Synthesis method and device for English dubbing, storage medium and electronic device

Abstract

The present application discloses a synthesis method and device for English dubbing, a storage medium and an electronic device, which can be applied to the financial field or other fields. The method comprises: when receiving an instruction for speech synthesis of an English text, determining whether each English word in the English text meets a preset replacement condition, and determining the English words that meet the replacement condition as words to be replaced; determining a target splicing word group corresponding to each word to be replaced in a preset plurality of splicing word groups; replacing each word to be replaced in the English text with its corresponding target splicing word group to obtain the replaced English text; processing the replaced English text through a preset speech synthesis model, and using the synthesized speech obtained by the processing as the English dubbing corresponding to the English text. By using the method of the present application, English words that are difficult to pronounce accurately can be replaced with splicing word groups, which is conducive to improving the accuracy of synthesized pronunciation, avoiding manual correction, and improving efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of speech synthesis, and in particular to a synthesis method and device for English dubbing, a storage medium and an electronic device. Background Art

[0002] In the daily work of service institutions such as banks, it is often necessary to dub various English versions of materials in order to provide voice services to users.

[0003] Currently, dubbing of English materials is usually performed through speech synthesis, specifically, the text of the English material is input into a preset speech synthesis model to obtain the English dubbing corresponding to the English material.

[0004] In specific applications, English dubbing obtained based on existing synthesis methods often has inaccurate pronunciation. At this time, it is usually corrected through manual dubbing, or the speech synthesis model is adjusted and re-synthesized to improve the accuracy of English dubbing. This requires a lot of human resources and time, and the efficiency of synthetic dubbing is low. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a synthesis method for English dubbing to solve the problem that a large amount of human resources and time are consumed to improve the accuracy of English dubbing, and the efficiency is low.

[0006] The embodiment of the present invention also provides a synthesis device for English dubbing to ensure the actual implementation and application of the above method.

[0007] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0008] A synthesis method for English dubbing, comprising:

[0009] When receiving an instruction to perform speech synthesis on an English text, determining whether each English word in the English text meets a preset replacement condition, and determining the English words that meet the preset replacement condition as words to be replaced;

[0010] Determine a target splicing word group corresponding to each to-be-replaced word in the English text from a plurality of preset splicing word groups; each of the splicing word groups is composed of a plurality of splicing words, and the combined pronunciation of each word contained in each of the target splicing word groups matches the pronunciation of the corresponding to-be-replaced word;

[0011] Replacing each of the to-be-replaced words in the English text with a target concatenated word group corresponding to the to-be-replaced word to obtain a replaced English text;

[0012] The replaced English text is processed by a preset speech synthesis model to obtain a synthesized speech corresponding to the replaced English text, and the synthesized speech is used as the English dubbing corresponding to the English text.

[0013] In the above method, optionally, determining whether each English word in the English text meets a preset replacement condition includes:

[0014] For each English word in the English text, it is determined whether there is a word matching the English word in each preset word. If there is a word matching the English word in each preset word, it is determined that the English word meets the preset replacement condition.

[0015] In the above method, optionally, the step of judging whether there is a word matching the English word in each preset word includes:

[0016] Compare each of the preset words with the English word;

[0017] If there is a preset word that is the same as the English word among the preset words, then determining that there is a word that matches the English word among the preset words;

[0018] If there is no preset word identical to the English word among the preset words, it is determined that there is no word matching the English word among the preset words.

[0019] The above method, optionally, determines the target concatenated word group corresponding to each to-be-replaced word in the English text from among the preset multiple concatenated word groups, including:

[0020] Determining a one-to-one correspondence between the plurality of concatenated word groups and the respective preset words;

[0021] Determine a target preset word corresponding to each of the words to be replaced, wherein the target preset word corresponding to each of the words to be replaced is a preset word among the preset words that matches the word to be replaced;

[0022] The splicing word group corresponding to the target preset word corresponding to each of the to-be-replaced words is determined as the target splicing word group corresponding to each of the to-be-replaced words.

[0023] In the above method, optionally, the step of processing the replaced English text by a preset speech synthesis model to obtain a synthesized speech corresponding to the replaced English text includes:

[0024] Loading the replaced English text into the input layer of the speech synthesis model, and obtaining output speech from the output layer of the speech synthesis model after being processed by the speech synthesis model;

[0025] The acquired output speech is used as the synthesized speech corresponding to the replaced English text.

[0026] A synthesis device for English dubbing, comprising:

[0027] A first determining unit is used to determine whether each English word in the English text meets a preset replacement condition when receiving an instruction to perform speech synthesis on the English text, and determine the English words that meet the preset replacement condition as words to be replaced;

[0028] A second determining unit is used to determine a target concatenated word group corresponding to each to-be-replaced word in the English text from a plurality of preset concatenated word groups; each of the concatenated word groups is composed of a plurality of concatenated words, and the combined pronunciation of each word contained in each of the target concatenated word groups matches the pronunciation of the corresponding to-be-replaced word;

[0029] A replacement unit, used for replacing each of the to-be-replaced words in the English text with a target concatenated word group corresponding to the to-be-replaced word, to obtain a replaced English text;

[0030] The synthesis unit is used to process the replaced English text through a preset speech synthesis model to obtain a synthesized speech corresponding to the replaced English text, and use the synthesized speech as the English dubbing corresponding to the English text.

[0031] In the above device, optionally, the first determining unit includes:

[0032] The judging subunit is used to judge, for each English word in the English text, whether there is a word matching the English word in each preset word, and if there is a word matching the English word in each preset word, it is determined that the English word meets the preset replacement condition.

[0033] In the above device, optionally, the judging subunit includes:

[0034] A comparison subunit, used for comparing each of the preset words with the English word;

[0035] A first determining subunit is used to determine whether there is a word matching the English word among the preset words if there is a preset word that is the same as the English word among the preset words;

[0036] The second determining subunit is used to determine that there is no word matching the English word among the preset words if there is no preset word identical to the English word among the preset words.

[0037] A storage medium includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the above-mentioned English dubbing synthesis method.

[0038] An electronic device includes a memory and one or more instructions, wherein the one or more instructions are stored in the memory and configured to be executed by one or more processors to perform the above-mentioned English dubbing synthesis method.

[0039] A synthesis method for English dubbing based on the above-mentioned embodiment of the present invention includes: when receiving an instruction for performing speech synthesis on an English text, determining whether each English word in the English text meets a preset replacement condition, and determining the English words that meet the preset replacement condition as words to be replaced; determining a target spliced ​​word group corresponding to each word to be replaced in the English text from a plurality of preset spliced ​​word groups; each of the spliced ​​word groups is composed of a plurality of spliced ​​words, and the combined pronunciation of each word contained in each of the target spliced ​​word groups matches the pronunciation of the corresponding word to be replaced; replacing each word to be replaced in the English text with the target spliced ​​word group corresponding to the word to be replaced, to obtain a replaced English text; processing the replaced English text through a preset speech synthesis model, to obtain a synthesized speech corresponding to the replaced English text, and using the synthesized speech as the English dubbing corresponding to the English text. By applying the method provided in the embodiment of the present invention, replacement conditions can be set in advance, English words that need to be replaced can be identified in the English text, and replaced with corresponding concatenated word groups. Single words that are difficult for the speech synthesis model to synthesize accurate pronunciation can be replaced with concatenated phrases of multiple simple words, which is conducive to the speech synthesis model to synthesize accurate pronunciation, thereby improving the accuracy of English dubbing of English texts without consuming a large amount of human resources and time for manual dubbing or adjusting the model, which is conducive to improving dubbing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, 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 embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0041] Figure 1A method flow chart of a synthesis method of English dubbing provided by an embodiment of the present invention;

[0042] Figure 2 Another method flow chart of a synthesis method of English dubbing provided by an embodiment of the present invention;

[0043] Figure 3 A schematic flow chart of a synthesis process of English dubbing provided by an embodiment of the present invention;

[0044] Figure 4 A schematic diagram of the structure of a synthesis device for English dubbing provided by an embodiment of the present invention;

[0045] Figure 5 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] In this application, the terms "comprises", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element.

[0048] As can be seen from the background technology, the existing synthesis method of English dubbing is usually to directly input the English text to be dubbed into the speech synthesis model for synthesis. If the synthesized dubbing has inaccurate pronunciation, it is usually dubbed manually or the training sample is adjusted to modify the speech synthesis model to re-dub to improve the accuracy. However, this method usually consumes a lot of human resources and time, and manual dubbing also has the problem of inconsistent voice style.

[0049] Therefore, the embodiments of the present invention provide a synthesis method and device for English dubbing, a storage medium and an electronic device, which replace designated words in an English text with a spliced ​​word group, perform speech synthesis with the replaced English text, improve the accuracy of speech synthesis, avoid manual correction, and improve dubbing efficiency.

[0050] It should be noted that the synthesis method and device for English dubbing, storage medium and electronic device provided by the present invention can be used in the financial field or other fields, for example, can be used in the application scenario of banking service dubbing in the financial field. Other fields are any fields other than the financial field, for example, the communication service field. The above is only an example and does not limit the application field of the synthesis method and device for English dubbing, storage medium and electronic device provided by the present invention.

[0051] The embodiment of the present invention provides a method for synthesizing English dubbing, which can be applied to a speech synthesis system, and the execution subject can be a processor of the system. The method flow chart of the method is as follows: Figure 1 As shown, including:

[0052] S101: When receiving an instruction to perform speech synthesis on an English text, determining whether each English word in the English text meets a preset replacement condition, and determining the English words that meet the preset replacement condition as words to be replaced;

[0053] In the method provided by the embodiment of the present invention, the user can import English text through the front end and send a speech synthesis instruction to the processor. When the processor receives the instruction, it can recognize the English text, recognize each English word contained in the text one by one, and determine whether each English word meets the preset replacement condition. Each English word in the English text that meets the replacement condition is determined as a word to be replaced.

[0054] S102: Determine a target concatenated word group corresponding to each to-be-replaced word in the English text from among a plurality of preset concatenated word groups; each of the concatenated word groups is composed of a plurality of concatenated words, and the combined pronunciation of each word contained in each of the target concatenated word groups matches the pronunciation of the corresponding to-be-replaced word;

[0055] In the method provided in the embodiment of the present invention, multiple concatenated word groups can be pre-set, each of which is a word group composed of multiple words. For example, the concatenated word group fine-nance is composed of the two words fine and nance. The concatenated word group is obtained by pre-analyzing single words that are easy to mispronounce in speech synthesis, splitting them into multiple words with the same pronunciation, and then splicing the split words. For example, the word finance, which is pronounced as This pronunciation does not match the correct pronunciation of finance. By splitting finance into fine-nance, that is, taking fine-nance as its corresponding concatenated word group, and performing speech synthesis through the speech synthesis model, the concatenated word group fine-nance can be pronounced as This pronunciation is the same as the correct pronunciation of finance.

[0056] For each word to be replaced, its corresponding target concatenated word group may be determined in each concatenated word group.

[0057] S103: replacing each of the to-be-replaced words in the English text with a target concatenated word group corresponding to the to-be-replaced word, to obtain a replaced English text;

[0058] In the method provided in the embodiment of the present invention, all the words to be replaced in the English text are replaced throughout the text, and each word to be replaced in the text is replaced with its corresponding target concatenated word group. Taking finance as an example, each finance in the English text is replaced with the target concatenated word group fine-nance corresponding to finance. After each word to be replaced is replaced with the corresponding target concatenated word group, the replaced English text is obtained. It should be noted that the embodiment of the present invention is only an example, and the English text may contain multiple different words to be replaced.

[0059] S104: Processing the replaced English text through a preset speech synthesis model to obtain a synthesized speech corresponding to the replaced English text, and using the synthesized speech as the English dubbing corresponding to the English text.

[0060] In the method provided by the embodiment of the present invention, the replaced English text can be input into a preset speech synthesis model, so that the speech synthesis model performs speech synthesis processing on the replaced English text to obtain the synthesized speech corresponding to the replaced English text, and the synthesized speech obtained by the speech synthesis model is used as the English dubbing corresponding to the English text.

[0061] Based on the method provided by the embodiment of the present invention, in the process of speech synthesis of English text, it can be determined whether each English word in the English text meets the preset replacement condition, and the English words that meet the preset replacement condition are replaced, and each word to be replaced in the English text is replaced with a target concatenated word group whose combined pronunciation matches its pronunciation. The replaced English text is processed by speech synthesis through a speech synthesis model to obtain the English dubbing corresponding to the English text. By applying the method provided by the embodiment of the present invention, English words that are difficult to synthesize with accurate pronunciation by the speech synthesis model can be replaced with a concatenated phrase formed by concatenating multiple words with the same combined pronunciation as the English word. The speech synthesis accuracy of the speech synthesis model for simple words (words with simpler syllables, such as monosyllabic words) is higher than that of complex words (words with more complex syllables, such as polysyllabic words). By synthesizing the speech of each word in the concatenated word group, the correct pronunciation of the corresponding English word can be accurately restored, which is conducive to improving the accuracy of speech synthesis, and then improving the accuracy of English dubbing of English text, without consuming a lot of human resources and time for manual dubbing or model adjustment, and can improve the efficiency of dubbing synthesis.

[0062] exist Figure 1 On the basis of the method shown, in the method provided by the embodiment of the present invention, the step of determining whether each English word in the English text meets a preset replacement condition includes:

[0063] For each English word in the English text, it is determined whether there is a word matching the English word in each preset word. If there is a word matching the English word in each preset word, it is determined that the English word meets the preset replacement condition.

[0064] In the method provided in the embodiment of the present invention, a plurality of preset words are pre-set, and each preset word can be a word that is easily mispronounced by the speech synthesis of the speech synthesis model, and the staff can determine by analyzing the speech samples synthesized by the speech synthesis model. It can be determined whether the English word meets the preset replacement condition by judging whether there is a word matching the English word among the preset words.

[0065] On the basis of the method provided in the above embodiment, in the method provided in the embodiment of the present invention, the step of determining whether there is a word matching the English word in each preset word includes:

[0066] Compare each of the preset words with the English word;

[0067] If there is a preset word that is the same as the English word among the preset words, then determining that there is a word that matches the English word among the preset words;

[0068] If there is no preset word identical to the English word among the preset words, it is determined that there is no word matching the English word among the preset words.

[0069] In the method provided by the embodiment of the present invention, the currently judged English word can be matched and compared with each preset word to determine whether the English word is the same as the preset word. If there is a preset word that is the same as the English word during the comparison process between each preset word and the English word, then there is a word matching the English word in each preset word. Each preset word is different from each other, so at most only one preset word is the same as the English word. If each preset word is different from the English word, then there is no word matching the English word in each preset word.

[0070] Based on the method provided in the above embodiment, Figure 2 , shows the process of determining the target splicing word group corresponding to each to-be-replaced word in the English text from among the preset multiple splicing word groups in the synthesis method of English dubbing provided by the embodiment of the present invention, and the implementation process includes:

[0071] S201: Determine a one-to-one correspondence between the plurality of concatenated word groups and the respective preset words;

[0072] In the method provided by the embodiment of the present invention, each concatenated word group and each preset word are arranged in a one-to-one correspondence, and the combined pronunciation of each word contained in each concatenated word group is the same as the pronunciation of the corresponding preset word.

[0073] The one-to-one correspondence between the plurality of concatenated word groups and the respective preset words may be determined according to a preset correspondence, that is, the concatenated word group corresponding to each preset word is determined.

[0074] S202: Determine a target preset word corresponding to each of the words to be replaced, wherein the target preset word corresponding to each of the words to be replaced is a preset word among the preset words that matches the word to be replaced;

[0075] In the method provided by the embodiment of the present invention, for each word to be replaced, a preset word matching the word among various preset words is used as a target preset word corresponding to the word to be replaced.

[0076] S203: Determine the concatenated word group corresponding to the target preset word corresponding to each of the to-be-replaced words as the target concatenated word group corresponding to each of the to-be-replaced words.

[0077] In the method provided by the embodiment of the present invention, based on the correspondence between the concatenated word groups and the preset words, the concatenated word group corresponding to each target preset word can be used as the target concatenated word group corresponding to the corresponding word to be replaced. For example, the word to be replaced is finance, and its corresponding target preset word is the preset word finance, and the concatenated word group corresponding to the target preset word finance is fine-nance, then the concatenated word group fine-nance is used as the target concatenated word group corresponding to the word to be replaced finance.

[0078] In order to better illustrate the synthesis process of the English dubbing provided by the embodiment of the present invention, Figure 3 The flow chart shown further illustrates the synthesis process of English dubbing provided by the embodiment of the present invention.

[0079] like Figure 3 As shown, the specific implementation process of the method provided in the embodiment of the present invention includes:

[0080] 1. Find inaccurate pronunciations;

[0081] The staff can find and analyze the inaccurate pronunciation of polysyllabic words by listening to the speech synthesized by the speech synthesis model. It should be noted that the analysis of polysyllabic words in the embodiment of the present invention is only a specific embodiment. In the specific implementation process, the speech synthesis model is prone to inaccurate pronunciation of polysyllabic words, but it does not limit the analysis object in the specific application process. As long as the pronunciation is inaccurate, it can be regarded as an inaccurate pronunciation.

[0082] 2. Targetedly split polysyllabic words into homophones, and concatenate and store them in the background;

[0083] For inaccurate pronunciation, the English word corresponding to each inaccurate pronunciation is split into multiple homophones with correct pronunciation, and after splicing the homophones, the spliced ​​word group is stored in the background corresponding to the English word.

[0084] 3. Request the backend to replace multiple words with incorrect pronunciations in the English text with the concatenated text and perform speech synthesis.

[0085] When speech synthesis is required for English text, the background can be requested for each pre-configured inaccurately pronounced English word and its corresponding concatenated word group. Each English word in the English text is identified, and the inaccurately pronounced words in the text are replaced throughout the text, usually replacing all inaccurate polysyllabic words, and each word to be replaced is replaced with its corresponding concatenated word group, that is, multiple homophones with the same pronunciation. Speech synthesis is performed with the replaced English text.

[0086] exist Figure 1 On the basis of the method shown, in the method provided by the embodiment of the present invention, the replaced English text is processed by a preset speech synthesis model to obtain the synthesized speech corresponding to the replaced English text, including:

[0087] Loading the replaced English text into the input layer of the speech synthesis model, and obtaining output speech from the output layer of the speech synthesis model after being processed by the speech synthesis model;

[0088] The acquired output speech is used as the synthesized speech corresponding to the replaced English text.

[0089] In the method provided by the embodiment of the present invention, the replaced English text is input into a preset speech synthesis model, and after being processed by the speech synthesis model, the speech output by the speech synthesis model is used as the English dubbing corresponding to the English text requesting speech synthesis.

[0090] and Figure 1 Corresponding to the synthesis method of an English dubbing shown in FIG. 1 , an embodiment of the present invention further provides a synthesis device for English dubbing, for Figure 1 The specific implementation of the method shown in is shown in the structural diagram Figure 4 As shown, including:

[0091] The first determining unit 301 is used for, when receiving an instruction to perform speech synthesis on an English text, determining whether each English word in the English text meets a preset replacement condition, and determining the English words meeting the preset replacement condition as words to be replaced;

[0092] The second determining unit 302 is used to determine a target concatenated word group corresponding to each to-be-replaced word in the English text from among a plurality of preset concatenated word groups; each of the concatenated word groups is composed of a plurality of concatenated words, and the combined pronunciation of each word contained in each of the target concatenated word groups matches the pronunciation of the corresponding to-be-replaced word;

[0093] A replacement unit 303 is used to replace each of the to-be-replaced words in the English text with a target concatenated word group corresponding to the to-be-replaced word to obtain a replaced English text;

[0094] The synthesis unit 304 is used to process the replaced English text through a preset speech synthesis model to obtain a synthesized speech corresponding to the replaced English text, and use the synthesized speech as the English dubbing corresponding to the English text.

[0095] Based on the device provided by the embodiment of the present invention, in the process of speech synthesis of English text, it can be determined whether each English word in the English text meets the preset replacement condition, and the English words that meet the preset replacement condition are replaced, and each word to be replaced in the English text is replaced with a target concatenated word group whose combined pronunciation matches its pronunciation. The replaced English text is processed by speech synthesis through a speech synthesis model to obtain the English dubbing corresponding to the English text. By using the device provided by the embodiment of the present invention, English words that are difficult to synthesize with accurate pronunciation by the speech synthesis model can be replaced with a concatenated phrase formed by splicing multiple words with the same combined pronunciation as the English word. The speech synthesis accuracy of the speech synthesis model for simple words (words with simpler syllables, such as monosyllabic words) is higher than that of complex words (words with more complex syllables, such as polysyllabic words). By synthesizing the speech of each word in the concatenated word group, the correct pronunciation of the corresponding English word can be accurately restored, which is conducive to improving the accuracy of speech synthesis, and then improving the accuracy of English dubbing of English text, without consuming a lot of human resources and time for manual dubbing or model adjustment, and can improve the efficiency of dubbing synthesis.

[0096] On the basis of the device provided in the above embodiment, in the device provided in the embodiment of the present invention, the first determining unit 301 includes:

[0097] The judging subunit is used to judge, for each English word in the English text, whether there is a word matching the English word in each preset word, and if there is a word matching the English word in each preset word, it is determined that the English word meets the preset replacement condition.

[0098] On the basis of the device provided in the above embodiment, in the device provided in the embodiment of the present invention, the judgment subunit includes:

[0099] A comparison subunit, used for comparing each of the preset words with the English word;

[0100] A first determining subunit is used to determine whether there is a word matching the English word among the preset words if there is a preset word that is the same as the English word among the preset words;

[0101] The second determining subunit is used to determine that there is no word matching the English word among the preset words if there is no preset word identical to the English word among the preset words.

[0102] On the basis of the device provided in the above embodiment, in the device provided in the embodiment of the present invention, the second determining unit 302 includes:

[0103] A third determining subunit is used to determine a one-to-one correspondence between the plurality of spliced ​​word groups and the respective preset words;

[0104] A fourth determination subunit is used to determine a target preset word corresponding to each of the words to be replaced, wherein the target preset word corresponding to each of the words to be replaced is a preset word among the preset words that matches the word to be replaced;

[0105] The fifth determining subunit is used to determine the concatenated word group corresponding to the target preset word corresponding to each of the to-be-replaced words as the target concatenated word group corresponding to each of the to-be-replaced words.

[0106] On the basis of the device provided in the above embodiment, in the device provided in the embodiment of the present invention, the synthesis unit 304 includes:

[0107] The model processing subunit is used to load the replaced English text into the input layer of the speech synthesis model, obtain the output speech from the output layer of the speech synthesis model after being processed by the speech synthesis model; and use the obtained output speech as the synthesized speech corresponding to the replaced English text.

[0108] An embodiment of the present invention further provides a storage medium, which includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the above-mentioned English dubbing synthesis method.

[0109] The embodiment of the present invention further provides an electronic device, the structural diagram of which is shown in FIG. Figure 5 As shown, it specifically includes a memory 401 and one or more instructions 402, wherein the one or more instructions 402 are stored in the memory 401 and are configured to be executed by one or more processors 403 to perform the following operations:

[0110] When receiving an instruction to perform speech synthesis on an English text, determining whether each English word in the English text meets a preset replacement condition, and determining the English words that meet the preset replacement condition as words to be replaced;

[0111] Determine a target splicing word group corresponding to each to-be-replaced word in the English text from a plurality of preset splicing word groups; each of the splicing word groups is composed of a plurality of splicing words, and the combined pronunciation of each word contained in each of the target splicing word groups matches the pronunciation of the corresponding to-be-replaced word;

[0112] Replacing each of the to-be-replaced words in the English text with a target concatenated word group corresponding to the to-be-replaced word to obtain a replaced English text;

[0113] The replaced English text is processed by a preset speech synthesis model to obtain a synthesized speech corresponding to the replaced English text, and the synthesized speech is used as the English dubbing corresponding to the English text.

[0114] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work.

[0115] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may 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 the present invention.

[0116] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A synthesis method for English dubbing, characterized in that: include: When receiving an instruction to perform speech synthesis on an English text, determining whether each English word in the English text meets a preset replacement condition, and determining the English words that meet the preset replacement condition as words to be replaced; Determine, among a plurality of preset concatenated word groups, a target concatenated word group corresponding to each to-be-replaced word in the English text; Each of the spliced ​​word groups is composed of a plurality of words, and the combined pronunciation of each word contained in each of the target spliced ​​word groups matches the pronunciation of the corresponding word to be replaced; Replacing each of the to-be-replaced words in the English text with a target concatenated word group corresponding to the to-be-replaced word to obtain a replaced English text; The replaced English text is processed by a preset speech synthesis model to obtain a synthesized speech corresponding to the replaced English text, and the synthesized speech is used as the English dubbing corresponding to the English text.

2. The method according to claim 1, characterized in that The step of determining whether each English word in the English text meets a preset replacement condition includes: For each English word in the English text, it is determined whether there is a word matching the English word in each preset word. If there is a word matching the English word in each preset word, it is determined that the English word meets the preset replacement condition.

3. The method according to claim 2, characterized in that The step of judging whether there is a word matching the English word in each of the preset words comprises: Compare each of the preset words with the English word; If there is a preset word that is the same as the English word among the preset words, then determining that there is a word that matches the English word among the preset words; If there is no preset word identical to the English word among the preset words, it is determined that there is no word matching the English word among the preset words.

4. The method according to claim 2, characterized in that: Determining a target splicing word group corresponding to each to-be-replaced word in the English text from among the preset multiple splicing word groups comprises: Determining a one-to-one correspondence between the plurality of concatenated word groups and the respective preset words; Determine a target preset word corresponding to each of the words to be replaced, wherein the target preset word corresponding to each of the words to be replaced is a preset word among the preset words that matches the word to be replaced; The splicing word group corresponding to the target preset word corresponding to each of the to-be-replaced words is determined as the target splicing word group corresponding to each of the to-be-replaced words.

5. The method according to claim 1, characterized in that The step of processing the replaced English text by a preset speech synthesis model to obtain a synthesized speech corresponding to the replaced English text includes: Loading the replaced English text into the input layer of the speech synthesis model, and obtaining output speech from the output layer of the speech synthesis model after being processed by the speech synthesis model; The acquired output speech is used as the synthesized speech corresponding to the replaced English text.

6. A synthesis device for English dubbing, characterized in that: include: A first determining unit is used to determine whether each English word in the English text meets a preset replacement condition when receiving an instruction to perform speech synthesis on the English text, and determine the English words that meet the preset replacement condition as words to be replaced; A second determining unit is used to determine a target splicing word group corresponding to each to-be-replaced word in the English text from among a plurality of preset splicing word groups; Each of the spliced ​​word groups is composed of a plurality of words, and the combined pronunciation of each word contained in each of the target spliced ​​word groups matches the pronunciation of the corresponding word to be replaced; A replacement unit, used for replacing each of the to-be-replaced words in the English text with a target concatenated word group corresponding to the to-be-replaced word, to obtain a replaced English text; The synthesis unit is used to process the replaced English text through a preset speech synthesis model to obtain a synthesized speech corresponding to the replaced English text, and use the synthesized speech as the English dubbing corresponding to the English text.

7. The device according to claim 6, characterized in that The first determining unit includes: The judging subunit is used to judge, for each English word in the English text, whether there is a word matching the English word in each preset word, and if there is a word matching the English word in each preset word, it is determined that the English word meets the preset replacement condition.

8. The device according to claim 7, characterized in that The judging subunit comprises: A comparison subunit, used for comparing each of the preset words with the English word; A first determining subunit is used to determine whether there is a word matching the English word among the preset words if there is a preset word that is the same as the English word among the preset words; The second determining subunit is used to determine that there is no word matching the English word among the preset words if there is no preset word identical to the English word among the preset words.

9. A storage medium, characterized in that: The storage medium includes stored instructions, wherein when the instructions are executed, the device where the storage medium is located is controlled to execute the English dubbing synthesis method according to any one of claims 1 to 5.

10. An electronic device, characterized in that: The system comprises a memory and one or more instructions, wherein the one or more instructions are stored in the memory and configured to be executed by one or more processors to perform the English dubbing synthesis method as claimed in any one of claims 1 to 5.

Images