Audio reading material manufacturing method and device, computer equipment and storage medium

Abstract

The embodiment of the invention discloses a production method and device of audio books, computer equipment and a storage medium. The method comprises the following steps: identifying and extracting a text segment into which background sound should be inserted in a target text; generating a target background sound according to the extracted content of the text fragment; converting the target text into a target text voice; and inserting the target background sound in a position corresponding to the text segment in the target text voice, and synthesizing to obtain the audio book. By implementing the method provided by the embodiment of the invention, the audio reading material is rich in sound layering sense, and audiences listen to the audio reading material vividly and interestingly, so that the audiences listen to the audio reading material more preferably.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method, device, computer equipment and storage medium for producing audio books. Background Art

[0002] In order to actively respond to the national strategy of population aging and keep up with the development trend of the elderly cause and the elderly care industry, many life insurance companies have made efforts to build a universal and diversified elderly care service system and developed a variety of elderly care products. These products are inexpensive and easy for the elderly to operate, and continue to meet the growing multi-level, high-quality, and healthy elderly care needs of the elderly. Among them, smart speakers are one of the representative products.

[0003] In addition to the function of interacting with the elderly, smart speakers also provide a variety of entertainment content for the elderly. As the eyesight of the elderly gradually declines with age, it is difficult for them to watch video content. Therefore, many elderly people like to listen to electronic audiobooks. The current electronic audiobooks are rich in content and can meet the needs of most elderly people. However, such electronic audiobooks usually only have direct text sounds, and the sound has no layering, which makes people feel boring when listening. Summary of the invention

[0004] The embodiments of the present invention provide a method, apparatus, computer equipment and storage medium for producing an audio book, aiming to solve the technical problem that the sound of current electronic audio books lacks a sense of hierarchy and makes people feel dull when listening.

[0005] In a first aspect, an embodiment of the present invention provides a method for producing an audio book, comprising:

[0006] Identify and extract text segments in the target text where background sound should be inserted;

[0007] generating a target background sound according to the extracted content of the text segment;

[0008] Converting target text into target text speech;

[0009] The target background sound is inserted into the target text speech at a position corresponding to the text segment, and the audio book is synthesized.

[0010] In some embodiments, before the step of identifying and extracting the text segment in the target text into which the background sound should be inserted, the step further includes:

[0011] Select the required text according to the needs of the target users, regularize the required text, and obtain the target text.

[0012] In some embodiments, the step of identifying and extracting the text segment in the target text into which the background sound should be inserted specifically includes:

[0013] Identify text segments in the target text where background sound should be inserted;

[0014] Mark each text segment according to its position in the target text;

[0015] Extract each text segment after the token identification.

[0016] In some embodiments, the step of generating a target background sound according to the content of the text segment specifically includes:

[0017] Content analysis is performed on each extracted text segment, and a target background sound with a corresponding identifier is generated for each text segment according to the analysis result.

[0018] In some embodiments, the step of converting the target text into the target text speech specifically includes:

[0019] Converting target text into target text speech;

[0020] The corresponding identifier is marked at the time position corresponding to the identifier position of each text segment in the target text speech.

[0021] In some embodiments, the step of inserting the target background sound into the target text speech at a position corresponding to the text segment to synthesize the audio book specifically includes:

[0022] Step S141: finding a time position in the target text speech that is marked with an identifier corresponding to the target background sound identifier;

[0023] Step S142: inserting the corresponding target background sound at the time position to synthesize the audio book.

[0024] In some embodiments, the duration of each target background sound is less than or equal to the duration of the corresponding text segment in the target text speech;

[0025] The volume of each target background sound is lower than or equal to the volume of the speech at the corresponding time position in the target text speech.

[0026] In a second aspect, an embodiment of the present invention further provides a device for producing an audio book, the device for producing an audio book comprising:

[0027] A recognition and extraction unit, used for recognizing and extracting text segments in the target text where background sound should be inserted;

[0028] A background sound generating unit, configured to generate a target background sound according to the content of the extracted text segment;

[0029] A text-to-speech conversion unit, used for converting a target text into a target text-to-speech;

[0030] The audio book synthesis unit is used to insert the target background sound into the target text speech at the position corresponding to the text segment to synthesize the audio book.

[0031] In a third aspect, an embodiment of the present invention further provides a computer device, which includes a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above method when executing the computer program.

[0032] In a fourth aspect, an embodiment of the present invention further provides a storage medium, wherein the storage medium stores a computer program, wherein the computer program includes program instructions, and the program instructions can implement the above method when executed by a processor.

[0033] The embodiment of the present invention provides a method, device, computer equipment and storage medium for producing an audio book. The method includes: identifying and extracting a text segment in a target text where background sound should be inserted; generating a target background sound according to the content of the extracted text segment; converting the target text into a target text speech; adding the target background sound at a position corresponding to the text segment in the target text speech to synthesize the audio book. The method for producing an audio book provided by the embodiment of the present invention synthesizes the audio book by inserting a target background sound matching the text content at the time position where the background sound needs to be inserted in the target text speech. Since the background sound matching the text content is inserted at the corresponding time position, the audio book has a rich sense of sound layering, and is lively and interesting to listen to, making the audience like to listen to audio books more. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0035] Figure 1 A schematic diagram of a process for producing an audio book provided by an embodiment of the present invention;

[0036] Figure 2 A schematic diagram of a sub-process of a method for producing an audio book provided by an embodiment of the present invention;

[0037] Figure 3A schematic diagram of a sub-flow diagram of a method for producing an audio book provided by another embodiment of the present invention;

[0038] Figure 4 A schematic diagram of a sub-flow diagram of a method for producing an audio book provided by another embodiment of the present invention;

[0039] Figure 5 A schematic flow chart of a method for producing an audio book provided in another embodiment of the present invention;

[0040] Figure 6 A schematic block diagram of an audio book production device provided by an embodiment of the present invention;

[0041] Figure 7 A schematic block diagram of a recognition and extraction unit of an audio book production device provided in an embodiment of the present invention;

[0042] Figure 8 A schematic block diagram of a background sound generating unit of an audio book production device provided by an embodiment of the present invention;

[0043] Fig. 9 A schematic block diagram of an audio book synthesis unit of an audio book production device provided in an embodiment of the present invention;

[0044] Fig.10 A schematic block diagram of an audio book production device provided by another embodiment of the present invention; and

[0045] Fig.11 A schematic block diagram of a computer device provided in 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 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] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0048] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0049] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0050] See also Figure 1 , Figure 1 A schematic flow chart of a method for producing an audio book provided by an embodiment of the present invention. As shown in the figure, the method for producing an audio book includes the following steps S110-140.

[0051] S110, identifying and extracting text segments in the target text into which background sound should be inserted.

[0052] In one embodiment, if Figure 2 As shown, the step S110 may include steps S111-S113.

[0053] S111, identifying text segments in the target text into which background sound should be inserted.

[0054] This step S111 specifically includes: analyzing the title and text content of each chapter of the target text to find out the text segment describing the background sound. The text segment describing the background sound is the text segment into which the background sound should be inserted. For example, the content of a text segment in a certain chapter is: "There is a horse galloping in front, making a whirring sound." It can be seen from the text content that there is a sentence describing the background sound in the text segment. That is, the text segment: "There is a horse galloping in front, making a whirring sound" is the text segment into which the background sound should be inserted.

[0055] S112: Mark each text segment according to its position in the target text.

[0056] This step S112 specifically includes: firstly determining the number of text segments in the target text where background sounds should be inserted, and marking each text segment according to the sequence position of each text segment in the target text. The identification of each text segment is different from the identification of other text segments; specifically, digital numbering, letter numbering, or other forms of numbering can be used; for example, assuming that there are 6 text segments in the target text where background sounds should be inserted, the 6 text segments can be marked in sequence at the positions of the 1st to 6th text segments according to their sequence positions in the target text: number 1, number 2, number 3, number 4, number 5, number 6. The marked text segment position can be any position of the text segment, such as the starting position of the text segment, the ending position of the text segment, the middle position of the text segment, or the starting and ending positions of the text segment.

[0057] S113, extracting each text segment after the mark.

[0058] The text segments extracted in this step are used in the subsequent steps to generate the corresponding target background sounds.

[0059] S120: Generate target background sound according to the extracted content of the text segment.

[0060] In one embodiment, step S120 includes: performing content analysis on each extracted text segment, and generating a target background sound with a corresponding identifier for each text segment according to the analysis result. Specifically: according to the content of each extracted text segment, the background sound type of the corresponding text segment is analyzed and determined; for each text segment, a target background sound carrying a corresponding identifier is generated according to the background sound type. For example, assuming that the content of a text segment identified as number 1 is: "There is a horse galloping in front, making a whirring sound", it can be analyzed and determined that the background sound type of the text segment is: the sound of a horse galloping, and then a target background sound carrying a horse galloping with an identifier of number 1 is generated. The specific generation process can be: searching for the background sound of a single horse running and galloping in a preset background sound library, extracting the background sound found, and inserting number 1 into the extracted background sound, that is, obtaining the target background sound identified as number 1. The identifier in the target text and the identifier in the target background sound can be the same or different. When the identifiers of the two are different, a one-to-one mapping relationship between the two needs to be established. For example, if the identifiers in the target text are identified by numbers and the identifiers in the target background sound are identified by uppercase letters, it is necessary to establish a one-to-one mapping relationship between the digital identifiers and the uppercase letter identifiers, as shown in Table 1. In the process of generating the target background sound, it is necessary to add uppercase letter identifiers that establish a mapping relationship with the digital identifiers of the corresponding text fragments in the target background sound according to the mapping relationship Table 1.

[0061] S130: Convert the target text into target text speech.

[0062] In one embodiment, if Figure 3 As shown, the step S130 may include steps S131-S132.

[0063] Step S131: Convert the target text into target text speech.

[0064] This step S131 can specifically use the Text To Speech (TTS) technology in the prior art to convert the target text into the target text speech. Among them, TTS refers to the technology that uses linguistics and psychology at the same time, with the support of the built-in chip, through the design of neural network, to intelligently convert text into natural speech flow.

[0065] Step S132: marking a corresponding identifier at a time position corresponding to the identifier position of each text segment in the target text speech.

[0066] In this embodiment, after the target text is converted into the target text speech, according to the identification position of each text segment in the target text, the corresponding identification is marked at the time position corresponding to the identification position of each text segment in the target text speech. Of course, in the process of converting the target text into the target text speech, according to the identification position of each text segment in the target text, the corresponding identification is marked at the time position corresponding to the identification position of each text segment in the target text speech. For example, when the identification of each text segment is marked at the starting position of the corresponding text segment, the corresponding identification is marked at the time position corresponding to the starting position of each text segment in the target text speech. Similarly, the identification of each text segment in the target text and the corresponding identification in the target text speech can be the same or different. For example, the identification at the starting position of a certain text segment of the target text is numbered 1, then the time position corresponding to the position marked as numbered 1 in the target text speech is marked as numbered 1. When the identification in the target text and the corresponding identification in the target text speech are different, it is necessary to establish a one-to-one mapping relationship between the two. For example, if the identifiers in the target text are digitally identified and the identifiers in the target text speech are lowercase letter identifiers, it is necessary to establish a one-to-one mapping relationship between the digital identifiers and the lowercase letter identifiers, as shown in Table 1. In the process of generating the target text speech, it is necessary to match the lowercase letter identifiers with the time position mark corresponding to the digital identifier position of each text segment in the target text speech according to the mapping relationship.

[0067] Mapping relationship table 1:

[0068]

[0069]

[0070] S140: inserting the target background sound into the target text speech at a position corresponding to the text segment, and synthesizing to obtain the audio book.

[0071] In one embodiment, as shown in FIG. 4 , the step S140 may include steps S141 - S142 .

[0072] Step S141: Find the time position marked with an identifier corresponding to each target background sound identifier in the target text speech.

[0073] In this embodiment, when a text segment has a corresponding identifier that is the same in the target text and the target background sound, and is also the same in the target text and the target text speech, it indicates that it is also the same in the target text speech and the target background sound; at this time, this step S141 only needs to find the time position marked with an identifier that is the same as each target background sound identifier in the target text speech. When a text segment has a corresponding identifier that is a one-to-one mapping relationship between the target text and the target background sound, and is also a one-to-one mapping relationship between the target text and the target text speech, it indicates that it also has a one-to-one mapping relationship between the target text speech and the target background sound, as shown in Table 1. At this time, this step S141 needs to find the time position marked with an identifier that establishes a mapping relationship with each target background sound identifier in the target text speech based on the established mapping relationship.

[0074] Step S142: inserting the corresponding target background sound at the time position to synthesize the audio book.

[0075] In one embodiment, the duration of the target background sound is less than or equal to the duration of the corresponding text segment in the target text speech; the volume of the target background sound is lower than or equal to the volume of the speech at the corresponding time position in the target text speech. Generally, the duration can be set to 3 seconds to 5 seconds, which can enrich the sound layering in the audiobook without affecting the original target text speech in the audiobook.

[0076] In one embodiment, as shown in FIG. 5 , before the step S110 of identifying and extracting the text segment in the target text where the background sound should be inserted, the following steps are further included:

[0077] S101, selecting required text according to target user needs, regularizing the required text, and obtaining target text.

[0078] The step S101 of regularizing the required text specifically includes: removing various formats in the required text, such as pictures, watermarks, etc., and only retaining the text itself and punctuation marks. The required text may be a novel, story, script, poem, lyric, song, fu, etc.

[0079] In some embodiments, the target users may be user groups of various age groups, such as elderly groups, middle-aged groups, young people groups, adolescent groups, or infant groups, or other specific groups, such as literature enthusiasts groups, history enthusiasts groups, and the like.

[0080] In some embodiments, the target background sound may be various environmental background sounds such as music, crowd noise, animal calls, object collision sounds, wind, rain, and water flow.

[0081] The audio book production method provided in the embodiment of the present invention synthesizes an audio book by inserting a target background sound matching the text content at the time position where the background sound needs to be inserted in the target text speech. Since the background sound matching the text content is inserted at the corresponding time position, the sound layering of the audio book is rich, and it is vivid and interesting to listen to, so that the audience likes to listen to the audio book more.

[0082] Figure 6 is a schematic block diagram of an audio book production device provided by an embodiment of the present invention. Figure 6 As shown, it corresponds to the above audio book production method. The audio book production device includes a unit for executing the above audio book production method, and the device can be configured in a terminal such as a desktop computer, a tablet computer, a laptop computer, a smart speaker, etc. For details, please refer to Figure 6 The audio book production device 100 includes: an identification and extraction unit 110, a background sound generation unit 120, a text-to-speech conversion unit 130, and an audio book synthesis unit 140. The identification and extraction unit 110 is used to identify and extract the text segment in the target text where the background sound should be inserted. The background sound generation unit 120 is used to generate the target background sound according to the content of the extracted text segment. The text-to-speech conversion unit 130 is used to convert the target text into a target text speech. The audio book synthesis unit 140 is used to insert the target background sound into the target text speech at the position corresponding to the text segment to synthesize the audio book.

[0083] The audio book production device 100 provided in the embodiment of the present invention synthesizes an audio book by inserting a target background sound matching the text content at the time position where the background sound needs to be inserted in the target text speech. Since the background sound matching the text content is inserted at the corresponding time position, the sound layering of the audio book is rich, and it is vivid and interesting to listen to, making the audience like listening to audio books more.

[0084] In one embodiment, if Figure 7As shown, the recognition and extraction unit 110 includes: a recognition subunit 111, a marking subunit 112, and an extraction subunit 113. The recognition subunit 111 is used to recognize the text segment in the target text where the background sound should be inserted. The marking subunit 112 is used to mark each text segment according to the sequence position of each text segment in the target text. The extraction subunit 113 is used to extract each marked text segment.

[0085] The identification subunit 111 is specifically used to analyze the title and text content of each chapter of the target text to find out the text segment describing the background sound. The text segment describing the background sound is the text segment into which the background sound should be inserted. For example, the content of a text segment in a certain chapter is: "There is a horse galloping in front, making a whirring sound." It can be seen from the text content that there is a sentence describing the background sound in the text segment. That is, the text segment: "There is a horse galloping in front, making a whirring sound" is the text segment into which the background sound should be inserted.

[0086] The marking subunit 112 is specifically used to first determine the number of text segments in the target text where background sounds should be inserted, and mark each text segment according to the order of each text segment in the target text. The identification of each text segment is different from the identification of other text segments; specifically, digital numbering, letter numbering, or other forms of numbering can be used; for example, assuming that there are 6 text segments in the target text where background sounds should be inserted, the 6 text segments can be marked in sequence at the positions of the 1st to 6th text segments according to their order in the target text: number 1, number 2, number 3, number 4, number 5, number 6. The position of the marked text segment can be any position of the text segment, such as the starting position of the text segment, the ending position of the text segment, the middle position of the text segment, or the starting and ending positions of the text segment.

[0087] In one embodiment, the background sound generation unit 120 is specifically used to perform content analysis on each extracted text segment, and generate a target background sound with a corresponding identifier for each text segment according to the analysis result. Specifically: the background sound generation unit 120 analyzes and determines the background sound type of the corresponding text segment according to the content of each extracted text segment; for each text segment, the target background sound carrying the corresponding identifier is generated according to the background sound type. For example, assuming that the content of a text segment identified as number 1 is: "There is a horse galloping in front, making a whirring sound", it can be analyzed and determined that the background sound type of the text segment is: the sound of a horse galloping, and then a target background sound carrying the identifier number 1 is generated. The specific generation process can be: searching for the background sound of a single horse running and galloping in a preset background sound library, extracting the background sound found, and inserting number 1 into the extracted background sound, that is, obtaining the target background sound identified as number 1. The identifier in the target text and the identifier in the target background sound can be the same or different. When the identifiers of the two are different, a one-to-one mapping relationship between the two needs to be established. For example, if the identifiers in the target text are identified by numbers and the identifiers in the target background sound are identified by uppercase letters, it is necessary to establish a one-to-one mapping relationship between the digital identifiers and the uppercase letter identifiers, as shown in Table 1. In the process of generating the target background sound, it is necessary to add uppercase letter identifiers in the target background sound that establish a mapping relationship with the digital identifiers of the corresponding text fragments based on the mapping relationship.

[0088] In one embodiment, if Figure 8As shown, the text-to-speech conversion unit 130 includes: a text-to-speech conversion subunit 131 and a first marking subunit 132. The text-to-speech conversion subunit 131 is used to convert the target text into the target text-to-speech. The text-to-speech conversion subunit 131 can specifically use the Text To Speech (TTS) technology in the prior art to realize the conversion of the target text into the target text-to-speech. TTS refers to the technology of converting text into a natural speech stream intelligently by using linguistics and psychology, under the support of the built-in chip, through the design of a neural network. The first marking subunit 132 is used to mark the corresponding mark at the time position corresponding to the mark position of each text segment in the target text-to-speech. The first marking subunit 132 marks the corresponding mark at the time position corresponding to the mark position of each text segment in the target text-to-speech during the process of the text-to-speech conversion subunit 131 converting the target text into the target text-to-speech. For example, when the mark of each text segment is marked at the starting position of the corresponding text segment, the corresponding mark is marked at the time position corresponding to the starting position of each text segment in the target text-to-speech. Similarly, the identifier of each text segment in the target text and the corresponding identifier in the target text speech may be the same or different. For example, if the identifier at the starting position of a text segment of the target text is numbered 1, then the time position corresponding to the position marked as numbered 1 in the target text speech is marked as numbered 1. When the identifier in the target text and the corresponding identifier in the target text speech are different, it is necessary to establish a one-to-one mapping relationship between the two. For example, if the identifier in the target text is identified by numbers and the identifier in the target text speech is identified by lowercase letters, it is necessary to establish a one-to-one mapping relationship between the digital identifier and the lowercase letter identifier, as shown in Table 1. In the process of generating the target text speech, it is necessary to match the lowercase letter identifier corresponding to the time position mark of each text segment digital identifier position in the target text speech according to the mapping relationship.

[0089] In one embodiment, if Fig. 9 As shown, the audio book synthesis unit 140 includes: an identifier search subunit 141 and a background sound insertion subunit 142. The identifier search subunit 141 is used to find the time position marked with an identifier corresponding to the target background sound identifier in the target text speech. The background sound insertion subunit 142 is used to insert the corresponding target background sound at the time position to synthesize the audio book.

[0090] In the present embodiment, when a certain text segment, its corresponding identification is the same in the target text and the target background sound, and is the same in the target text and the target text voice, it indicates that it is also the same in the target text voice and the target background sound. At this time, the identification search subunit 141 only needs to find the time position marked with the identification that is the same as each target background sound identification in the target text voice. When a certain text segment, its corresponding identification is a one-to-one mapping relationship between the target text and the target background sound, and is a one-to-one mapping relationship between the target text and the target text voice, it indicates that it also has a one-to-one mapping relationship between the target text voice and the target background sound, as shown in Table 1, at this time, the identification search subunit 141 needs to find the time position marked with the identification that establishes a mapping relationship with each target background sound identification in the target text voice according to the established mapping relationship.

[0091] In one embodiment, the duration of each target background sound is less than or equal to the duration of the corresponding text segment in the target text speech. The volume of each target background sound is lower than or equal to the voice volume at the corresponding time position in the target text speech. The volume of the target background sound is lower than or equal to the voice volume at the corresponding time position in the target text speech. The general duration can be set to 3 seconds to 5 seconds, which can enrich the sound layering in the audio book without affecting the original target text speech in the audio book.

[0092] In one embodiment, if Fig.10 As shown, the audio book production device 100 further includes: a text selection unit 150. The text selection unit 150 is used to select the required text according to the target user's needs, and regularize the required text to obtain the target text. Among them, regularizing the required text specifically includes: removing various formats in the required text, such as pictures, watermarks, etc., and only retaining the text itself and punctuation marks. Among them, the required text can be a novel, a story, a script, a poem, a lyric, a song, a fu, etc.

[0093] In some embodiments, the target users may be user groups of various age groups, such as elderly groups, middle-aged groups, young people groups, adolescent groups, or infant groups, or other specific groups, such as literature enthusiasts groups, history enthusiasts groups, and the like.

[0094] In some embodiments, the target background sound may be various environmental background sounds such as music, crowd noise, animal calls, object collision sounds, wind, rain, and water flow.

[0095] The audio book production device can be implemented in the form of a computer program. Fig.11 Runs on the computer device shown.

[0096] See also Fig.11 , Fig.11 2 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device 200 may be a terminal or a server, wherein the terminal may be an electronic device with communication functions such as a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a personal digital assistant, and a wearable device. The server may be an independent server or a server cluster composed of multiple servers.

[0097] See also Fig.10 The computer device 200 includes a processor 202 , a memory and a network interface 205 connected via a system bus 201 , wherein the memory may include a non-volatile storage medium 203 and an internal memory 204 .

[0098] The non-volatile storage medium 203 can store an operating system 2031 and a computer program 2032. The computer program 2032 includes program instructions, and when the program instructions are executed, the processor 202 can execute a **** method.

[0099] The processor 202 is used to provide computing and control capabilities to support the operation of the entire computer device 200 .

[0100] The internal memory 204 provides an environment for the operation of the computer program 2032 in the non-volatile storage medium 203. When the computer program 2032 is executed by the processor 202, the processor 202 can execute a **** method.

[0101] The network interface 205 is used to communicate with other devices over the network. Those skilled in the art will appreciate that Fig.11 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device 200 to which the solution of the present application is applied. The specific computer device 200 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0102] The processor 202 is used to run a computer program 2032 stored in a memory to implement the following steps: identifying and extracting a text segment in a target text into which background sound should be inserted; generating a target background sound based on the content of the extracted text segment; converting the target text into a target text speech; inserting the target background sound into the target text speech at a location corresponding to the text segment to synthesize the audio book.

[0103] In one embodiment, before implementing the step of identifying and extracting the text segment in the target text where the background sound should be inserted, the processor 202 also implements the following steps: selecting the required text according to the needs of the target user, regularizing the required text, and obtaining the target text.

[0104] In one embodiment, when the processor 202 implements the step of identifying and extracting the text segment in the target text where background sound should be inserted, it specifically implements the following steps: identifying the text segment in the target text where background sound should be inserted; marking each text segment according to the sequence position of each text segment in the target text; and extracting each marked text segment.

[0105] In one embodiment, when the processor 202 implements the step of generating the target background sound according to the content of the text segment, it specifically implements the following steps: performing content analysis on each extracted text segment, and generating a target background sound with a corresponding identifier for each text segment according to the analysis result.

[0106] In one embodiment, when the processor 202 implements the step of converting the target text into the target text speech, it specifically implements the following steps: converting the target text into the target text speech; marking a corresponding identifier at a time position corresponding to the identifier position of each text segment in the target text speech.

[0107] In one embodiment, when the processor 202 implements the step of inserting the target background sound at a position corresponding to the text segment in the target text speech to synthesize the audio book, it specifically implements the following steps: finding a time position marked with an identifier corresponding to the target background sound identifier in the target text speech; inserting the corresponding target background sound at the time position to synthesize the audio book.

[0108] It should be understood that in the embodiment of the present application, the processor 202 may be a central processing unit (CPU), and the processor 202 may also be 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. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0109] It can be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0110] Therefore, the present invention also provides a storage medium. The storage medium can be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions. When the program instructions are executed by a processor, the processor executes the following steps: identifying and extracting a text segment in a target text into which background sound should be inserted; generating a target background sound according to the content of the extracted text segment; converting the target text into a target text speech; inserting the target background sound into the target text speech at a position corresponding to the text segment, and synthesizing the audio book.

[0111] In one embodiment, before executing the program instructions to implement the step of identifying and extracting the text segment in the target text where background sound should be inserted, the processor also implements the following steps: selecting the required text according to the needs of the target user, regularizing the required text, and obtaining the target text.

[0112] In one embodiment, when the processor executes the program instructions to implement the step of identifying and extracting the text segment in the target text where background sound should be inserted, the processor specifically implements the following steps: identifying the text segment in the target text where background sound should be inserted; marking each text segment according to the sequence position of each text segment in the target text; and extracting each marked text segment.

[0113] In one embodiment, when the processor executes the program instructions to implement the step of generating the target background sound according to the content of the text fragment, it specifically implements the following steps: performing content analysis on each extracted text fragment, and generating a target background sound with a corresponding identifier for each text fragment according to the analysis results.

[0114] In one embodiment, when the processor executes the program instructions to implement the step of converting the target text into target text speech, it specifically implements the following steps: converting the target text into target text speech; marking a corresponding identifier at a time position corresponding to the identifier position of each text segment in the target text speech.

[0115] In one embodiment, when the processor executes the program instructions to implement the step of inserting the target background sound at the position corresponding to the text segment in the target text speech to synthesize the audio book, the processor specifically implements the following steps: finding the time position marked with an identifier corresponding to the target background sound identifier in the target text speech; inserting the corresponding target background sound at the time position to synthesize the audio book.

[0116] The storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which are computer-readable storage media that can store program codes.

[0117] 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, 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 terms of function in the above description. 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 the present invention.

[0118] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0119] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0120] 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 storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0121] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for producing an audio book, characterized in that: include: Identify and extract text segments in the target text where background sound should be inserted; generating a target background sound according to the extracted content of the text segment; Converting target text into target text speech; The target background sound is inserted into the target text speech at a position corresponding to the text segment, and the audio book is synthesized.

2. The method for producing an audio book according to claim 1, characterized in that: The step of identifying and extracting the text segment in the target text into which the background sound should be inserted also includes: Select the required text according to the needs of the target users, regularize the required text, and obtain the target text.

3. The method for producing an audio book according to claim 1 or 2, characterized in that: The step of identifying and extracting the text segment in the target text into which the background sound should be inserted specifically includes: Identify text segments in the target text where background sound should be inserted; Mark each text segment according to its position in the target text; Extract each text segment after the token identification.

4. The method for producing an audio book according to claim 3, characterized in that: The step of generating the target background sound according to the content of the text segment specifically includes: Content analysis is performed on each extracted text segment, and a target background sound with a corresponding identifier is generated for each text segment according to the analysis result.

5. The method for producing an audio book according to claim 4, characterized in that: The step of converting the target text into the target text speech specifically comprises: Converting target text into target text speech; The corresponding identifier is marked at the time position corresponding to the identifier position of each text segment in the target text speech.

6. The method for producing an audio book according to claim 5, characterized in that: The step of inserting the target background sound into the target text speech at a position corresponding to the text segment to synthesize the audio book specifically includes: Finding a time position in the target text speech that is marked with an identifier corresponding to the target background sound identifier; The corresponding target background sound is inserted at the time position to synthesize the audio book.

7. The method for producing an audio book according to claim 6, characterized in that: The duration of each target background sound is less than or equal to the duration of the corresponding text segment in the target text speech; The volume of each target background sound is lower than or equal to the volume of the speech at the corresponding time position in the target text speech.

8. An audio book production device, characterized in that: include: A recognition and extraction unit, used for recognizing and extracting text segments in the target text where background sound should be inserted; A background sound generating unit, configured to generate a target background sound according to the content of the extracted text segment; A target text-to-speech conversion unit, used for converting a target text into a target text-to-speech; The audio book synthesis unit is used to insert the target background sound into the target text speech at the position corresponding to the text segment to synthesize the audio book.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the method according to any one of claims 1 to 7 can be implemented.

Images