output the final text.

[0125] According to the above aspects and any possible implementation manner, there is further provided an implementation manner, wherein the apparatus further includes:

[0126] The first statistical module is used to count the texts corresponding to the voice commands collected by each vehicle computer;

[0127] A first selection module, used to select texts with a frequency of appearance higher than a preset frequency from the texts corresponding to the voice commands collected by the vehicle computers;

[0128] A first determination module, used to determine the pinyin corresponding to the text with a frequency of occurrence higher than a preset frequency;

[0129] The first storage module is used to store the text with a frequency of appearance higher than a preset frequency and the pinyin corresponding to the text with a frequency of appearance higher than the preset frequency in the cache.

[0130] According to the above aspects and any possible implementation manner, there is further provided an implementation manner, wherein the apparatus further includes:

[0131] The second statistical module is used to count the texts corresponding to the voice commands collected by each vehicle computer;

[0132] A second determination module is used to determine the number of occurrences of each text and the total number of occurrences of the texts corresponding to the voice commands collected by the vehicle computers;

[0133] A first calculation module, used to calculate the ratio of the number of occurrences of each of the texts to the total number of occurrences;

[0134] A second calculation module, used for calculating the weight of each text according to the proportion of each text;

[0135] A second selection module is used to select a target text with a higher weight than a preset weight from the texts;

[0136] The second storage module is used to store the target text, the weight of the target text and the pinyin corresponding to the target text in the cache.

[0137] According to the above aspect and any possible implementation manner, an implementation manner is further provided, wherein the second calculation module is specifically configured to:

[0138] Get the corresponding relationship between text proportion and text weight;

[0139] The proportion of each text is matched with the corresponding relationship to determine the weight of each text.

[0140] According to the above aspects and any possible implementation manner, there is further provided an implementation manner, wherein the apparatus further includes:

[0141] A third determination module is used to determine the polyphonetic characters in the cache and the pinyin corresponding to the polyphonetic characters;

[0142] A judgment module, used for judging whether the polyphonetic character and the pinyin corresponding to the polyphonetic character match by using a preset pronunciation dictionary; wherein the preset pronunciation dictionary records the polyphonetic character and the corresponding correct pinyin;

[0143] The first updating module is used to update the pinyin corresponding to the polyphonetic character to the correct pinyin corresponding to the polyphonetic character recorded in the preset pronunciation dictionary if there is no match.

[0144] According to the above aspects and any possible implementation manner, there is further provided an implementation manner, wherein the apparatus further includes:

[0145] A fourth determination module, used to determine each text in the cache, the pinyin corresponding to each text, and the weight of each text;

[0146] The second processing module is used to use a preset pronunciation dictionary to determine whether the texts and the pinyin corresponding to the texts match, and to recalculate the new weights of the texts using the texts corresponding to the voice commands collected by the vehicle computer at different time periods; wherein the preset pronunciation dictionary records the texts and the corresponding correct pinyin;

[0147] A second updating module is used for updating the pinyin corresponding to any text to the correct pinyin corresponding to any text recorded in the preset pronunciation dictionary if any text does not match the corresponding pinyin;

[0148] The third updating module is used to update the weight of any text to the new weight if the difference between the new weight of any text and the weight in the cache is greater than a preset threshold.

[0149] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0150] According to an embodiment of the present disclosure, the present disclosure further provides an electronic device, including:

[0151] at least one processor; and

[0152] a memory communicatively connected to the at least one processor; wherein,

[0153] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform any one of the above method embodiments.

[0154] According to an embodiment of the present disclosure, the present disclosure further provides a vehicle, comprising: the speech recognition device as described in the above embodiment or the electronic device as described in the above embodiment.

[0155] According to an embodiment of the present disclosure, the present disclosure further provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute any one of the above method embodiments.

[0156] Figure 5A schematic block diagram of an electronic device 500 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0157] The device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 505.

[0158] A number of components in the device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0159] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 501 performs the various methods and processes described above, such as method 100. For example, in some embodiments, the method 100 may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the method 100 described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the method 100 in any other appropriate manner (e.g., by means of firmware).

[0160] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0161] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0162] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0163] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0164] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0165] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0166] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0167] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A speech recognition method, characterized in that: include: Get voice commands; Recognize the voice command by using a preset acoustic model to obtain the corresponding pinyin and the score of the pinyin; Determine whether the score of the pinyin is greater than a preset score threshold; If the score of the pinyin is greater than the preset score threshold, determining whether the text corresponding to the pinyin is found in the cache; If the text corresponding to the pinyin is found in the cache, the text corresponding to the pinyin is output.

2. The method according to claim 1, characterized in that The method further comprises: If the score of the pinyin is less than or equal to the preset score threshold, or the text corresponding to the pinyin is not found in the cache, calling a preset decoder to correct the pinyin and / or the score of the pinyin, and identifying a final text, wherein the final text is the text corresponding to the pinyin with the highest score; The final text is output.

3. The method according to claim 1, characterized in that The method further comprises: Count the texts corresponding to the voice commands collected by each vehicle computer; Selecting texts with a higher appearance frequency than a preset frequency from the texts corresponding to the voice commands collected by the vehicle computers; Determine the pinyin corresponding to the text whose appearance frequency is higher than a preset frequency; The text with a frequency of appearance higher than a preset frequency and the pinyin corresponding to the text with a frequency of appearance higher than a preset frequency are stored in the cache correspondingly.

4. The method according to claim 1, characterized in that The method further comprises: Count the texts corresponding to the voice commands collected by each vehicle computer; Determine the number of occurrences of each text and the total number of occurrences of the texts corresponding to the voice commands collected by each vehicle computer; Calculate the ratio of the number of occurrences of each of the texts to the total number of occurrences; Calculate the weight of each text according to the proportion of each text; Selecting a target text with a weight higher than a preset weight from the texts; The target text, the weight of the target text, and the pinyin corresponding to the target text are stored in the cache.

5. The method according to claim 4, characterized in that Calculating the weight of each text according to the proportion of each text includes: Get the corresponding relationship between text proportion and text weight; The proportion of each text is matched with the corresponding relationship to determine the weight of each text.

6. The method according to claim 1, characterized in that The method further comprises: Determine the polyphonetic characters in the cache and the pinyin corresponding to the polyphonetic characters; Using a preset pronunciation dictionary to determine whether the polyphonetic character and the pinyin corresponding to the polyphonetic character match; wherein the preset pronunciation dictionary records the polyphonetic character and the corresponding correct pinyin; If there is no match, the pinyin corresponding to the polyphonetic character is updated to the correct pinyin corresponding to the polyphonetic character recorded in the preset pronunciation dictionary.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: Determine each text in the cache, the pinyin corresponding to each text, and the weight of each text; Using a preset pronunciation dictionary to determine whether the texts and the pinyin corresponding to the texts match, and using the texts corresponding to the voice commands collected by the vehicle computer at different time periods to recalculate the new weights of the texts; wherein the preset pronunciation dictionary records the texts and the corresponding correct pinyin; If any text does not match the corresponding pinyin, the pinyin corresponding to the text is updated to the correct pinyin corresponding to the text recorded in the preset pronunciation dictionary; If the difference between the new weight of any text and the weight in the cache is greater than a preset threshold, the weight of any text is updated to the new weight.

8. A speech recognition device, characterized in that: include: An acquisition module, used to acquire voice commands; A recognition module, used to recognize the voice command through a preset acoustic model to obtain the corresponding pinyin and the score of the pinyin; A first judging module, used to judge whether the score of the pinyin is greater than a preset score threshold; A second judgment module is used to judge whether the text corresponding to the pinyin is found in the cache if the score of the pinyin is greater than the preset score threshold; The output module is used to output the text corresponding to the pinyin if the text corresponding to the pinyin is found in the cache.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-7.

11. A vehicle, characterized in that: include: The apparatus as claimed in claim 8, and / or the electronic device as claimed in claim 9, and / or the readable storage medium as claimed in claim 10.

Images