WO2021196646A1

WO2021196646A1 - Interactive object driving method and apparatus, device, and storage medium

Info

Publication number: WO2021196646A1
Application number: PCT/CN2020/129814
Authority: WO
Inventors: 吴文岩; 吴潜溢; 钱晨; 王宇欣
Original assignee: 北京市商汤科技开发有限公司
Priority date: 2020-03-31
Filing date: 2020-11-18
Publication date: 2021-10-07
Also published as: CN113672194A; KR20210124182A; JP2022530726A; CN111459454B; CN111459454A; TW202139052A

Abstract

An interactive object driving method and apparatus, a device, and a storage medium. The method comprises: obtaining a speech frame sequence contained in a speech segment; obtaining a control parameter of at least one partial area of an interactive object corresponding to the speech frame sequence; and controlling the posture of the at least one partial area of the interactive object according to the control parameter obtained.

Description

Driving method, device, equipment and storage medium of interactive object

Related cross references

This application is filed based on a Chinese patent application with an application number of 2020102472765 and an application date of March 31, 2020, and claims the priority of the Chinese patent application. The entire content of the Chinese patent application is hereby incorporated by reference into this application.

Technical field

The present disclosure relates to the field of computer technology, and in particular to a method, device, device, and storage medium for driving interactive objects.

Background technique

The way of human-computer interaction is mostly based on keystrokes, touches, and voice input, and responds by presenting images, texts or virtual characters on the display screen. At present, virtual characters are mostly improved on the basis of voice assistants.

Summary of the invention

The embodiments of the present disclosure provide a driving solution for interactive objects.

According to an aspect of the present disclosure, there is provided a method for driving an interactive object, the method comprising: obtaining a sequence of voice frames contained in a voice segment; obtaining a control parameter of at least one local area of the interactive object corresponding to the sequence of voice frames ; Control the posture of the interactive object according to the acquired control parameter.

With reference to any one of the embodiments provided in the present disclosure, the method further includes: controlling the display device displaying the interactive object to output voice and/or display text according to the voice segment.

With reference to any one of the embodiments provided in the present disclosure, the control parameter of the local area of the interactive object includes the posture control vector of the local area; acquiring the control parameter of at least one local area of the interactive object corresponding to the speech frame sequence, The method includes: acquiring a first acoustic feature sequence corresponding to the voice frame sequence; acquiring an acoustic feature corresponding to at least one voice frame according to the first acoustic feature sequence; acquiring at least one of the interactive objects corresponding to the acoustic feature The attitude control vector of a local area.

In combination with any of the embodiments provided in the present disclosure, in combination with any of the embodiments provided in the present disclosure, the first acoustic feature sequence includes an acoustic feature vector corresponding to each voice frame in the voice frame sequence; The first acoustic feature sequence, acquiring the acoustic feature corresponding to at least one speech frame, includes: sliding a window on the first acoustic feature sequence with a time window of a set length and a set step size, and changing the time window The acoustic feature vector within is used as the corresponding acoustic feature of the at least one speech frame, and a second acoustic feature sequence is obtained according to the plurality of acoustic features obtained by completing the sliding window.

In conjunction with any one of the embodiments provided in the present disclosure, controlling the posture of the interactive object according to the control parameter includes: obtaining a sequence of posture control vectors corresponding to the second acoustic feature sequence; and according to the sequence of posture control vectors Control the posture of the interactive object.

In conjunction with any one of the embodiments provided in the present disclosure, acquiring the attitude control vector of at least one local area of the interactive object corresponding to the acoustic feature includes: inputting the acoustic feature into a pre-trained cyclic neural network to obtain The attitude control vector of at least one local area of the interactive object corresponding to the acoustic feature.

With reference to any one of the embodiments provided in the present disclosure, the recurrent neural network is obtained through acoustic feature sample training; the method further includes: obtaining an acoustic feature sample, specifically including: obtaining a video segment of a character uttering a voice, from the video segment Extract the corresponding voice segment from the video segment; sample the video segment to obtain multiple first image frames containing the character; and sample the voice segment to obtain multiple voice frames; Acoustic characteristics of the speech frame corresponding to the image frame; converting the first image frame into a second image frame containing the interactive object, and obtaining the attitude control vector value of at least one local area corresponding to the second image frame ; According to the attitude control vector value, annotate the acoustic feature corresponding to the first image frame to obtain the acoustic feature sample.

With reference to any of the embodiments provided in the present disclosure, the method further includes: training the initial recurrent neural network according to the acoustic feature samples, and training to obtain the recurrent neural network after the change in the network loss satisfies the convergence condition, wherein The network loss includes the difference between the attitude control vector value of the at least one local area predicted by the recurrent neural network and the marked attitude control vector value.

According to an aspect of the present disclosure, there is provided a driving device for an interactive object, the device comprising: a first acquisition unit for acquiring a sequence of speech frames contained in a speech segment; a second acquisition unit for acquiring the The control parameter of at least one partial area of the interactive object corresponding to the frame sequence; the driving unit is configured to control the posture of the interactive object according to the acquired control parameter.

According to an aspect of the present disclosure, an electronic device is provided, the device includes a memory and a processor, the memory is used to store computer instructions that can be run on the processor, and the processor is used to execute the computer instructions when the computer instructions are executed. The method for driving interactive objects described in any of the embodiments provided in the present disclosure is implemented.

According to an aspect of the present disclosure, there is provided a computer-readable storage medium having a computer program stored thereon, and the computer program program, when executed by a processor, implements the method for driving an interactive object according to any one of the embodiments provided in the present disclosure .

The driving method, device, device, and computer-readable storage medium of an interactive object according to one or more embodiments of the present disclosure obtain the voice frame sequence contained in the voice segment, and determine the location of at least one partial area of the interactive object according to the voice frame sequence. The parameter value is controlled to control the posture of the interactive object, so that the interactive object makes a posture that matches the voice segment, so that the target object feels that it is communicating with the interactive object, and the interaction between the target object and the interactive object is improved. Interactive experience.

Description of the drawings

In order to more clearly explain one or more embodiments of this specification or the technical solutions in the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, in the following description The drawings are only some of the embodiments described in one or more embodiments of this specification. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

FIG. 1 is a schematic diagram of a display device in a method for driving interactive objects proposed by at least one embodiment of the present disclosure;

2 is a flowchart of a method for driving interactive objects proposed by at least one embodiment of the present disclosure;

Fig. 3 is a schematic diagram of a process of feature encoding a speech frame sequence proposed by at least one embodiment of the present disclosure;

4 is a schematic structural diagram of a driving device for interactive objects proposed in at least one embodiment of the present disclosure;

FIG. 5 is a schematic structural diagram of an electronic device proposed in at least one embodiment of the present disclosure.

Detailed ways

The exemplary embodiments will be described in detail here, and examples thereof are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present disclosure. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

The term "and/or" in this article is only an association relationship describing the associated objects, which means that there can be three relationships, for example, A and/or B, which can mean: A alone exists, A and B exist at the same time, exist alone B these three situations. In addition, the term "at least one" in this document means any one of a plurality of or any combination of at least two of the plurality, for example, including at least one of A, B, and C, may mean including A, Any one or more elements selected in the set formed by B and C.

At least one embodiment of the present disclosure provides a method for driving interactive objects. The driving method may be executed by electronic devices such as a terminal device or a server. The terminal device may be a fixed terminal or a mobile terminal, such as a mobile phone, a tablet, or a game. The server includes a local server or a cloud server, etc., and the method can also be implemented by a processor calling computer-readable instructions stored in a memory.

In the embodiments of the present disclosure, the interaction object may be any virtual image capable of interacting with the target object. In an embodiment, the interactive object may be a virtual character, or may also be a virtual animal, virtual item, cartoon image, or other virtual images capable of implementing interactive functions. The display form of the interactive object may be 2D or 3D, which is not limited in the present disclosure. The target object may be a user, a robot, or other smart devices. The interaction manner between the interaction object and the target object may be an active interaction manner or a passive interaction manner. In an example, the target object can make a demand by making gestures or body movements, and trigger the interactive object to interact with it by means of active interaction. In another example, the interactive object may actively greet the target object, prompt the target object to make an action, etc., so that the target object interacts with the interactive object in a passive manner.

The interactive objects may be displayed through terminal devices, which may be televisions, all-in-one machines with display functions, projectors, virtual reality (VR) devices, and augmented reality (AR) devices Etc., the present disclosure does not limit the specific form of the terminal device.

Fig. 1 shows a display device proposed by at least one embodiment of the present disclosure. As shown in Figure 1, the display device has a transparent display screen, and a stereoscopic picture can be displayed on the transparent display screen to present a virtual scene and interactive objects with a stereoscopic effect. For example, the interactive objects displayed on the transparent display screen in FIG. 1 include virtual cartoon characters. In some embodiments, the terminal device described in the present disclosure may also be the above-mentioned display device with a transparent display screen. The display device is configured with a memory and a processor, and the memory is used to store computer instructions that can run on the processor. The processor is used to implement the method for driving the interactive object provided in the present disclosure when the computer instruction is executed, so as to drive the interactive object displayed on the transparent display screen to communicate or respond to the target object.

In some embodiments, in response to the sound-driven data used to drive the interactive object to output voice, the interactive object may emit a specified voice to the target object. The terminal device can generate sound-driven data according to the actions, expressions, identities, preferences, etc. of the target object around the terminal device to drive the interactive object to communicate or respond by emitting a specified voice, thereby providing anthropomorphic services for the target object. It should be noted that the sound-driven data can also be generated in other ways, for example, generated by the server and sent to the terminal device.

During the interaction between the interactive object and the target object, when the interactive object is driven to make a specified voice according to the sound driving data, the interactive object may not be able to drive the interactive object to make facial movements synchronized with the specified voice, making the interactive object dull when uttering the voice , Unnatural, affecting the interactive experience between the target object and the interactive object. Based on this, at least one embodiment of the present disclosure proposes a method for driving an interactive object, so as to improve the interaction experience between the target object and the interactive object.

FIG. 2 shows a flowchart of a method for driving an interactive object according to at least one embodiment of the present disclosure. As shown in FIG. 2, the method includes steps 201 to 203.

In step 201, a sequence of speech frames contained in the speech segment is obtained.

The voice segment may be a voice segment corresponding to the sound-driven data of the interactive object, and the sound-driven data may include audio data (voice data), text, and so on. The sound-driven data may be driving data generated by a server or a terminal device according to the actions, expressions, identity, preferences, etc. of the target object interacting with the interactive object, or may be sound-driven data called by the terminal device from the internal memory. The present disclosure does not limit the acquisition method of the sound-driven data.

In the embodiment of the present disclosure, the speech frame sequence contained in the speech segment may be obtained by performing frequency division processing on the speech segment. The frequency division processing is performed on the voice segment, that is, the voice segment is divided into multiple voice frames, and each voice frame is arranged in time order to form a voice frame sequence. The number of sampling points (duration) and frame shift (the degree of overlap between frames) contained in the speech frame obtained by performing frequency division processing can be determined according to the driving requirements of the interactive object, which is not limited in the present disclosure.

FIG. 3 shows a schematic diagram of a driving method of interactive objects proposed by at least one embodiment of the present disclosure. Perform segmentation/frequency division processing on the voice segment signal, and the resulting voice frame sequence is shown in Figure 3.

In step 202, the control parameter value of at least one partial region of the interactive object corresponding to the speech frame sequence is acquired.

The local area is obtained by dividing the whole (including face and/or body) of the interactive object. The control of one or more local areas of the face may correspond to a series of facial expressions or actions of the interactive object. For example, the control of the eye area may correspond to the facial actions of the interactive object such as opening, closing, blinking, and changing the perspective; The control of the mouth area can correspond to facial actions such as closing the mouth of the interactive object and opening the mouth to different degrees. The control of one or more local areas of the body may correspond to a series of physical actions of the interactive object. For example, the control of the leg area may correspond to the actions of the interactive object such as walking, jumping, and kicking.

The control parameter of the local area of the interactive object includes the posture control vector of the local area. The attitude control vector of each local area is used to drive the local area of the interactive object to perform actions. Different posture control vector values correspond to different motions or motion ranges. For example, for the posture control vector of the mouth area, one set of posture control vector values can make the mouth of the interactive object slightly open, and another set of posture control vector values can make the mouth of the interactive object open wider. By controlling the vector values with different postures to drive the interactive objects, the corresponding local areas can make different actions or actions with different amplitudes.

The local area can be selected according to the action of the interactive object that needs to be controlled. For example, when the face and limbs of the interactive object need to be controlled to perform actions at the same time, the posture control vector of all the local areas can be obtained; when the expression of the interactive object needs to be controlled , Then the posture control vector of the local area corresponding to the face can be obtained.

In the embodiments of the present disclosure, the control parameter value of at least one local area of the interactive object can be determined according to the acoustic characteristics of the speech frame sequence, and the control parameter value can also be determined according to other characteristics of the speech frame sequence.

In the embodiments of the present disclosure, the corresponding relationship between a certain characteristic of the speech frame sequence and the control parameter value of the interactive object can be established in advance, and the corresponding control parameter value can be obtained when the speech frame sequence is obtained. The specific method for obtaining the control parameter value of the interaction object matching the speech frame sequence will be described in detail later.

In step 203, the posture of the interactive object is controlled according to the acquired control parameter value.

Wherein, the control parameter value, for example, the attitude control vector value, is matched with the speech frame sequence contained in the speech segment. For example, when the display device showing the interactive object is outputting the voice segment, or is displaying the text corresponding to the voice segment, the gesture made by the interactive object is the same as the output voice and/or the displayed text It is synchronized, so as to give the target object a feeling that the interactive object is speaking.

In the embodiment of the present disclosure, by acquiring the speech frame sequence contained in the speech segment, and determining the control parameter value of at least one partial area of the interactive object according to the speech frame sequence, the posture of the interactive object is controlled so that the interactive object A gesture matching the speech segment is made, so that the target object feels that it is communicating with the interactive object, and the interactive experience of the target object is improved.

In some embodiments, the method is applied to a server, including a local server or a cloud server. The server processes the speech segment, generates the control parameter value of the interactive object, and uses three-dimensional rendering according to the control parameter value. The engine performs rendering to obtain the animation of the interactive object. The server may send the animation to the terminal for display to communicate or respond to the target object, and may also send the animation to the cloud, so that the terminal can obtain the animation from the cloud to communicate or respond to the target object . After the server generates the control parameter value of the interactive object, the control parameter value may also be sent to the terminal, so that the terminal completes the process of rendering, generating animation, and performing display.

In some embodiments, the method is applied to a terminal, and the terminal processes the speech segment, generates the control parameter value of the interactive object, and uses the three-dimensional rendering engine to render according to the control parameter value to obtain the interactive The animation of the object, the terminal can display the animation to communicate or respond to the target object.

In some embodiments, the display device displaying the interactive object may be controlled to output voice and/or display text according to the voice segment. And while outputting voice and/or displaying text, the gesture of the interactive object displayed by the display device can be controlled according to the control parameter value.

In the embodiment of the present disclosure, since the control parameter value matches the voice frame sequence of the voice segment, the voice and/or text outputted according to the voice segment is different from the control parameter value based on the control parameter value. When the gesture is synchronized, the gesture made by the interactive object is synchronized with the output voice and/or the displayed text, and the target object is given the feeling that the interactive object is speaking.

In some embodiments, in the case where the control parameter of at least one partial area of the interactive object includes an attitude control vector, the attitude control vector may be obtained in the following manner.

First, obtain the acoustic feature sequence corresponding to the speech frame sequence. Here, in order to distinguish from the acoustic feature sequence mentioned later, the acoustic feature sequence corresponding to the speech frame sequence is referred to as the first acoustic feature sequence.

In the embodiments of the present disclosure, the acoustic features may be features related to speech emotion, such as fundamental frequency features, common peak features, Mel Frequency Cepstral Cofficient (MFCC) and so on.

The first acoustic feature sequence is obtained by processing the entire speech frame sequence. Taking the MFCC feature as an example, the speech frame sequence can be windowed, fast Fourier transform, etc. Filtering, logarithmic processing, and discrete cosine processing to obtain the MFCC coefficients corresponding to each speech frame.

The first acoustic feature sequence is obtained by processing the entire speech frame sequence, and reflects the overall acoustic feature of the speech segment.

In the embodiment of the present disclosure, the first acoustic feature sequence includes an acoustic feature vector corresponding to each voice frame in the voice frame sequence. Taking MFCC as an example, the first acoustic feature sequence includes the MFCC coefficients of each speech frame. The first acoustic feature sequence obtained according to the speech frame sequence is shown in FIG. 3.

Next, according to the first acoustic feature sequence, the acoustic feature corresponding to at least one speech frame is acquired.

In the case that the first acoustic feature sequence includes the acoustic feature vector corresponding to each voice frame in the voice frame sequence, the same number of feature vectors corresponding to the at least one voice frame may be used as the voice The acoustic characteristics of the frame. Wherein, the same number of feature vectors may form a feature matrix, and the feature matrix is the acoustic feature corresponding to the at least one speech frame.

Taking FIG. 3 as an example, the N feature vectors in the first acoustic feature sequence form the acoustic features of the corresponding N speech frames; where N is a positive integer. The first acoustic feature sequence may include multiple acoustic features, and the speech frames corresponding to each of the acoustic features may partially overlap.

Finally, the attitude control vector of at least one local area of the interactive object corresponding to the acoustic feature is acquired.

According to the obtained acoustic feature corresponding to the at least one speech frame, the attitude control vector of the at least one local area can be obtained. The local area can be selected according to the action of the interactive object that needs to be controlled. For example, when the face and limbs of the interactive object need to be controlled to perform actions at the same time, the posture control vector of all the local areas can be obtained; when the expression of the interactive object needs to be controlled , Then the posture control vector of the local area corresponding to the face can be obtained.

While playing the voice segment, the interactive object is driven to make an action according to the attitude control vector corresponding to each acoustic feature obtained through the first acoustic feature sequence, so that the terminal device can output sound while the interactive object can Perform actions that match the output sound, including facial actions, expressions, and body actions, so that the target object feels that the interactive object is speaking. And because the attitude control vector is related to the acoustic characteristics of the output sound, driving according to the attitude control vector can make the expression and body movements of the interactive object have emotional factors, thereby making the speaking process of the interactive object more natural and vivid , Thereby improving the interactive experience between the target object and the interactive object.

In some embodiments, the acoustic feature corresponding to the at least one speech frame may be acquired by performing a sliding window on the first acoustic feature sequence.

By sliding the window of the first acoustic feature sequence with a time window of a set length and a set step size, the acoustic feature vector in the time window is used as the acoustic feature of the corresponding same number of speech frames, thereby obtaining Acoustic characteristics corresponding to these speech frames. After the sliding window is completed, the second acoustic feature sequence can be obtained according to the obtained multiple acoustic features.

Taking the driving method of the interactive object shown in FIG. 3 as an example, the speech frame sequence includes 100 speech frames per second, the length of the time window is 1 s, and the step length is 0.04 s. Since each feature vector in the first acoustic feature sequence corresponds to a speech frame, correspondingly, the first acoustic feature sequence also includes 100 feature vectors per second. During the window sliding process on the first acoustic feature sequence, 100 feature vectors in the time window are obtained each time as the acoustic features of the corresponding 100 speech frames. By moving the time window in steps of 0.04s on the first acoustic feature sequence, the acoustic features corresponding to the 1st to 100th speech frames 1 and the acoustic features 2 corresponding to the 4th to 104th speech frames are respectively obtained, By analogy, after traversing the first acoustic feature, acoustic feature 1, acoustic feature 2,..., acoustic feature M is obtained, thereby obtaining the second acoustic feature sequence, where M is a positive integer, and its value is based on the sequence of the speech frame The number of frames (the number of feature vectors in the first acoustic feature sequence), the length of the time window, and the step size are determined.

According to the acoustic feature 1, the acoustic feature 2,..., the acoustic feature M, the corresponding attitude control vector 1, the attitude control vector 2,..., the attitude control vector M can be obtained respectively, so as to obtain the sequence of the attitude control vector.

As shown in FIG. 3, the sequence of the attitude control vector and the second acoustic feature sequence are aligned in time. Acoustic feature 1, acoustic feature 2, ..., acoustic feature M in the second acoustic feature sequence , Are respectively obtained according to the N feature vectors in the first acoustic feature sequence. Therefore, while the voice frame is played, the interactive object can be driven to make an action according to the sequence of the posture control vector.

Assuming that the output of acoustic features starts at the set time of the first time window, the attitude control vector before the set time can be set to the default value, that is, when the speech frame sequence is just started to be played, the interactive object A default action is made, and after the set time, the interactive object is driven to make an action using the sequence of the posture control vector obtained according to the first acoustic feature sequence.

Take Figure 3 as an example. Acoustic feature 1 is output at t0, and the acoustic feature is output at intervals of 0.04s corresponding to the step size. Acoustic feature 2 is output at t1, and acoustic feature 3 is output at t2 until at t (M-1) Acoustic feature M is output at every moment. Correspondingly, in the time period ti~t(i+1) corresponds to the feature vector (i+1), where i is an integer smaller than (M-1), and before t0, the attitude control vector is the default Attitude control vector.

In the embodiment of the present disclosure, the interactive object is driven to make an action according to the sequence of the gesture control vector while playing the voice segment, so that the action of the interactive object is synchronized with the output sound, and the target object With the feeling that the interactive object is speaking, the interactive experience between the target object and the interactive object is improved.

The length of the time window is related to the amount of information contained in the acoustic feature. The greater the length of the time window, the more information it contains, and the stronger the correlation between the actions and sounds that drive the interactive object. The sliding step length of the time window is related to the time interval (frequency) of obtaining the attitude control vector, that is, it is related to the frequency of driving the interactive object to make an action. The length and step length of the time window can be set according to the actual interactive scene, so that the expressions and actions made by the interactive object are more closely related to the sound, and are more vivid and natural.

In some embodiments, the acoustic feature includes Mel frequency cepstral coefficients MFCC in L dimensions, where L is a positive integer. MFCC represents the distribution of the energy of the speech signal in different frequency ranges. The MFCC of L dimensions can be obtained by converting multiple speech frame data in the speech frame sequence to the frequency domain and using a Mel filter including L subbands. . Obtain the posture control vector according to the MFCC of the speech segment to drive the interactive object to perform facial and physical actions according to the posture control vector, so that the expression and physical actions of the interactive object have emotional factors, and the speaking process of the interactive object It is more natural and vivid, thereby improving the interactive experience of the target object.

In some embodiments, by inputting the acoustic feature to a pre-trained recurrent neural network, the attitude control vector of at least one local area of the interactive object corresponding to the acoustic feature can be obtained. Since the cyclic neural network is a time recurrent neural network, it can learn the historical information of the input acoustic features, and output the attitude control vector of the at least one local area according to the acoustic feature sequence. Wherein, the acoustic feature sequence includes a first acoustic feature sequence and a second acoustic feature sequence.

In the embodiment of the present disclosure, a pre-trained cyclic neural network is used to obtain the attitude control vector of at least one local area of the interactive object corresponding to the acoustic feature, and the historical feature information of the acoustic feature and the current feature information are merged, thereby The historical attitude control vector has an impact on the current attitude control vector change, making the expression changes and body movements of the interactive characters more smooth and natural.

In some embodiments, the recurrent neural network can be trained in the following manner.

First, an acoustic feature sample is obtained, the acoustic feature sample is annotated with a true value, and the true value is a posture control vector value of at least one local area of the interactive object.

After the acoustic feature samples are obtained, the initial recurrent neural network is trained according to the acoustic feature samples, and the recurrent neural network is trained after the change of the network loss satisfies the convergence condition, wherein the network loss includes the recurrent neural network The difference between the attitude control vector value of the at least one local area and the real value obtained by network prediction.

In some embodiments, the acoustic feature samples can be obtained by the following method.

First, obtain a video segment of a character's voice, and extract the corresponding voice segment from the video segment. For example, a video segment in which a real person is speaking can be obtained.

Next, the video segment is sampled according to the first sampling period to obtain multiple first image frames containing the character; the voice segment is sampled according to the second sampling period to obtain multiple voice frames.

Wherein, the second sampling period is less than the first sampling period, that is, the frequency of sampling the voice segment is higher than the frequency of sampling the video segment, so that one first image frame can correspond to the acoustics of at least one voice frame. feature.

Afterwards, the acoustic feature corresponding to the at least one speech frame corresponding to the first image frame is acquired. It should be noted that the number of speech frames corresponding to a first image frame in the training process is the same as the number of speech frames corresponding to the acoustic features obtained in the aforementioned driving process, and the number of acoustic features obtained in the training process The method is the same as in the aforementioned driving process.

Then, the first image frame is converted into a second image frame containing the interactive object, and the attitude control vector value of at least one local area corresponding to the second image frame is obtained. Wherein, the attitude control vector value may include the attitude control vector value of all the local areas, and may also include the attitude control vector value of some of the local areas.

Taking the first image frame as an image frame containing a real person as an example, the image frame of the real person can be converted into a second image frame containing the image represented by the interactive object, and the local area of the real person The posture control vector corresponds to the posture control vector of each local area of the interactive object, so that the posture control vector of each local area of the interactive object in the second image frame can be obtained.

Finally, according to the attitude control vector value, an acoustic feature corresponding to the first image frame is annotated to obtain an acoustic feature sample.

In the embodiment of the present disclosure, the video segment of a character is split into corresponding multiple first image frames and multiple voice frames, and the first image frame containing the real person is converted into the first image frame containing the interactive object. Two image frames are used to obtain the attitude control vector corresponding to the acoustic feature of at least one speech frame, so that the acoustic feature has a better correspondence with the attitude control vector, so as to obtain high-quality acoustic feature samples, so that the action of the interactive object is closer to the corresponding character Real action.

FIG. 4 shows a schematic structural diagram of a device for driving an interactive object according to at least one embodiment of the present disclosure. As shown in FIG. 4, the device may include: a first obtaining unit 401, configured to obtain a sequence of speech frames contained in a speech segment; The second acquiring unit 402 is configured to acquire a control parameter of at least one partial region of the interaction object corresponding to the speech frame sequence; the driving unit 403 is configured to control the posture of the interaction object according to the acquired control parameter.

In some embodiments, the device further includes an output unit for controlling the display device displaying the interactive object to output voice and/or display text according to the voice segment.

In some embodiments, the control parameter of the local area of the interactive object includes a posture control vector of the local area, and the second acquiring unit is specifically configured to: acquire the first acoustic feature sequence corresponding to the speech frame sequence Acquire the acoustic feature corresponding to at least one speech frame according to the first acoustic feature sequence; Acquire the attitude control vector of at least one local area of the interactive object corresponding to the acoustic feature.

In some embodiments, the first acoustic feature sequence includes an acoustic feature vector corresponding to each voice frame in the voice frame sequence, and after acquiring at least one voice frame corresponding to the first acoustic feature sequence The second acquiring unit is specifically configured to: acquire a sequence of posture control vectors corresponding to the second acoustic feature sequence; and control the posture of the interactive object according to the sequence of posture control vectors.

In some embodiments, the driving unit is specifically configured to: obtain a sequence of a posture control vector corresponding to the second acoustic feature sequence; and control the posture of the interactive object according to the sequence of the posture control vector.

In some embodiments, when acquiring the attitude control vector of at least one local area of the interactive object corresponding to the acoustic feature, the second acquiring unit is specifically configured to: input the acoustic feature into a pre-trained loop A neural network obtains a posture control vector of at least one local area of the interactive object corresponding to the acoustic feature.

In some embodiments, the recurrent neural network is obtained through acoustic feature sample training; the device further includes a sample acquisition unit, configured to: extract the voice segment of the character from the acquired video segment; Sampling the segment to obtain a plurality of first image frames containing the character; and sampling the speech segment to obtain a plurality of speech frames; obtaining the acoustic characteristics of the speech frame corresponding to the first image frame; The first image frame is converted into a second image frame containing the interactive object, and the attitude control vector value of at least one local area corresponding to the second image frame is obtained; The acoustic feature corresponding to the first image frame is annotated to obtain an acoustic feature sample.

In some embodiments, the device further includes a training unit for training the initial recurrent neural network according to the acoustic feature samples, and training to obtain the recurrent neural network after the change in network loss satisfies the convergence condition, wherein The network loss includes the difference between the attitude control vector value of the at least one local area and the labeled attitude control vector value predicted by the initial recurrent neural network.

At least one embodiment of this specification also provides an electronic device. As shown in FIG. 5, the device includes a memory and a processor. The memory is used to store computer instructions that can run on the processor. The method for driving interactive objects described in any embodiment of the present disclosure is realized by computer instructions.

At least one embodiment of this specification also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the method for driving an interactive object according to any embodiment of the present disclosure is realized.

Those skilled in the art should understand that one or more embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, one or more embodiments of this specification may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, one or more embodiments of this specification may adopt computer programs implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The form of the product.

The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, as for the data processing device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for related parts, please refer to the part of the description of the method embodiment.

The foregoing describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than in the embodiments and still achieve desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown in order to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

The embodiments of the subject and functional operations described in this specification can be implemented in the following: digital electronic circuits, tangible computer software or firmware, computer hardware including the structures disclosed in this specification and structural equivalents thereof, or among them A combination of one or more. The embodiments of the subject matter described in this specification can be implemented as one or more computer programs, that is, one or one of the computer program instructions encoded on a tangible non-transitory program carrier to be executed by a data processing device or to control the operation of the data processing device Multiple modules. Alternatively or in addition, the program instructions may be encoded on artificially generated propagated signals, such as machine-generated electrical, optical or electromagnetic signals, which are generated to encode information and transmit it to a suitable receiver device for data transmission. The processing device executes. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them.

The processing and logic flow described in this specification can be executed by one or more programmable computers executing one or more computer programs to perform corresponding functions by operating according to input data and generating output. The processing and logic flow can also be executed by a dedicated logic circuit, such as FPGA (Field Programmable Gate Array) or ASIC (Application Specific Integrated Circuit), and the device can also be implemented as a dedicated logic circuit.

Computers suitable for executing computer programs include, for example, general-purpose and/or special-purpose microprocessors, or any other type of central processing unit. Generally, the central processing unit will receive instructions and data from a read-only memory and/or a random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Generally, the computer will also include one or more mass storage devices for storing data, such as magnetic disks, magneto-optical disks, or optical disks, or the computer will be operatively coupled to this mass storage device to receive data from or send data to it. It transmits data, or both. However, the computer does not have to have such equipment. In addition, the computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or, for example, a universal serial bus (USB ) Flash drives are portable storage devices, just to name a few.

Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, including, for example, semiconductor memory devices (such as EPROM, EEPROM, and flash memory devices), magnetic disks (such as internal hard disks or Removable disks), magneto-optical disks, CD ROM and DVD-ROM disks. The processor and the memory can be supplemented by or incorporated into a dedicated logic circuit.

Although this specification contains many specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claimed protection, but are mainly used to describe the features of specific embodiments of a particular invention. Certain features described in multiple embodiments in this specification can also be implemented in combination in a single embodiment. On the other hand, various features described in a single embodiment can also be implemented in multiple embodiments separately or in any suitable sub-combination. In addition, although features may function in certain combinations as described above and even initially claimed as such, one or more features from the claimed combination may in some cases be removed from the combination, and the claimed The combination of protection can be directed to a sub-combination or a variant of the sub-combination.

Similarly, although operations are depicted in a specific order in the drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. In addition, the separation of various system modules and components in the above embodiments should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can usually be integrated together in a single software product. In, or packaged into multiple software products.

Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desired results. In addition, the processes depicted in the drawings are not necessarily in the specific order or sequential order shown in order to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

The above descriptions are only preferred embodiments of one or more embodiments of this specification, and are not intended to limit one or more embodiments of this specification. All within the spirit and principle of one or more embodiments of this specification, Any modification, equivalent replacement, improvement, etc. made should be included in the protection scope of one or more embodiments of this specification.

Claims

A driving method of interactive objects includes:

Acquire the sequence of speech frames contained in the speech segment;

Acquiring a control parameter value of at least one partial area of the interactive object corresponding to the speech frame sequence;

Controlling the posture of the interactive object according to the acquired control parameter value.
The method according to claim 1, further comprising: controlling the display device displaying the interactive object to output voice and/or display text according to the voice segment.
The method according to claim 1 or 2, wherein the control parameter of the local area of the interactive object includes the attitude control vector of the local area;

Obtaining the control parameter of at least one partial area of the interaction object corresponding to the speech frame sequence includes:

Acquiring a first acoustic feature sequence corresponding to the speech frame sequence;

Acquiring an acoustic feature corresponding to at least one speech frame according to the first acoustic feature sequence;

Obtain a posture control vector of at least one local area of the interactive object corresponding to the acoustic feature.
The method according to claim 3, wherein the first acoustic feature sequence includes an acoustic feature vector corresponding to each voice frame in the voice frame sequence;

According to the first acoustic feature sequence, acquiring the acoustic feature corresponding to at least one speech frame includes:

Perform a sliding window on the first acoustic feature sequence with a time window of a set length and a set step size, and use the acoustic feature vector in the time window as the corresponding acoustic feature of the at least one speech frame, and Obtaining a second acoustic feature sequence according to the plurality of acoustic features obtained by completing the sliding window;

Controlling the posture of the interactive object according to the acquired control parameter includes:

Acquiring a sequence of attitude control vectors corresponding to the second acoustic feature sequence;

The posture of the interactive object is controlled according to the sequence of the posture control vector.
The method according to claim 3, wherein acquiring the attitude control vector of at least one local area of the interactive object corresponding to the acoustic feature comprises:

The acoustic feature is input to a pre-trained recurrent neural network, and the attitude control vector of at least one local area of the interactive object corresponding to the acoustic feature is obtained.
The method according to claim 5, wherein the recurrent neural network is obtained through acoustic feature sample training;

Obtain the acoustic feature samples according to the following methods:

Acquire a video segment in which a character speaks, extract from the video segment the speech segment in which the character speaks; sample the video segment to obtain a plurality of first image frames containing the character; and Sampling the voice segment to obtain multiple voice frames;

Acquiring an acoustic feature of the speech frame corresponding to the first image frame;

Transforming the first image frame into a second image frame containing the interactive object, and obtaining a posture control vector value of at least one local area corresponding to the second image frame;

According to the attitude control vector value, annotate the acoustic feature corresponding to the first image frame to obtain the acoustic feature sample.
The method according to claim 6, further comprising: training the initial recurrent neural network according to the acoustic feature samples, and training to obtain the recurrent neural network after the change of the network loss satisfies the convergence condition, wherein the network loss includes The difference between the posture control vector value of the at least one local area and the marked posture control vector value predicted by the recurrent neural network.
A driving device for interactive objects, including:

The first acquiring unit is used to acquire the sequence of speech frames contained in the speech segment;

The second acquiring unit is configured to acquire control parameters of at least one partial region of the interaction object corresponding to the speech frame sequence;

The driving unit is configured to control the posture of the interactive object according to the acquired control parameter.
8. The apparatus according to claim 8, further comprising an output unit, configured to control the display device displaying the interactive object to output voice and/or display text according to the voice segment.
The device according to claim 8 or 9, wherein the control parameter of the local area of the interactive object includes a posture control vector of the local area, and the second acquiring unit is configured to:

Acquiring a first acoustic feature sequence corresponding to the speech frame sequence;

Acquiring an acoustic feature corresponding to at least one speech frame according to the first acoustic feature sequence;

Obtain a posture control vector of at least one local area of the interactive object corresponding to the acoustic feature.
The apparatus according to claim 10, wherein the first acoustic feature sequence includes an acoustic feature vector corresponding to each speech frame in the speech frame sequence;

When acquiring the acoustic features corresponding to at least one speech frame according to the first acoustic feature sequence, the second acquiring unit is configured to:

Perform a sliding window on the first acoustic feature sequence with a time window of a set length and a set step size, and use the acoustic feature vector in the time window as the corresponding acoustic feature of the at least one speech frame, and Obtaining a second acoustic feature sequence according to the plurality of acoustic features obtained by completing the sliding window;

The driving unit is used for:

Acquiring a sequence of attitude control vectors corresponding to the second acoustic feature sequence;

The posture of the interactive object is controlled according to the sequence of the posture control vector.
The device according to claim 10, wherein, when acquiring the attitude control vector of at least one local area of the interactive object corresponding to the acoustic feature, the second acquiring unit is configured to: input the acoustic feature to A pre-trained cyclic neural network obtains the attitude control vector of at least one local area of the interactive object corresponding to the acoustic feature.
The device according to claim 12, wherein the recurrent neural network is obtained through acoustic feature sample training;

The device also includes a sample acquisition unit for:

Acquire a video segment in which a character speaks, extract a corresponding speech segment from the video segment; sample the video segment to obtain a plurality of first image frames containing the character; and sample the speech segment To obtain multiple speech frames;

Acquiring an acoustic feature of the speech frame corresponding to the first image frame;

Transforming the first image frame into a second image frame containing the interactive object, and obtaining a posture control vector value of at least one local area corresponding to the second image frame;

According to the attitude control vector value, annotate the acoustic feature corresponding to the first image frame to obtain the acoustic feature sample.
The device according to claim 13, further comprising a training unit for training the initial recurrent neural network according to the acoustic feature samples, and training to obtain the recurrent neural network after the change of the network loss satisfies the convergence condition, wherein The network loss includes the difference between the attitude control vector value of the at least one local area predicted by the recurrent neural network and the marked attitude control vector value.
An electronic device, comprising a memory and a processor, the memory is used to store computer instructions that can run on the processor, and the processor is used to implement any one of claims 1 to 7 when the computer instructions are executed Methods.
A computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the method according to any one of claims 1 to 7.