Speech recognition method, device and equipment, vehicle and medium

The speech recognition method enhances navigation accuracy by combining acoustic and language scores with personalized hot words, addressing the challenge of similar pronunciations in voice navigation systems.

CN119068869AActive Publication Date: 2024-12-03BEIJING CO WHEELS TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202310639750.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-31
Publication Date
2024-12-03
Estimated Expiration
2043-05-31

AI Technical Summary

Technical Problem

Existing voice navigation systems struggle to accurately recognize navigation points of interest due to similar pronunciations caused by accents, leading to low recognition accuracy.

Method used

A speech recognition method that combines acoustic and language scores with personalized hot word scores to enhance recognition accuracy, using a client's historical navigation data to identify target hot words and determine the final recognition result.

Benefits of technology

Improves recognition accuracy by accounting for personalized search habits, effectively distinguishing between similar sounding navigation points despite accent variations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119068869A_ABST
    Figure CN119068869A_ABST
Patent Text Reader

Abstract

The embodiment of the invention relates to a voice recognition method, device and equipment, a vehicle and a medium. The method comprises the following steps: performing voice recognition on voice navigation information to obtain at least one candidate recognition result; determining an acoustic score of each candidate recognition result, and determining a language score of each candidate recognition result; identifying a target hot word contained in each candidate identification result according to a preset hot word library, and obtaining a predetermined target hot word score of the target hot word; and determining a reference score of each candidate recognition result according to the acoustic score, the language score and the target hot word score, and determining a target recognition result according to the reference scores. In the embodiment of the invention, the hot words of the client are introduced to determine the final recognition result on the basis of the voice recognition result in combination with language and acoustics, and the hot words of the client reflect personalized search habits and the like, so that the influence of approximate voices can be removed, and the accuracy of the recognition result is further improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence, and in particular to a speech recognition method, device, equipment, vehicle and medium. Background Art

[0002] Voice recognition technologies such as voice navigation commands account for a very high proportion of in-vehicle voice interactions. The accuracy of navigation point of interest (POI) recognition in voice navigation command recognition has a crucial impact on the success rate of voice navigation initiation.

[0003] In the related technology, a correspondence between regions and language recognition models is set. The language recognition model can be used to distinguish between voices with similar pronunciations due to accents in the corresponding region and other regions. The region to which the client belongs is determined based on the longitude and latitude of the initiating voice navigation, and the language recognition model of the region is determined based on the above correspondence. Navigation points are identified based on the language recognition model of the region.

[0004] However, the above-mentioned related technologies can only distinguish between the corresponding area and other areas with similar pronunciations due to accent problems. When the voice navigation instructions contain similar sounds, it is impossible to accurately recognize the results. For example, for an area including the two locations "Yindu Building" and "Yingdu Building", when the voice navigation instructions contain "yindudasha", it is obviously impossible to accurately recognize it. Summary of the invention

[0005] In order to solve the above technical problems or at least partially solve the above technical problems, the present disclosure provides a speech recognition method, device, equipment, vehicle and medium to solve the technical problem in the prior art that the recognition results cannot remove the influence of similar sounds, resulting in low recognition accuracy.

[0006] The embodiment of the present disclosure provides a speech recognition method, the method comprising: in response to receiving speech navigation information from a client, performing speech recognition on the speech navigation information to obtain at least one candidate recognition result; determining an acoustic score for each of the candidate recognition results, and determining a language score for each of the candidate recognition results; identifying a target hot word contained in each of the candidate recognition results according to a preset hot word library of the client, and obtaining a target hot word score of the predetermined target hot word, wherein the target hot word score is determined according to the total number of times the target hot word is added to the preset hot word library; determining a reference score for each of the candidate recognition results according to the acoustic score, the language score and the target hot word score; and determining a target recognition result from the at least one candidate recognition result according to the reference score.

[0007] The embodiment of the present disclosure also provides a speech recognition device, which includes: a recognition module, which is used to respond to the voice navigation information received from the client, and perform speech recognition on the voice navigation information to obtain at least one candidate recognition result; a first determination module, which is used to determine the acoustic score of each of the candidate recognition results; a second determination module, which is used to determine the language score of each of the candidate recognition results; an acquisition module, which is used to identify the target hot word contained in each of the candidate recognition results according to the preset hot word library of the client, and obtain the target hot word score of the predetermined target hot word, wherein the target hot word score is determined according to the total number of times the target hot word is added to the preset hot word library; a third determination module, which is used to determine the reference score of each of the candidate recognition results according to the acoustic score, the language score and the target hot word score; and a fourth determination module, which is used to determine the target recognition result in the at least one candidate recognition result according to the reference score.

[0008] An embodiment of the present disclosure also provides an electronic device, which includes: a processor; a memory for storing processor executable instructions; and a processor for reading executable instructions from the memory and executing the instructions to implement a speech recognition method as provided in an embodiment of the present disclosure.

[0009] The embodiments of the present disclosure also provide a vehicle, which includes the voice recognition device in the above embodiments, or the electronic device in the above embodiments.

[0010] The embodiment of the present disclosure further provides a computer-readable storage medium, which stores a computer program, and the computer program is used to execute the speech recognition method provided by the embodiment of the present disclosure.

[0011] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0012] The speech recognition scheme provided by the embodiment of the present disclosure responds to the voice navigation information received from the client, performs speech recognition on the voice navigation information to obtain at least one candidate recognition result, determines the acoustic score of each candidate recognition result, and determines the language score of each candidate recognition result, and then identifies the target hot words contained in each candidate recognition result according to the preset hot word library of the client, and obtains the target hot word score of the predetermined target hot word, wherein the target hot word score is determined according to the total number of times the target hot word is added to the preset hot word library of the client, and determines the reference score of each candidate recognition result according to the acoustic score, the language score and the target hot word score, and determines the target recognition result in at least one candidate recognition result according to the reference score. In the present technical scheme, on the basis of combining language and acoustics for speech recognition results, the hot words of the client are introduced to determine the final recognition results. Since the hot words of the client reflect personalized search habits, etc., the influence of similar sounds can be removed, and the accuracy of the recognition results can be further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] 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. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0014] Figure 1 A flowchart of a speech recognition method provided by an embodiment of the present disclosure;

[0015] Figure 2 A schematic diagram of a speech recognition function module provided by an embodiment of the present disclosure;

[0016] Figure 3 A schematic diagram of a word segmentation node structure corresponding to a word segmentation language score provided in an embodiment of the present disclosure;

[0017] Figure 4 A schematic diagram of the structure of a speech recognition device provided by an embodiment of the present disclosure;

[0018] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0019] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0020] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0021] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0022] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0023] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0024] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0025] In order to solve the above problems, the embodiments of the present disclosure provide a speech recognition method, in which acoustics and language are combined to determine the target recognition result, and the recognition accuracy is preliminarily guaranteed. Among them, acoustics refers to the physical quantity that represents the acoustic characteristics of speech, and is also a general term for the acoustic performance of various sound elements, such as the energy concentration area, resonance peak frequency, resonance peak intensity and bandwidth that represent the timbre, and the duration, fundamental frequency, average voice power, etc. that represent the rhythmic characteristics of speech. Language reflects the word-forming characteristics of speech, etc. In the speech recognition method, the client's hot words are also introduced to determine the final recognition results. Since the client's hot words reflect the client's personalized search habits, recognition enhancement can be performed. For example, it is ensured that the recognition results in the navigation voice instructions can be accurately recognized even in the presence of similar sounds and accents.

[0026] The method is introduced below in conjunction with specific embodiments.

[0027] Figure 1The present invention provides a flow chart of a speech recognition method provided in an embodiment of the present invention. The method can be performed by a speech recognition device, wherein the device can be implemented by software and / or hardware and can generally be integrated in an electronic device. Figure 1 As shown, the method includes:

[0028] Step 101, in response to receiving voice navigation information from a client, performing voice recognition on the voice navigation information to obtain at least one candidate recognition result.

[0029] Among them, in different application scenarios, the way of receiving voice navigation information is different. In some possible embodiments, voice navigation information input through a vehicle-mounted microphone can be received.

[0030] In one embodiment of the present disclosure, in response to receiving voice navigation information from a client, voice recognition is performed on the voice navigation information to obtain at least one candidate recognition result, and the candidate recognition result can be considered to include a recognition result of a navigation location, wherein at least one candidate recognition result can include near-phonetic words, words with similar accents, etc. For example, when the candidate voice navigation information includes "yingdudasha", at least one candidate recognition result can include "Yindu Building" and "Yingdu Building".

[0031] It should be noted that in different application scenarios, the manner of performing speech recognition on the voice navigation information to obtain at least one candidate recognition result is different, and examples are described as follows:

[0032] In some possible examples, voice recognition can be performed on the navigation voice information, and a preset voice table can be queried, which contains recognition results and voices corresponding to the recognition results, and the recognition results whose matching degree with the voices in the preset voice table is greater than a preset matching degree threshold are determined as candidate recognition results.

[0033] Step 102: determine the acoustic score of each candidate recognition result, and determine the language score of each candidate recognition result.

[0034] It is easy to understand that the language score can determine the correlation between characters of the candidate recognition results based on language perspectives such as word formation, and the acoustic score can determine the confidence of the candidate recognition results from acoustic perspectives such as syllables.

[0035] In an embodiment of the present disclosure, the acoustic score and language score of each candidate recognition result are determined, so that the corresponding target recognition result can be determined by combining the acoustic score and the language score. Thus, the target recognition result is determined by combining the acoustic characteristics and the language characteristics, thereby ensuring the accuracy of the target recognition result.

[0036] It should be noted that in different application scenarios, the method of determining the acoustic score of each candidate recognition result is different, and the examples are as follows:

[0037] In some possible embodiments, candidate acoustic feature information of each candidate recognition result may be extracted. The candidate acoustic feature information may be any information representing the candidate recognition result in the acoustic dimension, and the acoustic feature information is matched with a plurality of preset standard acoustic feature information, and the standard acoustic feature information with the highest matching degree is determined as the target standard acoustic feature information that is successfully matched, and then the preset acoustic score corresponding to the target standard acoustic feature information is determined as the acoustic score of each candidate recognition result.

[0038] In some possible embodiments, Figure 2 As shown, the candidate recognition results can be input into a pre-trained acoustic model, and the acoustic model can calculate the acoustic scores of the candidate recognition results.

[0039] Similarly, in different application scenarios, the language score of each candidate recognition result is determined differently:

[0040] In some possible embodiments, at least one candidate word segmentation corresponding to each candidate recognition result is identified. For example, the candidate recognition result can be matched with a preset word segmentation vocabulary, and at least one corresponding candidate word segmentation is determined based on the matching result. The word segmentation language score of each candidate word segmentation is determined. For example, each word segmentation in the preset word segmentation vocabulary is set with a corresponding word segmentation language score, and the word segmentation language score of each candidate word segmentation can be determined based on the preset word segmentation language score.

[0041] For another example, a word segmentation node graph is pre-set, and the word segmentation node graph includes multiple word segmentation nodes connected by node edges, each connected word segmentation node has a corresponding word segmentation language score, and the word segmentation language score is the confidence score of the corresponding word segmentation, etc. The word segmentation language score can be obtained based on experimental data, for example, Figure 3 As shown, when the word segmentation node graph includes a, b, c, d, e, f, and g, a and b are connected by node edge L1, b and c are connected by node edge L2, b and d are connected by node edge L3, d and e are connected by node edge L4, a and f are connected by node edge L5, and f and g are connected by node edge L6. The word segmentations a, b, c, d, e, f, and g have corresponding pre-set word segmentation language scores q1, q2, q3, q4, q5, q6, and q7. In this embodiment, the word segmentation language score of each candidate word segmentation is obtained by querying the word segmentation language score contained in the word segmentation node graph.

[0042] Furthermore, after determining the word segmentation language score of each candidate word segmentation, the sum of the word segmentation language scores corresponding to at least one candidate word segmentation is calculated to determine the language score of each candidate recognition result.

[0043] In some possible embodiments, continue to refer to Figure 2 , the candidate recognition results can also be input into a pre-trained language model, and the language model can calculate the language score of the candidate recognition results.

[0044] Step 103, identifying the target hot word contained in each candidate recognition result according to the preset hot word library of the client, and obtaining the target hot word score of the predetermined target hot word, wherein the target hot word score is determined according to the total number of times the target hot word is added to the preset hot word library.

[0045] Among them, the preset hot word library of the client contains multiple candidate hot words, and each candidate hot word can be understood as a navigation location that the client uses more frequently, etc. Therefore, even if there are two candidate recognition results with similar pronunciations, denoising can be performed based on the preset hot word library to avoid errors caused by similar sounds. For example, when the candidate voice navigation information contains "yingdudasha", at least one candidate recognition result may include "Yindu Building" and "Yingdu Building". However, if "Yindu Building" belongs to the preset hot word library, the target hot word score corresponding to "Yindu Building" will enhance its subsequent reference score, making it easier to distinguish it from "Yingdu Building".

[0046] It should be noted that in different application scenarios, the methods for obtaining the client's preset hot word library are different. The examples are as follows:

[0047] In some possible embodiments, the historical navigation locations of the client can be obtained, and the historical navigation locations can be all the historical navigation locations on the navigation platform within a recent preset time period, etc., and historical search parameters of the historical navigation locations can be obtained, and the historical navigation locations corresponding to the historical search parameters that meet the preset hot word search conditions are determined as candidate hot words, and a preset hot word library of the client is generated based on all the candidate hot words.

[0048] In different application scenarios, the above historical search parameters are different, and the corresponding preset hot word search conditions are different. In some possible embodiments, the historical search parameters include the number of historical navigations. When the number of historical navigations is greater than a preset number threshold, it is determined that the corresponding historical search parameters meet the preset hot word search conditions, that is, the navigation locations that are more frequently used by the client are taken as candidate hot words.

[0049] In some possible embodiments, the historical search parameters include an input method for historical navigation locations. When the input method is a preset input method, it is determined that the historical search parameters meet the preset hot word search conditions. It can be understood that the above-mentioned preset input method is an input method that can accurately reflect the search intention of the client, and the historical navigation locations input by the preset input method have a higher accuracy rate than the historical navigation locations input by voice.

[0050] For example, when the historical navigation location input according to the voice navigation instruction entered by the client is inaccurate, the accurate historical navigation location is usually input on the client through other input methods, for example, by calling the keyboard to input the accurate historical navigation location, or by selecting the accurate historical navigation location on the map, etc. Therefore, in this embodiment, the preset input method can be a keyboard input method or a map selection input method, etc.

[0051] In some possible embodiments, when the client authorization is obtained, the address book locations in the address book on the client can also be read, and the read address book locations can also be added to the hot word library as candidate hot words.

[0052] In the actual execution process, the hot word score of each candidate hot word in the hot word library is also determined in advance.

[0053] In one embodiment of the present disclosure, a preset language model may also be pre-trained, and the training sample data of the language model may be obtained by training using navigation locations input by other clients belonging to the same region as the client. In the present embodiment, for candidate hot words added to the hot word library for the first time, they are input into the corresponding preset language model to obtain the hot word score of each candidate hot word. For candidate hot words that are not added to the hot word library for the first time, in order to enhance the recognition of the hot words, the hot word weight value of the candidate hot words that are not added to the hot word library for the first time is determined, and the hot word score of the candidate hot words corresponding to the adding operation is updated according to the hot word weight value.

[0054] Among them, in some possible implementations, the above-mentioned hot word weight value is used to determine the hot word weight of each candidate hot word based on the total number of times each candidate hot word is added to the hot word library, wherein the higher the total number, the higher the corresponding hot word weight, thereby further enhancing the weight of the more commonly used candidate hot words, and updating the reference hot word score of the corresponding candidate hot word according to the hot word weight, wherein the third product value of the hot word weight and the current hot word score of the corresponding candidate hot word can be calculated, and the hot word score of the corresponding candidate hot word is updated according to the third product value, etc.

[0055] In the actual execution process, a unit weight increase value may be preset. Each time a candidate hot word is detected and not added to the preset hot word library for the first time, the preset unit weight increase value is used as the hot word weight, and the hot word score of the corresponding candidate hot word is updated in real time according to the preset unit weight increase value. That is, the third product value of the preset unit weight increase value and the current hot word score is calculated, and the hot word score of the corresponding candidate hot word is updated according to the third product value. The preset unit weight increase value can be set according to the needs of the scene, and is not limited here.

[0056] In one embodiment of the present disclosure, after the hot word library is obtained, the target hot word included in each candidate recognition result is obtained according to the preset hot word library, and the hot word score of the predetermined target hot word is obtained.

[0057] Step 104 , determining a reference score for each candidate recognition result according to the acoustic score, the language score, and the target hot word score.

[0058] In one embodiment of the present disclosure, the reference score of each candidate recognition result is determined based on the acoustic score, language score and target hot word score, that is, the acoustic characteristics, language characteristics and historical search personalized preferences of the candidate recognition result are comprehensively considered to ensure the accuracy of the final recognition result.

[0059] It should be noted that in different application scenarios, the reference score of each candidate recognition result is determined in different ways according to the acoustic score, language score and target hot word score. The examples are as follows:

[0060] In some possible examples, the acoustic score is normalized to obtain a first normalized value, a first product value of the language score and a preset first weight value is calculated, wherein the preset first weight value can be calibrated according to experimental data, the first product value is normalized to obtain a second normalized value, a second product value of the preset second weight value and the target hot word score is calculated, and the second product value is normalized to obtain a third normalized value, wherein the normalization processing method in this example can be any normalization processing method in the prior art, which are not listed here one by one, and then, the first normalized value, the second normalized value and the third normalized value are summed to obtain a reference score for each candidate recognition result.

[0061] That is, in this embodiment, the first reference score can be obtained by using the following formula (1), where Score(y) in formula (1) is the reference score, logP(y|x) is the first normalized value, where x is the voice navigation information, y is the candidate recognition result, and logP L (y) is the language score, where L is the language model, λ is the first weight value, γ is the second weight value, logP c (y) is the target hot word score, γlogP c (y) is the third normalized value:

[0062] Score(y)=logP(y|x)+λlogP L (y)+γlogP c (y)Formula (1)

[0063] In some possible examples, the acoustic score, the language score, and the target hot word score may be normalized respectively to obtain three normalized values, and the three normalized values ​​may be summed to obtain a reference score.

[0064] Step 105: Determine a target recognition result from at least one candidate recognition result according to the reference score.

[0065] In one embodiment of the present disclosure, the candidate recognition result corresponding to the maximum value among all reference scores is determined as the target recognition result, thereby continuing to refer to Figure 2 In the embodiments of the present disclosure, based on the recognition of speech recognition results by combining language and acoustics, the target recognition results are further determined by combining a preset hot word library that reflects the personalized search habits of the client, thereby removing the influence of similar sounds and improving the recognition accuracy of the target recognition results.

[0066] In summary, the speech recognition method provided by the embodiment of the present disclosure responds to the voice navigation information received from the client, performs speech recognition on the voice navigation information to obtain at least one candidate recognition result, determines the acoustic score of each candidate recognition result, and determines the language score of each candidate recognition result, and then identifies the target hot words contained in each candidate recognition result according to the preset hot word library of the client, and obtains the target hot word score of the predetermined target hot word, wherein the target hot word score is determined according to the total number of times the target hot word is added to the preset hot word library of the client, and the reference score of each candidate recognition result is determined according to the acoustic score, the language score and the target hot word score, and the target recognition result is determined in at least one candidate recognition result according to the reference score. In the present technical solution, on the basis of combining language and acoustics for speech recognition results, the hot words of the client are introduced to determine the final recognition results. Since the hot words of the client reflect personalized search habits, etc., the influence of similar sounds can be removed, and the accuracy of the recognition results can be further improved.

[0067] In order to implement the above embodiment, the present disclosure also proposes a speech recognition device.

[0068] Figure 4 This is a schematic diagram of the structure of a speech recognition device provided by an embodiment of the present disclosure. The device can be implemented by software and / or hardware and can generally be integrated into an electronic device for speech recognition. Figure 4 As shown, the device includes: an identification module 410, a first determination module 420, a second determination module 430, an acquisition module 440, a third determination module 450 and a fourth determination module 460, wherein:

[0069] The recognition module 410 is used for performing speech recognition on the voice navigation information in response to receiving the voice navigation information from the client to obtain at least one candidate recognition result;

[0070] A first determination module 420, configured to determine an acoustic score of each candidate recognition result;

[0071] A second determination module 430 is used to determine a language score for each candidate recognition result;

[0072] The acquisition module 440 is used to identify the target hot word contained in each candidate recognition result according to the preset hot word library of the client, and obtain the target hot word score of the predetermined target hot word, wherein the target hot word score is determined according to the total number of times the target hot word is added to the preset hot word library of the client;

[0073] A third determination module 450 is used to determine a reference score of each candidate recognition result according to the acoustic score, the language score and the target hot word score;

[0074] The fourth determination module 460 is used to determine a target recognition result from at least one candidate recognition result according to the reference score.

[0075] The speech recognition device provided in the embodiments of the present disclosure can execute the speech recognition method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0076] In some possible embodiments, the first determining module 420 is configured to:

[0077] Extracting candidate acoustic feature information of each candidate recognition result;

[0078] Matching the candidate acoustic feature information with the preset standard acoustic feature information to determine the target standard acoustic feature information that has been successfully matched;

[0079] A preset acoustic score corresponding to the target standard acoustic feature information is determined as the acoustic score of each candidate recognition result.

[0080] In some possible embodiments, the second determining module 430 is configured to:

[0081] Identify at least one candidate word segmentation corresponding to each candidate recognition result;

[0082] The word segmentation language score of each candidate word segmentation is determined, and the sum of the word segmentation language scores corresponding to at least one candidate word segmentation is calculated to determine the language score of each candidate recognition result.

[0083] In some possible embodiments, the third determining module 450 is configured to:

[0084] Normalizing the acoustic score to obtain a first normalized value;

[0085] Calculating a first product value of the language score and a preset first weight value, and normalizing the first product value to obtain a second normalized value;

[0086] Calculate a second product value of a preset second weight value and a target hot word score, and normalize the second product value to obtain a third normalized value;

[0087] The first normalized value, the second normalized value, and the third normalized value are summed to obtain a reference score for each candidate recognition result.

[0088] In some possible embodiments, the fourth determining module 460 is configured to:

[0089] The candidate recognition result corresponding to the maximum value among all reference scores is determined as the target recognition result.

[0090] In some possible embodiments, the present invention further includes: a hot word determination module, which is used to:

[0091] Determine the historical navigation location of the client, and obtain the historical search parameters of the historical navigation location;

[0092] Determine the historical navigation locations corresponding to the historical search parameters that meet the preset hot word search conditions as candidate hot words;

[0093] Generate a preset hot word library for the client based on all candidate hot words.

[0094] In some possible embodiments, the historical search parameter includes the number of historical navigations, and when the number of historical navigations is greater than a preset number threshold, it is determined that the historical search parameter meets the preset hot word search condition; and / or,

[0095] The historical search parameters include an input method of the historical navigation location, and when the input method is a preset input method, it is determined that the historical search parameters meet the preset hot word search condition.

[0096] In some possible embodiments, the hot word score acquisition module is used to:

[0097] In response to an operation of obtaining a hot word to be added to a preset hot word library, determining whether the candidate hot word corresponding to the adding operation is added to the preset hot word library for the first time;

[0098] When it is the first time to add to the preset hot word library, the hot word score of the candidate hot word corresponding to the adding operation is determined according to the preset language model; when it is not the first time to add to the preset hot word library, the hot word weight value corresponding to the adding operation is determined, and the hot word score of the candidate hot word corresponding to the adding operation is updated according to the hot word weight value.

[0099] In some possible embodiments, the hot word score acquisition module is used to:

[0100] Determine the total number of times the hot word corresponding to the add operation is added to the preset hot word library,

[0101] Determine the hot word weight corresponding to the total number of times, wherein the hot word weight is proportional to the total number of times; or,

[0102] Determine the preset unit weight increase value as the hot word weight value.

[0103] In some possible embodiments, the hot word score acquisition module is used to:

[0104] Get the current hot word score of the candidate hot word corresponding to the join operation;

[0105] Calculate the third product value of the current hot word score and the hot word weight;

[0106] The hot word score of the candidate hot word corresponding to the adding operation is updated according to the sum of the current hot word score and the third product value.

[0107] In order to implement the above embodiments, the present disclosure also proposes a computer program product, including a computer program / instruction, which implements the speech recognition method in the above embodiments when executed by a processor.

[0108] In order to implement the above embodiments, the present disclosure also proposes a vehicle, which includes the voice recognition device in the above embodiments, or the electronic device mentioned in the following embodiments.

[0109] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure.

[0110] The following specific reference Figure 5 , which shows a schematic diagram of the structure of an electronic device 500 suitable for implementing the embodiment of the present disclosure. The electronic device 500 in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0111] like Figure 5 As shown, the electronic device 500 may include a processor (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a memory 508 to a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 are also stored. The processor 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 504.

[0112] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 5 The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0113] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through a communication device 509, or installed from a memory 508, or installed from a ROM 502. When the computer program is executed by the processor 501, the above-mentioned functions defined in the speech recognition method of the embodiment of the present disclosure are executed.

[0114] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, 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 above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0115] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with 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"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0116] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0117] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device:

[0118] In response to receiving the voice navigation information from the client, the voice navigation information is speech recognized to obtain at least one candidate recognition result, the acoustic score of each candidate recognition result is determined, and the language score of each candidate recognition result is determined, and then, the target hot word contained in each candidate recognition result is identified according to the preset hot word library of the client, and the target hot word score of the predetermined target hot word is obtained, wherein the target hot word score is determined according to the total number of times the target hot word is added to the preset hot word library of the client, and the reference score of each candidate recognition result is determined according to the acoustic score, the language score and the target hot word score, and the target recognition result is determined in at least one candidate recognition result according to the reference score. In the present technical solution, on the basis of combining language and acoustics for speech recognition results, the hot words of the client are introduced to determine the final recognition results. Since the hot words of the client reflect personalized search habits, etc., the influence of similar sounds can be removed, and the accuracy of the recognition results can be further improved.

[0119] The electronic device may be written in one or more programming languages ​​or a combination thereof to write computer program code for performing the operations of the present disclosure, including but not limited to object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0120] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0121] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0122] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0123] 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.

[0124] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0125] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0126] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A speech recognition method, characterized in that: include: In response to receiving the voice navigation information from the client, performing voice recognition on the voice navigation information to obtain at least one candidate recognition result; Determining an acoustic score for each of the candidate recognition results, and determining a language score for each of the candidate recognition results; Identify a target hot word included in each candidate recognition result according to a preset hot word library of the client, and obtain a target hot word score of the predetermined target hot word, wherein the target hot word score is determined according to the total number of times the target hot word is added to the preset hot word library; Determining a reference score for each of the candidate recognition results according to the acoustic score, the language score, and the target hot word score; A target recognition result is determined from among the at least one candidate recognition result according to the reference score.

2. The method according to claim 1, characterized in that Determining the acoustic score of each candidate recognition result includes: Extracting candidate acoustic feature information of each of the candidate recognition results; Matching the candidate acoustic feature information with preset standard acoustic feature information to determine target standard acoustic feature information that has been successfully matched; A preset acoustic score corresponding to the target standard acoustic feature information is determined as the acoustic score of each candidate recognition result.

3. The method according to claim 1, characterized in that Determining the language score of each candidate recognition result includes: Identify at least one candidate word segmentation corresponding to each of the candidate recognition results; The word segmentation language score of each candidate word segmentation is determined, and the sum of the word segmentation language scores corresponding to at least one candidate word segmentation is calculated to determine the language score of each candidate recognition result.

4. The method according to claim 1, characterized in that The determining a reference score of each of the candidate recognition results according to the acoustic score, the language score and the target hot word score comprises: Normalizing the acoustic score to obtain a first normalized value; Calculating a first product value of the language score and a preset first weight value, and normalizing the first product value to obtain a second normalized value; Calculate a second product value of a preset second weight value and the target hot word score, and normalize the second product value to obtain a third normalized value; The first normalized value, the second normalized value, and the third normalized value are summed to obtain a reference score for each of the candidate recognition results.

5. The method according to any one of claims 1 to 4, characterized in that: The determining the target recognition result from the at least one candidate recognition result according to the reference score comprises: Determine the candidate recognition result corresponding to the maximum value among all the reference scores as the target recognition result.

6. The method according to claims 1 to 4, characterized in that: Before identifying the target hot word included in each candidate recognition result according to the preset hot word library of the client, the method further includes: Determine the historical navigation location of the client, and obtain the historical search parameters of the historical navigation location; Determine the historical navigation locations corresponding to the historical search parameters that meet the preset hot word search conditions as candidate hot words; A preset hot word library of the client is generated according to all the candidate hot words.

7. The method according to claim 6, characterized in that The historical search parameter includes the number of historical navigation times, and when the number of historical navigation times is greater than a preset number threshold, it is determined that the historical search parameter meets the preset hot word search condition; and / or, The historical search parameters include an input method of the historical navigation location, and when the input method is a preset input method, it is determined that the historical search parameters meet the preset hot word search condition.

8. The method according to claim 6, characterized in that Before obtaining the predetermined target hot word score of the target hot word, the method further includes: In response to an operation of acquiring a hot word to be added to the preset hot word library, determining whether the candidate hot word corresponding to the adding operation is added to the preset hot word library for the first time; When it is the first time to join the preset hot word library, the hot word score of the candidate hot word corresponding to the joining operation is determined according to the preset language model; when it is not the first time to join the preset hot word library, the hot word weight value corresponding to the joining operation is determined, and the hot word score of the candidate hot word corresponding to the joining operation is updated according to the hot word weight value.

9. The method according to claim 8, characterized in that: The determining the hot word weight value corresponding to the adding operation includes: Determine the total number of times the hot word corresponding to the adding operation is added to the preset hot word library, Determine a hot word weight corresponding to the total number of times, wherein the hot word weight is proportional to the total number of times; or, Determine the preset unit weight increase value as the hot word weight value.

10. The method according to claim 8 or 9, characterized in that The updating of the hot word score of the candidate hot word corresponding to the adding operation according to the hot word weight value includes: Obtaining the current hot word score of the candidate hot word corresponding to the adding operation; Calculate a third product value of the current hot word score and the hot word weight; The hot word score of the candidate hot word corresponding to the adding operation is updated according to the sum of the current hot word score and the third product value.

11. A speech recognition device, characterized in that: include: A recognition module, configured to respond to receiving the voice navigation information from the client and perform voice recognition on the voice navigation information to obtain at least one candidate recognition result; A first determination module, used to determine the acoustic score of each candidate recognition result; A second determination module, used to determine a language score for each of the candidate recognition results; an acquisition module, configured to identify a target hot word contained in each of the candidate recognition results according to a preset hot word library of the client, and acquire a target hot word score of the predetermined target hot word, wherein the target hot word score is determined according to the total number of times the target hot word is added to the preset hot word library; A third determination module, configured to determine a reference score of each of the candidate recognition results according to the acoustic score, the language score and the target hot word score; A fourth determination module is used to determine a target recognition result from among the at least one candidate recognition result according to the reference score.

12. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the executable instructions to implement the speech recognition method described in any one of claims 1-7.

13. A vehicle, characterized in that: The vehicle comprises: The speech recognition device as claimed in claim 11, or the electronic device as claimed in claim 12.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is used to execute the speech recognition method described in any one of claims 1 to 7.

Citation Information

Patent Citations

  • Speech recognition method, device and equipment and storage medium

    CN110164416A

  • Automatic voice recording method for online customized updating of hot words in telephone scene

    CN114283796A

  • Speech recognition method and device, equipment and storage medium

    CN114360499A

  • Speech recognition method and device, storage medium and electronic equipment

    CN115565526A

  • Adapting Automated Speech Recognition Parameters Based on Hotword Properties

    US20220189466A1