A voice conversion method, device and terminal equipment

Abstract

The present application is applicable to the field of speech processing technology, and provides a speech conversion method, apparatus and terminal device, the method comprising obtaining a first sound wave of a dialect speech to be converted; then obtaining a second sound wave matching the first sound wave of the dialect speech, the second sound wave being a sound wave of a pre-stored standard speech; finally, based on the second sound wave, generating a standard speech corresponding to the dialect speech; the present application can convert the dialect speech into the standard speech through the sound wave, and compared with the existing direct communication through the dialect, the dialect speech is converted into the standard speech for communication, which can make people communicate more smoothly.

Description

Technical Field

[0001] The present application belongs to the field of speech processing technology, and in particular, relates to a speech conversion method, apparatus and terminal device. Background Art

[0002] Dialects, also known as local languages, are languages ​​of a certain region that are different from the standard language and are only used in one region. Due to the differences in dialects in different regions, it is difficult for people in one region to understand the dialect of another region, which affects normal communication. Especially when one party asks for help in dialect, others may delay rescue because they do not understand the dialect.

[0003] Mandarin is the universal standard language of my country and the universal standard language for communication between different regions. People from different regions can communicate normally using Mandarin. Therefore, how to convert dialects into Mandarin to achieve smooth communication is a problem that needs to be considered at present. Summary of the invention

[0004] The embodiments of the present application provide a voice conversion method, apparatus and terminal device, which can solve the problem of poor communication using dialects.

[0005] In a first aspect, an embodiment of the present application provides a voice conversion method, including:

[0006] Obtaining the first sound wave of the dialect speech to be converted;

[0007] Acquire a second sound wave that matches the first sound wave of the dialect speech, wherein the second sound wave is a sound wave of a pre-stored standard speech;

[0008] Based on the second sound wave, a standard speech corresponding to the dialect speech is generated.

[0009] In a second aspect, an embodiment of the present application provides a speech conversion device, including:

[0010] A sound wave acquisition module, used to acquire the first sound wave of the dialect speech to be converted;

[0011] A query module, used to obtain a second sound wave that matches the first sound wave of the dialect speech, wherein the second sound wave is a sound wave of a pre-stored standard speech;

[0012] A conversion module is used to generate a standard speech corresponding to the dialect speech based on the second sound wave.

[0013] In a third aspect, an embodiment of the present application provides a terminal device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the speech conversion method described in any one of the first aspects above when executing the computer program.

[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and wherein when the computer program is executed by a processor, the speech conversion method described in any one of the first aspects is implemented.

[0015] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is executed on a terminal device, the terminal device executes the speech conversion method described in any one of the above-mentioned first aspects.

[0016] Compared with the prior art, the beneficial effects of the first aspect of the embodiment of the present application are as follows: the present application obtains a first sound wave of the dialect speech to be converted; then obtains a second sound wave that matches the first sound wave of the dialect speech, the second sound wave being a sound wave of a pre-stored standard speech; finally, based on the second sound wave, generates a standard speech corresponding to the dialect speech; the present application can convert the dialect speech into the standard speech through sound waves, and compared with the existing direct communication through dialect, the conversion of the dialect speech into the standard speech for communication can make people communicate more smoothly.

[0017] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0019] Figure 1 This is a schematic diagram of an application scenario of a voice conversion method provided by an embodiment of the present application;

[0020] Figure 2 is a flowchart of a voice conversion method provided by an embodiment of the present application;

[0021] Figure 3 is a flow chart of a first sound wave generating method provided in an embodiment of the present application;

[0022] Figure 4 It is a flowchart of a method for obtaining pronunciation characteristics provided in an embodiment of the present application;

[0023] Figure 5 is a flowchart of a method for obtaining pronunciation characteristics provided by another embodiment of the present application;

[0024] Figure 6 is a flow chart of a method for pre-storing sound waves provided in one embodiment of the present application;

[0025] Figure 7 is a flow chart of a method for pre-storing sound waves provided by another embodiment of the present application;

[0026] Figure 8 is a flow chart of a method for determining a third sound wave provided in an embodiment of the present application;

[0027] Fig. 9 is a structural diagram of a speech conversion device provided by an embodiment of the present application;

[0028] Fig.10 It is a structural diagram of a terminal device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0029] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0030] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0031] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0032] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0033] With the development of automobiles, people have higher and higher requirements for automobile safety. After an accident, how to quickly send out a rescue signal is also a concern for users. Based on the above problems, an emergency call function is set in the car. In an emergency, the emergency call function can actively or passively dial an emergency rescue phone so that users can get rescue as soon as possible.

[0034] When a user makes a voice call, if the user uses a dialect and the staff who answers the phone do not understand the dialect, it may cause a delay in the user's emergency help, and the user cannot be rescued in the first time, causing physical injury or property loss to the user. Therefore, how to convert the user's dialect into Mandarin so that the staff can clearly and accurately obtain the user's help content is a problem that needs to be solved at present.

[0035] Figure 1 The following is a schematic diagram of an application scenario of the voice conversion method provided in an embodiment of the present application. The voice conversion method can be used to convert a dialect into a standard voice. The voice acquisition device 10 is used to collect the user's dialect voice. The voice conversion device 20 is used to obtain the dialect voice from the voice acquisition device 10, and convert the dialect voice into a standard voice and then output it.

[0036] The following combination Figure 1 The voice conversion method of the embodiment of the present application is described in detail. The following voice conversion method can be applied in a voice conversion device.

[0037] Figure 2 A schematic flow chart of the voice conversion method provided by the present application is shown, referring to Figure 2 , the method is described in detail as follows:

[0038] S101, obtaining the first sound wave of the dialect speech to be converted.

[0039] In this embodiment, in an elastic medium, as long as the frequency of the longitudinal wave excited by the wave source is between 20-20000 Hz, it can cause human hearing. The vibration within this frequency range is called acoustic vibration, and the longitudinal wave excited by acoustic vibration is called sound wave.

[0040] In this embodiment, the sound wave of the dialect speech to be converted can be obtained from a voice acquisition device, and can also be obtained from a sound wave converter. Specifically, a digital-to-analog conversion chip (CODEC chip) can be used to convert the dialect speech into a sound wave. The CODEC chip can convert an analog signal into a digital signal. In this application, the sound wave of the dialect speech is recorded as the first sound wave.

[0041] Specifically, the first sound wave may be composed of sound waves of character strings in the dialect speech. For example, the dialect speech is "I am doing farm work", which includes four character strings "I", "at", "do", and "farm work", and the sound waves of each character string constitute the first sound wave.

[0042] Specifically, the first sound wave may also be composed of the sound wave of each phoneme in the dialect speech.

[0043] S102, obtaining a second sound wave that matches the first sound wave of the dialect speech, where the second sound wave is a pre-stored sound wave of a standard speech.

[0044] Specifically, the database may pre-store sound waves of various dialect speech, and associate the sound waves of each dialect speech with the sound waves of the corresponding standard speech.

[0045] Search the database to see whether the sound wave of the dialect speech exists in the database. If the sound wave of the dialect speech exists in the database, the sound wave associated with the sound wave of the dialect speech can be obtained. The sound wave associated with the sound wave of the dialect speech is the sound wave of the standard speech.

[0046] Optionally, the sound waves of the standard speech corresponding to the dialect speech are determined by a speech comparison chip.

[0047] S103: Generate a standard voice corresponding to the dialect voice based on the second sound wave.

[0048] In this embodiment, after the second sound wave of the standard voice is obtained, the second sound wave of the standard voice can be recognized to obtain and play the standard voice.

[0049] Specifically, after obtaining the second sound wave or the standard voice of the standard voice corresponding to the dialect voice, the second sound wave or the standard voice corresponding to the dialect voice can be sent to other electronic devices through the communication network.

[0050] In an embodiment of the present application, a first sound wave of the dialect speech to be converted is obtained; then a second sound wave matching the first sound wave of the dialect speech is obtained, the second sound wave being a sound wave of a pre-stored standard speech; finally, based on the second sound wave, a standard speech corresponding to the dialect speech is generated; the present application can convert the dialect speech into the standard speech through sound waves, and compared with the existing direct communication through dialect, the conversion of the dialect speech into the standard speech for communication can make people communicate more smoothly.

[0051] like Figure 3 As shown, in a possible implementation manner, the implementation process of step S101 may include:

[0052] S1011, obtaining voice information.

[0053] In this embodiment, the voice information can be obtained from the voice collection device in the vehicle, and can also be obtained from the terminal device used by the user, such as a mobile phone, a phone watch, etc.

[0054] In this embodiment, the voice information may include the user's voice and the sounds made by surrounding objects, such as the sound of a vehicle horn, the sound of birds, etc.

[0055] S1012: Perform noise reduction processing on the voice information to obtain noise-reduced voice information.

[0056] In this embodiment, in order to obtain a clearer user's voice, it is necessary to perform noise reduction processing on the voice information. Specifically, the acquired voice information is input into a neural network model to perform noise reduction processing on the voice information to obtain the voice information after noise reduction. After obtaining the voice information after noise reduction, the voice information can be identified to determine whether the voice information includes dialect voice. If the voice information does not include dialect voice, there is no need to process the voice information. Specifically, the voice information after noise reduction is input into a dialect recognition model to determine whether the voice information includes dialect voice.

[0057] S1013: If the noise-reduced speech information includes the dialect speech, extract the pronunciation characteristics of the dialect speech.

[0058] In this embodiment, the pronunciation characteristics include timbre and loudness, etc. Loudness may include pitch and volume, etc.

[0059] Specifically, the dialect speech is input into the feature extraction model to obtain the pronunciation characteristics of the dialect speech.

[0060] Optionally, it is possible to directly extract the pronunciation characteristics of the noise-reduced voice information without identifying whether the noise-reduced voice information includes the dialect voice, and regard the noise-reduced voice information as the dialect voice.

[0061] like Figure 4 As shown, specifically, the implementation process of step S1013 may include:

[0062] S10131, decompose the dialect speech to obtain various phonemes included in the dialect speech.

[0063] In this embodiment, phoneme is the smallest unit of speech divided according to the natural properties of speech, and is analyzed according to the pronunciation action in a syllable, where one action constitutes one phoneme. Phoneme is the smallest unit or the smallest speech segment that constitutes a syllable, and is the smallest linear unit of speech divided from the perspective of sound quality.

[0064] Specifically, the dialect speech is divided to obtain the speech of each word, and each word is decomposed to obtain the speech of each phoneme in each word, and the phonemes included in each word are arranged in the order of pronunciation. The phonemes included in each word are taken as a group of phoneme groups. The words in the dialect speech are arranged in the order of the time of receipt, and the phoneme groups corresponding to each word are also arranged in the order of the words.

[0065] S10132, extracting the pronunciation characteristics of each phoneme in the dialect speech, wherein the pronunciation characteristics of each phoneme in the dialect speech constitute the pronunciation characteristics of the dialect speech.

[0066] In this embodiment, each phoneme corresponds to a pronunciation characteristic, and the pronunciation characteristics of all phonemes in the dialect speech constitute the pronunciation characteristics of the dialect speech.

[0067] For example, dialect speech includes three phonemes a, b and c. The pronunciation feature corresponding to phoneme a is A, the pronunciation feature corresponding to phoneme b is B, and the pronunciation feature corresponding to phoneme c is C. The pronunciation characteristics of dialect speech include A, B and C.

[0068] In the embodiment of the present application, since the pronunciation of each word is composed of the pronunciation of phonemes, the pronunciation characteristics of the dialect speech can be obtained by extracting the pronunciation characteristics of the phonemes, and it is more accurate to characterize the pronunciation characteristics of the dialect using the pronunciation characteristics of the phonemes.

[0069] like Figure 5 As shown, specifically, the implementation process of step S1013 may include:

[0070] S201, decomposing the dialect speech to obtain various character strings included in the dialect speech.

[0071] In this embodiment, the dialect speech is input into the character string recognition model to obtain the character strings included in the dialect speech. The character string can be composed of one character or one word.

[0072] S202, extracting the pronunciation characteristics of each character string in the dialect speech, wherein the pronunciation characteristics of each character string in the dialect speech constitute the pronunciation characteristics of the dialect speech.

[0073] For example, the dialect speech includes three character strings: d, e and f. The pronunciation feature corresponding to the character string d is D, the pronunciation feature corresponding to the character string e is E, and the pronunciation feature corresponding to the character string f is F. The pronunciation characteristics of the dialect speech include D, E and F.

[0074] In the embodiment of the present application, since the dialect speech is composed of character strings, the pronunciation characteristics of the character strings are extracted, and the pronunciation characteristics of the dialect speech are represented by the pronunciation characteristics of the character strings so that the pronunciation characteristics of the dialect speech can be obtained more quickly.

[0075] S1014: Generate a first sound wave of the dialect speech based on the pronunciation characteristics.

[0076] In this embodiment, the pronunciation characteristics are input into the sound wave generation model to obtain the sound waves of the dialect speech.

[0077] In this embodiment, the sound wave of each phoneme in the dialect speech is generated based on the pronunciation characteristics of each phoneme in the dialect speech.

[0078] Specifically, the pronunciation characteristics of each phoneme are input into the sound wave generation model to obtain the sound waves of each phoneme. The first sound wave of the dialect speech includes the sound waves of each phoneme included in the dialect speech.

[0079] Optionally, the sound waves corresponding to each phoneme of each character form a sound wave group, and each sound wave group is arranged according to the arrangement order of the characters in the dialect pronunciation.

[0080] In this embodiment, the sound wave of each character string in the dialect speech is generated based on the pronunciation characteristics of each character string in the dialect speech.

[0081] Specifically, the pronunciation characteristics of each string are input into the sound wave generation model to obtain the sound waves of each string. The first sound wave of the dialect speech includes the sound waves of each string included in the dialect speech. Each string is arranged in the order of time received, and accordingly, the sound waves corresponding to each string are arranged in the order of time corresponding to the string.

[0082] In the embodiment of the present application, the noise reduction processing of the voice information can reduce the interference of noise and obtain clearer voice. The pronunciation characteristics of the dialect voice are extracted from the noise-reduced voice information, which can make the pronunciation characteristics of the extracted dialect voice more accurate, and thus the obtained sound waves more accurate.

[0083] In a possible implementation, the method may further include a process of pre-storing the dialect sound waves and the standard sound waves.

[0084] like Figure 6 Specifically, before step S102, the method may further include:

[0085] S301, obtaining the dialect pronunciation of the target phoneme in the target area.

[0086] In this embodiment, the target region may be a region selected according to needs, for example, the target region may be region A, region B or region C.

[0087] In this embodiment, the target phoneme may be a plurality of phonemes. Specifically, each phoneme included in Mandarin may be used as the target phoneme.

[0088] In this embodiment, the pronunciation of the target phonemes in the dialects of each target region may be different, and the dialect pronunciation of each target phoneme in each target region needs to be obtained.

[0089] S302: Obtain a dialect sound wave of the target phoneme based on the dialect pronunciation of the target phoneme.

[0090] In this embodiment, based on the dialect pronunciation of the target phoneme, the pronunciation characteristics of the target phoneme are obtained, and based on the pronunciation characteristics of the target phoneme, the dialect sound wave of the target phoneme is obtained.

[0091] S303: Acquire the standard sound wave of the target phoneme.

[0092] In this embodiment, the standard sound wave of the target phoneme is determined according to the standard voice or standard pronunciation of the target phoneme. The standard sound wave of the target phoneme can be obtained from a storage device or stored in the cloud.

[0093] S304, storing the dialect sound wave of the target phoneme, the standard sound wave of the target phoneme and the target region in association with each other.

[0094] In this embodiment, the target region is stored in association with the dialect sound wave and the standard sound wave, which is conducive to querying the dialect sound wave according to the region, making it faster to query the sound wave of the standard voice corresponding to the dialect voice.

[0095] Specifically, the dialect sound wave of each target phoneme may be pre-stored, and the dialect sound wave of the target phoneme may be associated with the standard sound wave of the target phoneme and stored.

[0096] For example, if the dialect sound wave corresponding to the pronunciation of the target phoneme r in region A is R, and the standard sound wave corresponding to the standard pronunciation of the target phoneme r is R', the dialect sound wave R and the standard sound wave R' of the target phoneme r are stored in association.

[0097] In the embodiment of the present application, the dialect sound wave, standard sound wave and target area of ​​the phoneme are stored in association, and a database for corresponding storage of the dialect sound wave and the standard sound wave can be established to facilitate the use of the dialect sound wave of the phoneme to find the corresponding standard sound wave, and then quickly convert the dialect speech into standard speech.

[0098] like Figure 7 Specifically, before step S102, the method may further include:

[0099] S401, obtaining the dialect pronunciation of the target character string in the target region.

[0100] In this embodiment, the target character string can be set as needed. For example, the target character string can be squat, sit down, etc.

[0101] For example, if the target string is "don't know", the dialect pronunciation of the target string in target region A is "zhi bu dao".

[0102] S402. Based on the dialect pronunciation of the target string, obtain the dialect sound wave of the target string.

[0103] Specifically, extract the pronunciation characteristics of the target string, and generate a dialect sound wave according to the pronunciation of the target string as well.

[0104] S403. Obtain the standard sound wave of the target string.

[0105] S404. Store the dialect sound wave of the target string, the standard sound wave of the target string, and the target region in an associated manner.

[0106] For example, if the target string is "don't know", the dialect pronunciation of the target string in target region A is "zhi bu dao". Store the sound wave of "zhi bu dao" and the sound wave of "don't know" in an associated manner.

[0107] In this embodiment, by establishing a correspondence database between the dialect sound wave and the standard sound wave of the string, the corresponding standard sound wave can be found using the dialect sound wave, and then the dialect speech can be quickly converted into standard speech.

[0108] In a possible implementation manner, the implementation process of step S201 may include:

[0109] S501. Obtain the purchase region of the vehicle of the target model.

[0110] In this embodiment, the target model may include one model or multiple models. The purchase region can be obtained from the user's purchase record.

[0111] S502. If the number of vehicles of the target model purchased in the purchase region is greater than a preset number, use the purchase region as the target region.

[0112] In this embodiment, count the number of vehicles of the target model purchased in each purchase region. If the number of vehicles of the target model purchased in a purchase region is greater than the preset number, it is determined that the number of people purchasing the vehicles of the target model in this purchase region is relatively large, and the dialect of this purchase region can be statistically analyzed and stored as a dialect sound wave.

[0113] S503. Store the target model and the target region in an associated manner.

[0114] In this embodiment, the target vehicle model is associated with the target region and stored. The target region can be locked according to the vehicle model that sends the dialect voice, and then the sound waves that match the dialect voice can be searched in the dialect sound waves associated with the target region, thereby speeding up the query.

[0115] In this embodiment, the target vehicle model is associated with the target region and stored. After receiving the dialect voice of the target vehicle model, data can be searched in the database corresponding to the target region first, thereby reducing the amount of data to be searched and improving the speed of data processing.

[0116] In a possible implementation, the implementation process of step S102 may include:

[0117] S1021, determining whether there is a third sound wave in the stored dialect sound waves, wherein the third sound wave is a sound wave in the dialect sound waves that matches the first sound wave of the dialect speech.

[0118] In this embodiment, after obtaining the sound wave of the dialect speech, the dialect sound wave matching the first sound wave of the dialect speech is searched in the database. Specifically, when the dialect sound wave is composed of the sound wave of the target phoneme, the dialect sound wave matching the sound wave of each phoneme in the dialect speech is searched in the database, and the dialect sound wave matching the sound wave of the dialect speech in the database is recorded as the third sound wave. Specifically, when the dialect sound wave is composed of the sound wave of the target character string, the dialect sound wave matching the sound wave of each character string in the dialect speech is searched in the database.

[0119] Specifically, the similarity between the first sound wave of the dialect speech and the dialect sound waves in the database is calculated, and the dialect sound wave corresponding to the maximum value of the similarity is used as the third sound wave.

[0120] S1022: If the third sound wave exists in the stored dialect sound waves, use the standard sound wave of the standard speech stored in association with the third sound wave as the second sound wave.

[0121] In this embodiment, after the third sound wave is found, the standard sound wave of the standard speech stored in association with the third sound wave is used as the second sound wave.

[0122] In the embodiment of the present application, by searching for a sound wave that matches the sound wave of the dialect speech in the database, the sound wave of the standard speech of the sound wave of the dialect speech can be quickly and accurately determined. It is also possible to filter out some waveforms that are not sound waves of the dialect speech by searching for a sound wave that matches the sound wave of the dialect speech. Specifically, if there is no dialect sound wave corresponding to the sound wave of the dialect speech in the database, it means that the sound wave of the dialect speech is a noise, which can be filtered out, thereby improving the accuracy of the standard speech corresponding to the dialect speech.

[0123] like Figure 8As shown, in a possible implementation manner, the implementation process of step S1021 may include:

[0124] S10211, if the dialect speech to be converted is speech collected by a speech collection device on the first vehicle, determine the target area associated with the model of the first vehicle according to the model of the first vehicle, and use the target area associated with the model of the first vehicle as the first area.

[0125] In this embodiment, after receiving the dialect voice to be converted, it is first determined whether the dialect voice to be converted comes from the vehicle. Specifically, the source of the dialect voice to be converted can be determined by the identifier of the device that sends the dialect voice to be converted.

[0126] If the dialect voice to be converted comes from the first vehicle, it is necessary to determine the model of the first vehicle. Specifically, the first vehicle can carry the vehicle model information when sending the dialect voice, or determine the model of the first vehicle according to the voice collection device. The database stores the association information between the voice collection device and the model of the first vehicle.

[0127] S10212, determining whether a third sound wave exists in the stored dialect sound waves associated with the first region.

[0128] In this embodiment, the third sound wave is first searched in the dialect sound waves associated with the first region, and if the third sound wave exists in the dialect sound waves associated with the first region, the search is stopped. If the third sound wave does not exist in the dialect sound waves associated with the first region, the third sound wave can be searched in other dialect sound waves, which are dialect sound waves in the database other than the dialect sound waves associated with the first region.

[0129] Seat distance, if the dialect sound waves associated with the first region include A, B and C, and the dialect sound waves associated with the second region are D and E. When searching for the third sound wave, first search A, B and C to see if the third sound wave exists. If the third sound wave does not exist in A, B and C, then search D and E to see if the third sound wave exists.

[0130] In this embodiment, the region corresponding to the model of the first vehicle is locked according to the model of the first vehicle, and the sound wave is searched in the database corresponding to the region, which can reduce the amount of data processing and improve the efficiency of voice conversion.

[0131] In a possible implementation, if the dialect voice to be converted is not the voice collected by the voice collection device on the vehicle, it is necessary to search for the third sound wave in all dialect sound waves stored in the entire database.

[0132] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0133] Corresponding to the voice conversion method described in the above embodiment, Fig. 9 A structural block diagram of a speech conversion device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0134] Reference Fig. 9 The device 600 may include: an acoustic wave acquisition module 610 , a query module 620 and a conversion module 630 .

[0135] The sound wave acquisition module 610 is used to acquire the first sound wave of the dialect speech to be converted;

[0136] A query module 620, configured to obtain a second sound wave that matches the first sound wave of the dialect speech, wherein the second sound wave is a sound wave of a pre-stored standard speech;

[0137] The conversion module 630 is used to generate a standard speech corresponding to the dialect speech based on the second sound wave.

[0138] In a possible implementation, the sound wave acquisition module 610 may be specifically used for:

[0139] Get voice information;

[0140] Performing noise reduction processing on the voice information to obtain noise-reduced voice information;

[0141] If the noise-reduced speech information includes the dialect speech, extracting pronunciation characteristics of the dialect speech, wherein the pronunciation characteristics include timbre and loudness;

[0142] Based on the pronunciation characteristics, a first sound wave of the dialect speech is generated.

[0143] In a possible implementation, the sound wave acquisition module 610 may also be used to:

[0144] Decomposing the dialect speech to obtain various phonemes included in the dialect speech;

[0145] Extracting the pronunciation characteristics of each phoneme in the dialect speech, wherein the pronunciation characteristics of each phoneme in the dialect speech constitute the pronunciation characteristics of the dialect speech;

[0146] Based on the pronunciation characteristics of each phoneme in the dialect speech, a sound wave of each phoneme in the dialect speech is generated, and the sound waves of the respective phonemes in the dialect speech constitute a first sound wave of the dialect speech.

[0147] In a possible implementation, the sound wave acquisition module 610 may also be used to:

[0148] Decomposing the dialect speech to obtain various character strings included in the dialect speech;

[0149] Extracting the pronunciation characteristics of each character string in the dialect speech, wherein the pronunciation characteristics of each character string in the dialect speech constitute the pronunciation characteristics of the dialect speech;

[0150] Based on the pronunciation characteristics of each character string in the dialect speech, a sound wave of each character string in the dialect speech is generated, and the sound wave of each character string in the dialect speech constitutes a first sound wave of the dialect speech.

[0151] In a possible implementation, the query module 620 may be specifically used to:

[0152] Determining whether there is a third sound wave in the stored dialect sound waves, wherein the third sound wave is a sound wave in the dialect sound waves that matches the first sound wave of the dialect speech;

[0153] If the third sound wave exists in the stored dialect sound waves, the standard sound wave of the standard speech stored in association with the third sound wave is used as the second sound wave.

[0154] In a possible implementation, the query module 620 is also connected to:

[0155] A first dialect pronunciation acquisition module is used to acquire the dialect pronunciation of the target phoneme in the target area;

[0156] A first sound wave generating module, configured to obtain a dialect sound wave of the target phoneme based on the dialect pronunciation of the target phoneme;

[0157] A first standard sound wave acquisition module, used to acquire the standard sound wave of the target phoneme;

[0158] an associated storage module, used for storing the dialect sound wave of the target phoneme, the standard sound wave of the target phoneme and the target region in an associated manner;

[0159] and / or,

[0160] A second dialect pronunciation acquisition module, used to acquire the dialect pronunciation of the target character string in the target region;

[0161] A second sound wave generating module, configured to obtain a dialect sound wave of the target character string based on the dialect pronunciation of the target character string;

[0162] A first standard sound wave acquisition module, used to acquire the standard sound wave of the target character string;

[0163] The associated storage module is used to associate and store the dialect sound wave of the target character string, the standard sound wave of the target character string and the target region.

[0164] In a possible implementation, the device 600 further includes:

[0165] A purchase area determination module is used to obtain the purchase area of ​​the target vehicle model;

[0166] a target region determining module, configured to determine the purchase region as the target region if the number of vehicles that purchased the target model in the purchase region is greater than a preset number;

[0167] The association module is used to associate and store the target vehicle model with the target region.

[0168] In a possible implementation, the query module 620 may be specifically used to:

[0169] If the dialect speech to be converted is speech collected by a speech collection device on a first vehicle, a target region associated with the model of the first vehicle is determined according to the model of the first vehicle, and the target region associated with the model of the first vehicle is used as the first region;

[0170] It is determined whether the third sound wave exists in the stored dialect sound waves associated with the first region.

[0171] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0172] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0173] The present application also provides a terminal device, see Fig.10 The terminal device 700 may include: at least one processor 710, a memory 720, and a computer program stored in the memory 720 and executable on the at least one processor 710. When the processor 710 executes the computer program, the steps in any of the above-mentioned method embodiments are implemented, for example Figure 2 Steps S101 to S103 in the illustrated embodiment. Alternatively, when the processor 710 executes the computer program, the functions of each module / unit in the above-mentioned device embodiments are implemented, for example Fig. 9 The functions of modules 610 to 630 are shown.

[0174] Exemplarily, the computer program may be divided into one or more modules / units, one or more modules / units are stored in the memory 720, and executed by the processor 710 to complete the present application. The one or more modules / units may be a series of computer program segments capable of completing specific functions, and the program segments are used to describe the execution process of the computer program in the terminal device 700.

[0175] Those skilled in the art will understand that Fig. 9 It is only an example of a terminal device and does not constitute a limitation on the terminal device. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, such as input and output devices, network access devices, buses, etc.

[0176] The processor 710 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0177] The memory 720 may be an internal storage unit of the terminal device, or an external storage device of the terminal device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. The memory 720 is used to store the computer program and other programs and data required by the terminal device. The memory 720 may also be used to temporarily store data that has been output or is to be output.

[0178] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0179] The speech conversion method provided in the embodiment of the present application can be applied to terminal devices such as computers, tablet computers, laptop computers, netbooks, personal digital assistants (PDAs), etc. The embodiment of the present application does not impose any restrictions on the specific type of terminal devices.

[0180] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0181] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0182] In the embodiments provided in the present application, it should be understood that the disclosed terminal equipment, devices and methods can be implemented in other ways. For example, the terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0183] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0184] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0185] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by one or more processors, the steps of each of the above-mentioned method embodiments can be implemented.

[0186] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by one or more processors, the steps of each of the above-mentioned method embodiments can be implemented.

[0187] Similarly, as a computer program product, when the computer program product runs on a terminal device, the terminal device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0188] The computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer readable media do not include electric carrier signals and telecommunication signals.

[0189] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A speech conversion method, characterized in that: include: Obtaining the first sound wave of the dialect speech to be converted; Acquire a second sound wave that matches the first sound wave of the dialect speech, wherein the second sound wave is a sound wave of a pre-stored standard speech; Based on the second sound wave, generating a standard speech corresponding to the dialect speech; The step of obtaining the first sound wave of the dialect speech to be converted comprises: Get voice information; Performing noise reduction processing on the voice information to obtain noise-reduced voice information; If the noise-reduced speech information includes the dialect speech, extracting pronunciation characteristics of the dialect speech, wherein the pronunciation characteristics include timbre and loudness; Based on the pronunciation characteristics, generating a first sound wave of the dialect speech; The extracting of the pronunciation characteristics of the dialect speech comprises: Decomposing the dialect speech to obtain various character strings included in the dialect speech; Extracting the pronunciation characteristics of each character string in the dialect speech, wherein the pronunciation characteristics of each character string in the dialect speech constitute the pronunciation characteristics of the dialect speech; Accordingly, based on the pronunciation characteristics, generating the first sound wave of the dialect speech includes: Based on the pronunciation characteristics of each character string in the dialect speech, a sound wave of each character string in the dialect speech is generated, and the sound wave of each character string in the dialect speech constitutes a first sound wave of the dialect speech.

2. The voice conversion method according to claim 1, characterized in that: The step of obtaining a second sound wave that matches the first sound wave of the dialect speech includes: Determining whether there is a third sound wave in the stored dialect sound waves, wherein the third sound wave is a sound wave in the dialect sound waves that matches the first sound wave of the dialect speech; If the third sound wave exists in the stored dialect sound waves, the standard sound wave of the standard speech stored in association with the third sound wave is used as the second sound wave.

3. The voice conversion method according to claim 2, characterized in that: Before acquiring the second sound wave matching the first sound wave of the dialect speech, the method further includes: Obtain the dialect pronunciation of the target phoneme in the target area; Based on the dialect pronunciation of the target phoneme, obtaining a dialect sound wave of the target phoneme; Acquiring a standard sound wave of the target phoneme; storing the dialect sound wave of the target phoneme, the standard sound wave of the target phoneme and the target region in association with each other; and / or, Get the dialect pronunciation of the target string in the target region; Based on the dialect pronunciation of the target character string, obtaining a dialect sound wave of the target character string; Obtaining a standard sound wave of the target character string; The dialect sound wave of the target character string, the standard sound wave of the target character string and the target region are stored in association.

4. The voice conversion method according to claim 3, characterized in that: The method further comprises: Get the purchase area of ​​the target vehicle model; If the number of vehicles that purchased the target model in the purchase area is greater than a preset number, the purchase area is used as the target area; The target vehicle model is associated with the target region and stored.

5. The voice conversion method according to claim 4, characterized in that: The step of determining whether the third sound wave exists in the stored dialect sound waves comprises: If the dialect speech to be converted is speech collected by a speech collection device on a first vehicle, a target region associated with the model of the first vehicle is determined according to the model of the first vehicle, and the target region associated with the model of the first vehicle is used as the first region; It is determined whether the third sound wave exists in the stored dialect sound waves associated with the first region.

6. A speech conversion device, characterized in that: include: A sound wave acquisition module, used to acquire the first sound wave of the dialect speech to be converted; A query module, used to obtain a second sound wave that matches the first sound wave of the dialect speech, wherein the second sound wave is a sound wave of a pre-stored standard speech; A conversion module, configured to generate a standard speech corresponding to the dialect speech based on the second sound wave; The sound wave acquisition module is also used to: acquire voice information; perform noise reduction processing on the voice information to obtain the noise-reduced voice information; if the noise-reduced voice information includes the dialect voice, extract the pronunciation characteristics of the dialect voice, wherein the pronunciation characteristics include timbre and loudness; based on the pronunciation characteristics, generate the first sound wave of the dialect voice; The sound wave acquisition module is also specifically used to: decompose the dialect speech to obtain the various character strings included in the dialect speech; extract the pronunciation characteristics of each character string in the dialect speech, and the pronunciation characteristics of each character string in the dialect speech constitute the pronunciation characteristics of the dialect speech; based on the pronunciation characteristics of each character string in the dialect speech, generate the sound wave of each character string in the dialect speech, and the sound wave of each character string in the dialect speech constitutes the first sound wave of the dialect speech.

7. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the speech conversion method according to any one of claims 1 to 5 is implemented.

Images