Audio generation method and apparatus, device, and storage medium

By obtaining the character attributes in literary works, it solves the problem that traditional solutions cannot meet the timbre needs of multiple characters, improves user experience and generation efficiency, and achieves efficient and low-cost audio literary works.

WO2024234970A1PCT designated stage expired Publication Date: 2024-11-21BEIJING YOUZHUJU NETWORK TECH CO LTD
View PDF 11 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2024/089927
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-12
Filing Date
2024-04-25
Publication Date
2024-11-21

AI Technical Summary

Technical Problem

The existing technology is difficult to generate audio literary works with multiple characters dubbing. The traditional solution can only generate a single tone, which cannot meet the different styles of tone requirements of different characters in the novel, resulting in poor user listening experience, and high manual dubbing costs, long cycles, and efficiency. Low.

Method used

By obtaining the character attributes of multiple characters in a literary work, determining the target sound characteristics based on these attributes, generating voice audio clips corresponding to each character, and combining them into complete audio, achieving multi-character playback and efficient audio literature Work generation.

Benefits of technology

It realizes the auditory effect of multi-character playback, improves the listening sensory experience and comfort of audio literary works, reduces the generation cost and cycle, improves efficiency, and can quickly and conveniently convert silent literary works into audio products.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2024089927_21112024_PF_FP_ABST
    Figure CN2024089927_21112024_PF_FP_ABST
Patent Text Reader

Abstract

The embodiments of the present disclosure provide an audio generation method and apparatus, a device, and a storage medium. The method comprises: obtaining character attributes corresponding to a plurality of characters in a literary work, and obtaining corresponding utterances which take as objects the plurality of characters; for each of the plurality of characters, based on the character attributes of the character, determining target sound characteristics of said character, and based on the target sound characteristics, generating a voice audio clip corresponding to a target utterance which takes the character as an object; and thus generating audio for the literary work at least on the basis of corresponding voice audio clips generated for the plurality of characters. The invention thus allows for conveniently and quickly generating, based on the characters of a literary work, audio of various timbres for the literary work, and ensures audio generation efficiency while improving the sensory experience of listening to the generated audio.
Need to check novelty before this filing date? Find Prior Art

Description

Audio generation method, device, equipment and storage medium

[0001] This application claims priority to the Chinese invention patent application entitled “Audio generation method, apparatus, device and storage medium” filed on May 12, 2023, with application number 202310538963.6. The entire contents of that application are incorporated by reference into this application. Technical Field

[0002] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to audio generation methods, apparatuses, devices, and computer-readable storage media. Background Art

[0003] With the rapid development of communication technology and smart devices, more and more applications are providing users with various types of audio, bringing numerous conveniences. Currently, some long-form audio products, such as audiobooks and blogs, are entering a period of rapid development. For example, audiobook applications can play the corresponding audio of books for users, allowing users to "read" the books without actually reading them. In view of this, it is desirable to be able to easily and quickly generate corresponding audio for literary works such as books, so as to provide users with more audio products.

[0004] Summary of the Invention

[0005] In a first aspect of the present disclosure, an audio generation method is provided. The method comprises: obtaining corresponding character attributes of multiple characters in a literary work and corresponding utterances centered on the multiple characters; determining, for each of the multiple characters based on the character attributes, target voice characteristics for the character; and generating, based on the target voice characteristics, a speech audio segment corresponding to a target utterance centered on the character; and generating audio for the literary work based on at least the corresponding speech audio segments generated for the multiple characters.

[0006] In a second aspect of the present disclosure, an audio generation device is provided. The device includes: an acquisition module configured to acquire corresponding character attributes of multiple characters in a literary work and corresponding utterances with the multiple characters as the main body; a segment generation module configured to determine, for each of the multiple characters, target sound characteristics for the character based on the character attributes, and generate, based on the target sound characteristics, a speech audio segment corresponding to a target utterance with the character as the main body; and a segment combination module configured to generate audio for the literary work based on at least the corresponding speech audio segments generated for the multiple characters.

[0007] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the device to perform the method of the first aspect.

[0008] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.

[0009] It should be understood that the content described in this summary section is not intended to limit the key features or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0011] FIG1 shows a schematic diagram of an example environment in which embodiments of the present disclosure can be implemented;

[0012] FIG2 shows a schematic diagram of an example architecture for audio generation according to some embodiments of the present disclosure;

[0013] FIG3 is a schematic diagram showing an example of generating speech audio according to some embodiments of the present disclosure;

[0014] FIG4 is a schematic diagram showing an example of generating additional audio segments according to some embodiments of the present disclosure;

[0015] FIG5 shows a flowchart of a process for audio generation according to some embodiments of the present disclosure;

[0016] FIG6 shows a schematic structural block diagram of an apparatus for audio generation according to certain embodiments of the present disclosure; and

[0017] FIG7 illustrates a block diagram of an electronic device in which one or more embodiments of the present disclosure may be implemented. DETAILED DESCRIPTION

[0018] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0019] For example, in response to a user's active request, a prompt message is sent to the user to clearly inform the user that the operation requested will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operations of the disclosed technical solution based on the prompt message.

[0020] As an optional but non-limiting implementation, in response to receiving a user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. Furthermore, the pop-up window may also contain a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0021] It is understandable that the above notification and user authorization process are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0022] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) must comply with the requirements of relevant laws, regulations and relevant provisions.

[0023] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0024] It should be noted that the titles of any section / subsection provided herein are not limiting. Various embodiments are described throughout this document, and any type of embodiment may be included under any section / subsection. Furthermore, the embodiments described in any section / subsection may be combined in any manner with any other embodiments described in the same section / subsection and / or in different sections / subsections.

[0025] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below. The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may be included below.

[0026] As used herein, the term "literary work" refers to a medium that uses words, pictures, images, and / or other symbols to reflect real or virtual society. In the embodiments of the present disclosure, the genres of literary works include but are not limited to novels, plays, fables, fairy tales, comics, etc.

[0027] As briefly mentioned above, we hope to convert more literary works into corresponding audio, bringing greater convenience to users. Taking novels as an example, audiobooks synthesized using artificial intelligence (AI) are developing towards improving listening comfort and experience. These audiobooks are typically generated based on the novel's content using text-to-speech (TTS) technology.

[0028] TTS technology can perform linguistic analysis on text content. Specifically, it analyzes the vocabulary, grammar, and semantics of each sentence to determine the underlying structure of the sentence and the phoneme composition of each word. Furthermore, it can extract the words or phrases corresponding to the processed text from a speech synthesis library, convert the linguistic description into a speech waveform, and generate the corresponding audio.

[0029] Currently, some applications (for example, reading applications, audiobook applications, etc.) have provided audio novels that are broadcast in a single tone (also called unicast) using TTS technology. However, traditional solutions can only generate audio with a single tone, and cannot provide different characters in the novel with different styles of timbre. The audio novels generated in this way have a poor listening experience for users. On the other hand, the solution of manually dubbing literary works to generate audio can meet the requirements for the authenticity of the audio corresponding to the literary works. For example, it can provide audio novels with multi-character broadcasts (also called multicast). However, the high cost of manual production and the long production cycle greatly limit the efficiency of audio generation.

[0030] Embodiments of the present disclosure provide a solution for audio generation. According to various embodiments of the present disclosure, character attributes of multiple characters and speeches with the characters as the main body are obtained from a literary work. Based on the character attributes of each character, the voice characteristics (e.g., timbre) of the character are determined, and then the determined voice characteristics are used to generate a voice audio segment corresponding to the speech of the character. At least the voice audio segments corresponding to the multiple characters are combined into audio for the literary work, also known as "audio literary work."

[0031] According to the embodiments of the present disclosure, the different voice characteristics of characters with different attributes are taken into account in the production of audio literary works. This creates an auditory effect of multiple characters playing together. Furthermore, by taking character attributes into account, the listening experience and comfort of the generated audio literary works are improved, achieving a precise interpretation of the content of the literary works. In this way, originally silent literary works can be easily and quickly converted into audio products, thereby improving the efficiency of audio literary work production. This helps provide users with more and more vivid audio literary works.

[0032] Sample Environment

[0033] Figure 1 shows a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. As shown in Figure 1, the environment 100 may include an electronic device 110, which may obtain a literary work 120 for which audio is to be generated.

[0034] The literary work 120 depicts a plurality of characters, and each character has corresponding speech. It should be noted that the character can be any image with corresponding speech, including but not limited to people, animals, plants, objects, etc. For example, the character can be a talking potato or a talking dog, etc.

[0035] Literary work 120 may be provided to electronic device 110 in any suitable format. In some embodiments, the content of literary work 120 itself (e.g., the text of a novel, digital graphic data of a comic) may be provided to electronic device 110. Alternatively or additionally, metadata describing the composition of literary work 120 (if any) may be provided to electronic device 110. Alternatively or additionally, information extracted from literary work 120 (such as that described below) may be provided to electronic device 110; such information may be extracted from literary work 110 by other devices or may be manually generated.

[0036] In the environment 100, the electronic device 110 can be any type of device with computing capabilities, including a terminal device or a server device. The terminal device can be any type of mobile terminal, fixed terminal, or portable terminal, including a mobile phone, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio / video player, a digital camera / camcorder, a positioning device, a television receiver, a radio broadcast receiver, an e-book device, a gaming device, or any combination thereof, including accessories and peripherals of these devices or any combination thereof.

[0037] A server-side device can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks, and big data and artificial intelligence platforms. Server-side devices can include, for example, computing systems / servers such as mainframes, edge computing nodes, and electronic devices in cloud environments.

[0038] The electronic device 110 may generate audio 130 for the literary work 120. In some embodiments, the electronic device 110 may utilize one or more trained machine learning models to generate the audio. These trained models may be deployed in the electronic device 110 or in other devices accessible to the electronic device 110.

[0039] Audio 130 is audio corresponding to literary work 120, also known as an audio literary work or an audio form of a literary work. Audio 130 includes at least audio corresponding to the speech of multiple characters in literary work 120. In some embodiments, audio 130 may also include audio corresponding to narration in literary work 120. Additionally, in some embodiments, audio 130 may include audio signals associated with the scene depicted in literary work 120, such as ambient sound effects, background music, and the like.

[0040] It should be understood that the structure and functionality of the environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure. The audio generation scheme according to embodiments of the present disclosure may be implemented on any number of devices.

[0041] Some example embodiments of the present disclosure will be described below with continued reference to the accompanying drawings.

[0042] Example Audio Generation Architecture

[0043] FIG2 shows a schematic diagram of an example architecture 200 for audio generation according to some embodiments of the present disclosure. Generally speaking, the architecture 200 includes an information extraction unit 210, a sound characteristics assignment unit 220, a speech segment generation unit 230, and a segment combination unit 240. These units in the architecture 200 and other units not shown may be implemented in the electronic device 110.

[0044] The information extraction unit 210 is configured to obtain corresponding character attributes of multiple characters in the literary work 120 and corresponding utterances centered around the multiple characters. Additionally, in some embodiments, the information extraction unit 210 may be further configured to obtain scene information 216 associated with scenes in the literary work 120. Scene information 216 describes the attributes of the scenes and the events occurring within them. Specifically, the information extraction unit 210 may obtain character information 212, utterance information 214, and optional scene information 216 from the literary work 120. This information is collectively referred to as structured information of the literary work 120. In other words, the information extraction unit 210 structures the literary work 120.

[0045] In some embodiments, the information extraction unit 210 can automatically extract structured information from the literary work 120. Natural language processing (NLP) technology and / or optical character recognition (OCR) technology, image recognition technology, etc. can be used to identify the content of the literary work 120 to extract the structured information. For example, if the literary work 120 is a pure text novel, the information extraction unit 210 can use any suitable NLP technology to determine the structured information from the text of the literary work 120. For another example, if the literary work 120 is a comic that combines text and graphics, the information extraction unit 210 can use OCR and NLP technologies to extract the structured information.

[0046] Alternatively or additionally, in some embodiments, the information extraction unit 210 may directly obtain structured information from metadata describing the architecture of the literary work 120. For example, if the literary work 120 is a screenplay, the information extraction unit 210 may directly obtain structured information from the screenplay written in a predetermined format. Alternatively, the information extraction unit 210 may semi-automatically obtain structured information. For example, the structured information may be determined from manually annotated literary work 120 based on manually annotated data.

[0047] Alternatively, in some embodiments, the architecture 200 may not include the information extraction unit 210. In such an embodiment, the electronic device 110 may directly obtain structured information generated manually, or obtain structured information provided by other devices.

[0048] The above describes an example of how to obtain structured information. The following describes structured information. Character information 212 includes character identifiers 201 and character attributes 202 for each of the multiple characters in literary work 120. Character identifiers 212 may include, but are not limited to, the character's name (e.g., Xiaoyi, Xiaoer, etc.), the character's identity (e.g., Senior Brother, Master, etc.), the character's image (e.g., different characters in a comic have different images), and so on.

[0049] The character attributes 202 may include one or more attribute dimensions. Examples of attribute dimensions may include, but are not limited to, the age, gender, background, personality (e.g., character setting), camp (e.g., good guy, villain), etc. of the character in the literary work.

[0050] The role identification 201 and the role attributes 202 of each role in the role information 212 correspond to each other. Schematically, if the role attributes of role A need to be obtained, the corresponding role attributes can be directly obtained from the role information 212 based on the identification of role A.

[0051] In some embodiments, different characters have different character identifiers 201, but may have the same character attributes 202. For example, if two characters are twins, their respective character identifiers 201 may be different (e.g., different names), but their character attributes 202 may be the same (e.g., gender, age, personality, etc.).

[0052] Speech information 214 includes narration 203 in the literary work 120 and character speech 204, which is primarily composed of multiple characters. Narration 203 is information other than character speech 204, and includes, but is not limited to, descriptions of the environment, plot, and action. Character speech 204, which is primarily composed of a character, may include, but is not limited to, conversations between that character and other characters (e.g., words spoken by that character to another character), that character's inner monologue, and that character's soliloquy.

[0053] The above generally describes the role information 212 and the utterance information 214. To more clearly understand the embodiments of the present disclosure, the following describes an example process for determining the role information 212 and the utterance information 214. However, it should be understood that the described process is merely exemplary and is not intended to limit the scope of the present disclosure.

[0054] Based on the text of the literary work 120, the information extraction unit 210 can determine a set of candidate characters with names in the literary work 120. For example, any suitable named entity recognition (NER) technique can be used to determine the candidate characters. Alternatively, the information extraction unit 210 can determine the voiceovers and character utterances in the literary work 120. For example, NLP techniques can be used to separate the novel into voiceovers and utterances. Furthermore, the information extraction unit 210 can utilize a speaker determination model to determine the subject of each utterance.

[0055] In some embodiments, the information extraction unit 210 can use the subject of the identified speech to filter the extracted candidate roles. Specifically, for each candidate role in a set of candidate roles, the amount of speech with the candidate role as the subject can be determined. A candidate role whose speech amount is greater than a threshold can be determined as one of the final multiple roles (i.e., a role with a role identifier 201). The amount of speech can be measured in any appropriate unit, such as the number of sentences, the number of words, etc. For example, since the literary work 120 may contain characters that only appear in conversations or memories of other people, such characters may have role attributes but no speech with them as the subject. The information extraction unit 210 can filter out such characters without speech by setting a threshold on the amount of speech as described above, retaining only the real characters with a certain amount of speech, and only extracting the character information 212 corresponding to the characters with a certain amount of speech. In this way, not only can the amount of data processing required for subsequent information extraction and assignment of sound characteristics be reduced, but also a more accurate interpretation of the content of the literary work can be achieved.

[0056] After identifying multiple characters in the literary work 120, the information extraction unit 210 can determine the character attributes 202 for each character. In some embodiments, the information extraction unit 210 can determine, for each of the multiple characters, descriptive information for the character and / or the relationship between the character and other characters in the multiple characters from the literary work. Descriptive information can include, for example, the character's age, identity, and evaluations of the character by other characters in the literary work. Relationships can include, for example, work relationships, family relationships, friendships, and other relationships between the characters in the literary work. Based on the descriptive information and relationships, the character attributes can then be determined.

[0057] In some embodiments, the information extraction unit 210 may match the extracted descriptive information and / or relationships to corresponding labels, where the labels are used to describe one or more dimensions of the character attributes. The information extraction unit 210 may utilize a trained label matching model (e.g., a multi-classifier), or pre-determined label matching rules, or manually annotated information, etc., based on the descriptive information and / or determine the labels associated with the character attributes corresponding to the character. These labels will serve as the character attributes 202 in the character information 212. For example, there may be a lot of descriptive information about the personality of a certain character in the literary work 120. The information extraction unit 210 may match several corresponding labels based on this descriptive information, thereby ensuring the accuracy and conciseness of the character attributes 202.

[0058] The above describes an example acquisition of character information 212 and speech signal 214. Continuing with architecture 200, character information 212 is provided to voice characteristic assignment unit 220. Voice characteristic assignment unit 220 is configured to determine, for each character in a plurality of characters, a target voice characteristic for that character based on character attributes 202 of that character. In this context, a voice characteristic may include any suitable acoustic feature, such as timbre, pitch, loudness, or a combination thereof.

[0059] The speech information 214 is provided to the speech segment generation unit 230 along with the target sound characteristics corresponding to each of the multiple characters determined by the sound characteristic assignment unit 220. The speech segment generation unit 230 is configured to generate a speech audio segment corresponding to a target speech with the character as the subject, based on the target sound characteristics. It is understood that in the literary work 120, the speech with a certain character as the subject may include multiple segments, such as those in different scenes or at different times in the same scene. In this case, the speech audio segment for the character may include sub-segments corresponding to the multiple segments.

[0060] The corresponding speech audio segments generated for the multiple characters are provided to the segment combination unit 240. The segment combination unit 240 is configured to generate the audio 130 for the literary work 120 based on at least the corresponding speech audio segments generated for the multiple characters. That is, the segment combination unit 240 at least combines the speech audio segments into an audible literary work.

[0061] In the embodiment of the present disclosure, different roles are matched with voice characteristics (e.g., timbre) that are adapted to their attributes, and automatic voice characteristic allocation is achieved. In this way, the effect of multiple people speaking can be achieved.

[0062] In some embodiments, in order to further improve the listening experience of the voice audio segment generated by the voice segment generation unit 230, the speech information 214 may also include the emotional characteristics 205 of the character's speech 204. For example, for the target speech of the character, the information extraction unit 210 can determine the emotional characteristics 205 contained in the target speech based on the content and context of the target speech. It should be noted that the emotions contained in different speeches may be different, and the emotions contained in speeches with the same content in different environments may be different. In addition, as mentioned above, a character's speech may include multiple paragraphs, and different emotions may be contained in each paragraph or even different sentences in a paragraph. Therefore, the information extraction unit 210 can determine the corresponding emotional characteristics 205 for each paragraph (or each sentence) of the character.

[0063] In this embodiment, the emotional characteristics 205 are also provided to the speech segment generation unit 230. Based on the target sound characteristics and the emotional characteristics 205, the speech segment generation unit 230 converts the text of the target utterance into a speech audio segment. Compared to speech audio segments generated based solely on the target sound characteristics, the speech audio segments generated by incorporating the emotional characteristics 205 can change in response to changes in emotion, thereby enhancing the sensory listening experience of the audio literary work.

[0064] Example of generating speech audio

[0065] An example embodiment of how to generate and combine speech audio segments into speech audio is described below with reference to FIG3 . FIG3 illustrates an example architecture for generating speech audio segments according to some embodiments of the present disclosure. In the example of FIG3 , the matching unit 310 can be considered an example implementation of the sound characteristic assignment unit 220 , the text-to-speech conversion unit 320 can be considered an example implementation of the speech segment generation unit, and the splicing unit 330 can be considered at least a portion of the segment combination unit 240 .

[0066] In this example, the role information 212 includes role attributes 301-1 of role 1, role attributes 301-2 of role 2, ..., role attributes 301-L of role L, etc., which are collectively or individually referred to as role attributes 301 of the role. L is a positive integer greater than or equal to 1.

[0067] Matching unit 310 obtains multiple distinct candidate voice characteristics, each corresponding to a character with specific character attributes. As shown in FIG3 , matching unit 310 may pre-acquire a voice characteristic library 315 , which includes multiple candidate voice characteristics, such as candidate voice characteristics 302-1, ..., 302-3, ..., 302-M, collectively or individually referred to as candidate voice characteristics 302 , where M is a positive integer greater than or equal to 1. In some embodiments, to ensure that different target voice characteristics are determined for different characters, M is a positive integer greater than or equal to L. For each of the multiple characters, matching unit 310 may select, based on the character attributes 301 of the character, a target voice characteristic from the multiple candidate voice characteristics 302 that matches the character attributes 301. For example, as shown in FIG3 , character 1 is matched to candidate voice characteristic 302-1, character 2 is matched to candidate voice characteristic 302-3, and character L is matched to candidate voice characteristic 302-M.

[0068] In some embodiments, matching unit 310 can utilize a trained matching model to determine, from the sound characteristic library 315, corresponding candidate sound characteristics 302 as target sound characteristics based on the character's character attributes 301. The matching model can be a multi-classifier that classifies multiple candidate sound characteristics 302 based on the character's character attributes 301. The candidate sound characteristics classified for a particular character serve as the target sound characteristics for that character. For the example shown in FIG3 , after matching unit 310 inputs character 1's character attributes 301-1 into the matching model, the output result can be candidate sound characteristics 302-1.

[0069] In some embodiments, the matching unit 310 may also determine the corresponding candidate sound characteristics 302 from the sound characteristic library 315 according to the character attributes 301 of the character based on a predetermined matching rule. The character attributes 301 of a character in a literary work may include attribute values ​​of multiple dimensions. The multiple dimensions may include, but are not limited to, the gender, age, camp, personality, etc. of the character in the literary work. The matching rule may indicate the correspondence between the combination of attribute values ​​of multiple dimensions and the candidate sound characteristics 302. The matching rule may be manually pre-set or may be learned by the matching unit 310 based on a large amount of sound data. For each character, the matching unit 310 may select, from the sound characteristic library 315 according to the matching rule, the candidate sound feature 302 corresponding to the combination of attribute values ​​of the multiple dimensions of the character as the target sound characteristic.

[0070] As an example, the character attributes 301-1 include attribute values ​​of multiple dimensions such as the character's age, personality, and camp. For example, the gender of character 1 is male, the age is young, the personality is cold and domineering, and the camp is decent. The matching unit 310 can determine, based on the matching rules and the combination of these attribute values, that the target sound characteristics corresponding to character 1 are sound characteristics with the label of "domineering president". For another example, the gender of character 2 is female, the age is elderly, the camp is decent, and the personality is kind and steady. The matching unit 310 can determine, based on the matching rules and the combination of these attribute values, that the target sound characteristics corresponding to character 2 are sound characteristics with the label of "kind grandmother". It should be understood that these attributes and sound characteristics are merely exemplary and are not intended to limit the scope of the present disclosure.

[0071] In this embodiment, an attribute system is established to label characters in literary works, including information such as gender, age, faction, and personality. These tags, when combined, accurately describe the characters. The voice attribute library, on the other hand, consists of a voice library composed of AI-generated voices with different styles and timbres. Based on character-voice attribute mapping rules, the optimal voice characteristics, such as the optimal timbre, can be matched to characters with different attributes.

[0072] For each character, the text conversion unit 320 can convert the text of the target speech with the character as the main body into a voice audio segment corresponding to the target speech of the character based on the target sound characteristics of the character. In the example of Figure 3, a voice audio segment 303-1 of character 1, a voice audio segment 303-2 of character 2, ..., and a voice audio segment 303-L of character L are generated, which are also collectively referred to as voice audio segments 303. The text-to-speech conversion unit 320 can use any suitable TSS technology to perform the conversion. In particular, as mentioned above, in some embodiments, the speech information can include emotional characteristics. In such an embodiment, the text-to-speech conversion unit 320 can use emotional TTS technology to synthesize the voice audio segment.

[0073] The splicing unit 330 generates speech audio 304 from at least the speech audio segments 303 of these characters. In some embodiments, the text conversion unit 320 also generates speech audio segments corresponding to the narration. Accordingly, the splicing unit 330 also combines the speech audio segments corresponding to the narration with the speech audio segments 303 of the multiple characters to synthesize speech audio 304. The splicing unit 330 may combine or splice the speech audio segments according to the order in which the corresponding narration and speech appear in the literary work 120.

[0074] It is understandable that the speech audio segment 303 and the speech audio 304 only include synthesized human voices and can be regarded as dry voices. Specifically, the speech audio 304 can be regarded as a complete dry voice corresponding to the literary work 120.

[0075] In some embodiments, the speech audio 304 may be used as the audio 130 that the literary work 120 ultimately corresponds to. In other embodiments, the speech audio 304 is only a part of the audio 130, which also includes other audio signals.

[0076] Example of generating additional audio clips

[0077] Continuing to refer to FIG2 . As mentioned above, in some embodiments, the information extraction unit 210 can also obtain scene information 216 associated with a scene in the literary work 120. The scene information 216 describes the attributes of the scene and the events that occur in the scene. In some embodiments, the information extraction unit 210 can determine the scene and the content describing the scene in the literary work based on at least one of the time-space transformation or the role transformation in the literary work 120, and extract the scene information from the content. For example, the information extraction unit 210 can determine that the scene corresponding to location A ends and the scene corresponding to location B begins based on the text of the type "the character goes from location A to location B" that appears in the literary work 120. The information extraction unit 210 can use a trained scene segmentation model to identify the scene information 216 from the literary work 120. Several literary works can be systematically annotated, and the annotated data can be used to train the scene segmentation model. In this way, a scene and / or plot recognition system can be formed.

[0078] The scene information 216 includes at least one of scene division 206, plot 207, and action 208. The scene division 206 is used to indicate the starting position and ending position of the scene in the literary work 120, the environment and location of the scene, the time corresponding to the scene, etc. The plot 207 is the plot that occurs in the scene, such as fighting, quarreling, eating, meeting, etc. The action 208 refers to the action performed by the character in the scene. The scene information 216 is provided to the additional segment generation unit 250. The additional segment generation unit 250 is configured to generate an additional audio segment corresponding to the scene based on the scene information 216. It can be understood that the various sounds in the additional audio segment match or fit with the scene.

[0079] In this embodiment, the additional audio segment is provided to segment combination unit 240. Segment combination unit 240 can generate audio 130 for the literary work 120 based on the additional audio segment and the speech audio segment generated by speech segment generation unit 230. In other words, segment combination unit 240 can combine the additional audio segment and the speech audio segment into an audio literary work. During the combination process, segment combination unit 240 can regularize the volume of each audio segment to ensure that the various sounds in the audio literary work are more balanced, for example, background music does not dominate the main sound.

[0080] The additional segment generation unit 250 may store an additional audio library containing a variety of additional sound audio. In some embodiments, the additional segment generation unit 250 may utilize a trained machine learning model based on the scene information 216 and the additional audio library to generate multiple additional audio segments corresponding to multiple scenes. In other embodiments, the additional audio segments may include sound effects and / or background music determined based on different types of scene attributes.

[0081] Such an example embodiment is described below with reference to FIG4 . FIG4 illustrates an example architecture for generating additional audio segments according to some embodiments of the present disclosure. In the example of FIG4 , the ambient sound matching unit 410 , the background music matching unit 420 , and the action sound matching unit 430 can be viewed as example implementations of the additional segment generation unit 250 in FIG2 .

[0082] As shown in FIG4 , the information extraction unit 210 can extract multiple scenes from the literary work 120, such as scenes 401-1, 401-2, ..., 401-N, which are collectively or individually referred to as scenes 401, where N is a positive integer greater than or equal to 1. The scene information of each scene 401 can indicate at least one of the time of the scene, the location of the scene, the plot occurring in the scene, or the actions performed by the characters in the scene.

[0083] The ambient sound matching unit 410 is configured to determine the ambient sound corresponding to the time and location of the scene 401. For example, if the time of a scene is night and the location is the seaside, the ambient sound matching unit 410 can determine a sound effect with the sound of waves as the ambient sound of the scene.

[0084] Background music matching unit 420 is configured to determine music that corresponds to the plot occurring in scene 401. For example, if the plot involves different characters arguing, background music matching unit 420 may select fast-paced, tense music as the background music for this plot. Alternatively, if the plot involves a family enjoying a meal, background music matching unit 420 may select warm and cozy music as the background music. It should be understood that a scene may contain different plots, and appropriate background music may be selected for each plot.

[0085] The action sound effect matching unit 430 is configured to determine an action sound effect corresponding to the action performed by the character. For example, if the action is running, the action sound effect matching unit 430 may determine the corresponding action sound effect to be the sound of running. For another example, if the action is opening and closing a door, the action sound effect matching unit 430 may determine the corresponding action sound effect to be the sound of a door opening and closing. It should be understood that different actions may occur in a scene, and an appropriate action effect can be selected for each action.

[0086] As an example, the information extraction unit 210 can determine the tags corresponding to the described scenes based on the text in the literary work, and use these tags as scene information. In this case, the environmental sound effect matching unit 410 can determine the matching environmental sound effects based on the tags corresponding to the combination of time and place, using predetermined matching rules or trained models. Similarly, the background music matching unit 420 determines the matching background music based on the tags corresponding to the plot, using predetermined matching rules or trained models. Similarly, the action sound effect matching unit 430 can determine the matching action sound effects based on the tags corresponding to the actions, using predetermined matching rules or trained models.

[0087] Furthermore, the ambient sound effects, background music, and action sound effects obtained by the ambient sound effect matching unit 410, the background music matching unit 420, and the action sound effect matching unit 430 are combined as additional audio segments corresponding to scene 401. In the example of FIG4 , additional audio segments 402-1 for scene 401-1, 402-2 for scene 401-2, ..., and 402-N for scene 401-N are obtained, which are also collectively or individually referred to as additional audio segments 402.

[0088] Continuing with Figure 4, the speech audio 305 is combined with the plurality of additional audio segments 402 to obtain the audio 130 corresponding to the literary work 120. This can be achieved, for example, by the segment combination unit 240 shown in Figure 2. The combination can be based on the order in which the corresponding words, plots, actions, etc. appear in the literary work.

[0089] In this embodiment, automated post-production music and sound effects can be added, matching background music, animations, ambient sounds, etc. according to the storyline, achieving an effect comparable to that of real-life audio. This can enhance the user's immersion in listening to audio literature.

[0090] The above describes some example embodiments of generating audio literature works disclosed herein. Overall, personalized voice audio can be achieved for different characters. In some embodiments, this can further incorporate different sound effects tailored to different scenarios. In this way, higher-quality audio can be obtained, which helps enhance the user's listening experience.

[0091] Furthermore, the embodiments of the present disclosure can address the high production costs and long production cycles of live multicast audiobooks. For example, a multicast audiobook of a million-word novel can be produced with only minimal TTS synthesis costs and a few minutes of synthesis time. Therefore, utilizing technologies such as machine learning can enable efficient and cost-effective mass production of high-quality audiobooks.

[0092] Example Process

[0093] FIG5 shows a flow chart of a process 500 for audio generation according to some embodiments of the present disclosure. The process 500 may be implemented at the electronic device 110. The process 500 is described below with reference to FIG1.

[0094] In block 510 , the electronic device 110 obtains corresponding character attributes of a plurality of characters in a literary work and corresponding utterances with the plurality of characters as subjects.

[0095] In block 520 , the electronic device 110 determines, for each of the multiple characters, target voice characteristics for the character based on the character attributes, and generates, based on the target voice characteristics, a speech audio segment corresponding to a target utterance with the character as the subject.

[0096] At block 530 , the electronic device 110 generates audio for the literary work based at least on the corresponding voice audio segments generated for the plurality of characters.

[0097] In some embodiments, determining the target voice characteristic includes: obtaining a plurality of candidate voice characteristics that are different from each other, each candidate voice characteristic corresponding to a character having a specific character attribute; and selecting the target voice characteristic from the plurality of candidate voice characteristics based on the character attribute of the character.

[0098] In some embodiments, the character attributes of the character include attribute values ​​of multiple dimensions, and selecting the target voice characteristic includes: selecting a candidate voice feature corresponding to a combination of the attribute values ​​of the multiple dimensions from multiple candidate voice characteristics as the target voice characteristic.

[0099] In some embodiments, generating the speech audio segment includes: determining emotional characteristics contained in the target utterance based on the content and context of the target utterance; and converting the text of the target utterance into the speech audio segment based on the target sound characteristics and emotional characteristics.

[0100] In some embodiments, process 500 also includes: obtaining scene information associated with a scene in a literary work, the scene information describing attributes of the scene and events occurring in the scene; and generating additional audio clips corresponding to the scene based on the scene information, and wherein generating audio for the literary work is further based on the additional audio clips.

[0101] In some embodiments, the scene information indicates at least one of the following: the time of the scene, the location of the scene, the plot occurring in the scene, or the actions performed by characters in the scene.

[0102] In some embodiments, generating the additional audio clip includes combining two or more of the following into the additional audio clip: ambient sound effects corresponding to the time and place, music corresponding to the plot, or action sound effects corresponding to the action.

[0103] In some embodiments, obtaining scene information includes: determining a scene and content describing the scene in the literary work based on at least one of a temporal and spatial transformation or a role transformation in the literary work; and extracting scene information from the content.

[0104] In some embodiments, the plurality of roles are determined by: determining a set of candidate roles having names in the literary work based on the text of the literary work; determining, for each candidate role in the set of candidate roles, an amount of discourse in the literary work with the candidate role as the subject; and determining the candidate role having an amount greater than a threshold as one of the plurality of roles.

[0105] In some embodiments, obtaining corresponding role attributes of multiple roles includes: for a given role among the multiple roles, determining, from a literary work, descriptive information for the given role and the relationship between the given role and other roles among the multiple roles; and determining the role attributes of the given role based on the descriptive information and the relationship.

[0106] Example devices and equipment

[0107] 6 shows a schematic structural block diagram of an apparatus 600 for audio generation according to certain embodiments of the present disclosure. The apparatus 600 may be implemented as or included in the electronic device 110. Each module / component in the apparatus 600 may be implemented by hardware, software, firmware, or any combination thereof.

[0108] As shown, apparatus 600 includes an acquisition module 610 configured to acquire corresponding character attributes of multiple characters in a literary work and corresponding utterances based on the multiple characters. Apparatus 600 also includes a segment generation module 620 configured to determine, for each of the multiple characters, target voice characteristics based on the character's character attributes, and generate, based on the target voice characteristics, a speech audio segment corresponding to a target utterance based on the character. Apparatus 600 also includes a segment combination module 630 configured to generate audio for the literary work based at least on the corresponding speech audio segments generated for the multiple characters.

[0109] In some embodiments, the segment generation module 620 is further configured to: obtain a plurality of candidate sound characteristics that are different from each other, each candidate sound characteristic corresponding to a character with specific character attributes; and select a target sound characteristic from the plurality of candidate sound characteristics based on the character attributes of the character.

[0110] In some embodiments, the role attributes of the character include attribute values ​​of multiple dimensions, and the segment generation module 620 is further configured to: select a candidate sound feature corresponding to a combination of attribute values ​​of multiple dimensions from multiple candidate sound characteristics as the target sound characteristic.

[0111] In some embodiments, the segment generation module 620 is further configured to: determine the emotional characteristics contained in the target utterance based on the content and context of the target utterance; and convert the text of the target utterance into a speech audio segment based on the target sound characteristics and emotional characteristics.

[0112] In some embodiments, the device 500 also includes: a scene information acquisition module, configured to acquire scene information associated with a scene in a literary work, the scene information describing the attributes of the scene and events occurring in the scene; and an additional audio generation module, configured to generate an additional audio segment corresponding to the scene based on the scene information, and wherein the generation of audio for the literary work is further based on the additional audio segment.

[0113] In some embodiments, the scene information indicates at least one of the following: the time of the scene, the location of the scene, the plot occurring in the scene, or the actions performed by characters in the scene.

[0114] In some embodiments, generating the additional audio clip includes combining two or more of the following into the additional audio clip: ambient sound effects corresponding to the time and place, music corresponding to the plot, or action sound effects corresponding to the action.

[0115] In some embodiments, the scene information acquisition module is further configured to: determine the scene and the content describing the scene in the literary work based on at least one of the time-space transformation or the role transformation in the literary work; and extract scene information from the content.

[0116] In some embodiments, the plurality of roles are determined by: determining a set of candidate roles having names in the literary work based on the text of the literary work; determining, for each candidate role in the set of candidate roles, an amount of discourse in the literary work with the candidate role as the subject; and determining the candidate role having an amount greater than a threshold as one of the plurality of roles.

[0117] In some embodiments, the acquisition module 610 is further configured to: determine, for a given role among multiple roles, descriptive information for the given role and the relationship between the given role and other roles among the multiple roles from literary works; and determine role attributes of the given role based on the descriptive information and the relationship.

[0118] FIG7 shows a block diagram of an electronic device 700 in which one or more embodiments of the present disclosure may be implemented. It should be understood that the electronic device 700 shown in FIG7 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. The electronic device 700 shown in FIG7 may be used to implement the electronic device 110 of FIG1 .

[0119] As shown in FIG7 , electronic device 700 is a general-purpose electronic device. Components of electronic device 700 may include, but are not limited to, one or more processors or processing units 710, memory 720, storage device 730, one or more communication units 740, one or more input devices 750, and one or more output devices 760. Processing unit 710 may be a real or virtual processor and is capable of performing various processes according to programs stored in memory 720. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to enhance the parallel processing capabilities of electronic device 700.

[0120] The electronic device 700 typically includes a plurality of computer storage media. Such media can be any accessible media that can be obtained by the electronic device 700, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 720 can be a volatile memory (e.g., a register, a cache, a random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 730 can be a removable or non-removable medium and can include a machine-readable medium, such as a flash drive, a disk, or any other medium that can be used to store information and / or data (e.g., training data for training) and can be accessed within the electronic device 700.

[0121] The electronic device 700 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not shown in FIG. 7 , a disk drive for reading from or writing to a removable, non-volatile disk (e.g., a “floppy disk”) and an optical drive for reading from or writing to a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to a bus (not shown) by one or more data media interfaces. The memory 720 may include a computer program product 725 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.

[0122] The communication unit 740 enables communication with other electronic devices via a communication medium. Additionally, the functions of the components of the electronic device 700 can be implemented as a single computing cluster or multiple computing machines that can communicate via a communication connection. Thus, the electronic device 700 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0123] Input device 750 may be one or more input devices, such as a mouse, keyboard, or trackball. Output device 760 may be one or more output devices, such as a display, a speaker, or a printer. Electronic device 700 may also communicate with one or more external devices (not shown) via communication unit 740 as needed, such as storage devices, display devices, or the like, with one or more devices that allow a user to interact with electronic device 700, or with any device that allows electronic device 700 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0124] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0125] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0126] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, such that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0127] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0128] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple implementations of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part for a module, program segment or instruction, and a part for a module, program segment or instruction comprises one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0129] While various implementations of the present disclosure have been described above, the foregoing description is intended to be illustrative, not exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is selected to best explain the principles of the implementations, their practical applications, or improvements to existing technologies, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. An audio generation method, comprising: Obtaining corresponding role attributes of a plurality of roles in a literary work and corresponding discourses with the plurality of roles as subjects; For each of the plurality of roles, Based on the character attributes of the character, determine the target sound characteristics for the character, and Based on the target sound characteristics, generating a speech audio segment corresponding to a target speech with the character as the main subject; as well as Audio for the literary work is generated based at least on the corresponding speech audio segments generated for the multiple characters.

2. The method of claim 1 , wherein determining the target sound characteristic comprises: obtaining a plurality of candidate voice characteristics that are different from each other, each candidate voice characteristic corresponding to a character having a specific character attribute; as well as The target voice characteristic is selected from the plurality of candidate voice characteristics based on the character attribute of the character.

3. The method according to claim 2, wherein the character attributes of the character include attribute values ​​of multiple dimensions, and selecting the target voice characteristics comprises: A candidate sound feature corresponding to a combination of the attribute values ​​of the plurality of dimensions is selected from the plurality of candidate sound features as the target sound feature.

4. The method of claim 1, wherein generating the speech audio segment comprises: Determining the emotional characteristics contained in the target utterance based on the content and context of the target utterance; as well as Based on the target sound characteristics and the emotional characteristics, the text of the target utterance is converted into the speech audio segment.

5. The method according to claim 1, further comprising: Acquire scene information associated with a scene in the literary work, the scene information describing attributes of the scene and events occurring in the scene; as well as Based on the scene information, an additional audio segment corresponding to the scene is generated, and Wherein generating the audio for the literary work is further based on the additional audio segment.

6. The method according to claim 5, wherein the scene information indicates at least one of the following: The time of the scene, The location of the scene, what happens in the scene, or Actions performed by characters in the scene.

7. The method of claim 6, wherein generating the additional audio segment comprises combining two or more of the following into the additional audio segment: Ambient sound effects corresponding to said time and said place, music that corresponds to the plot, or Action sound effects corresponding to the actions described.

8. The method according to claim 5, wherein acquiring the scene information comprises: Determining the scene and content describing the scene in the literary work based on at least one of a time-space transformation or a role transformation in the literary work; as well as The scene information is extracted from the content.

9. The method according to claim 1, wherein the plurality of roles are determined by: Based on the text of the literary work, determining a set of candidate characters with names in the literary work; For each candidate character in the set of candidate characters, determining the amount of discourse in the literary work with the candidate character as the subject; as well as The candidate role for which the amount is greater than a threshold is determined as one of the plurality of roles.

10. The method according to claim 1, wherein obtaining corresponding role attributes of the plurality of roles comprises: For a given role among the plurality of roles, Determining, from the literary work, descriptive information for the given character and a relationship between the given character and other characters in the plurality of characters; as well as Based on the description information and the relationship, role attributes of the given role are determined.

11. An audio generating device, comprising: An acquisition module is configured to acquire corresponding role attributes of a plurality of roles in a literary work and corresponding discourses with the plurality of roles as subjects; A fragment generation module is configured to generate a fragment for each of the plurality of roles. Based on the character attributes of the character, determine the target sound characteristics for the character, and Based on the target sound characteristics, generating a speech audio segment corresponding to a target speech with the character as the main subject; as well as The segment combination module is configured to generate audio for the literary work based on at least the corresponding voice audio segments generated for the multiple characters.

12. An electronic device comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 10 when executed by the at least one processing unit.

13. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 10.

Citation Information

Patent Citations

  • Intelligent reading theme setting method and device oriented to immersive reading

    CN107203569A

  • Method and apparatus for voice interaction

    CN109272984A

  • Method and device for generating audio for plain text document

    CN110491365A

  • Voice synthesis method, device and equipment and medium

    CN111667811A

  • Virtual character voice processing method and device and computer equipment

    CN111785246A