Inference of Emotions from Utterances in Audio Data Using Deep Learning

Abstract

A deep neural network can be trained to infer emotion data from input audio. The network can be a transformer-based network that can infer probability values for a set of emotions or emotion classes. The emotion probability values may be modified using one or more heuristics, such as for achieving smoothing of emotion determination over time, or via a user interface, where the user can modify the emotion determination as appropriate. The user may also provide prior emotion values that are mixed with these emotion determination values. The determined emotion values can be provided as input for emotion-based actions, such as providing audio-driven speech animation.

Description

Technical Field

[0001] The present invention relates to the inference of emotion from speech in audio data using deep learning.

Background Art

[0002] There are various situations where it may be desirable to determine the type of emotion presented by a person during speech, such as speech represented by captured audio data. In certain prior approaches, attempts have been made to infer emotion from input audio using machine learning, but these approaches have typically been limited to the person or speaker for whom each model was trained and have not generalized well to other speakers. These networks are typically based on spectrograms and require the conversion of audio to a spectrogram representation for analysis using image-based analysis, resulting in suboptimal results. Such approaches require training multiple models for different speakers, which can be complex and computationally expensive and can result in various levels of error in the emotion inferred for the input speech. Further, prior approaches determine a single emotion for the entire segment of audio, and thus do not capture variations in the speaker's emotional state within that segment.

Summary of the Invention

Means for Solving the Problems

[0003] With reference to the drawings, various embodiments according to the present disclosure are described.

Brief Description of the Drawings

[0004]

Figure 1

Figure 2A

Figure 2B

Figure 3

Figure 4A

Figure 4B

Figure 5

Figure 6

Figure 7A

Figure 7B

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15A

Figure 15B

Best Mode for Carrying Out the Invention

[0005] In the following description, various embodiments will be described. For the purpose of the description, specific configurations and details are set forth to provide a deep understanding of the embodiments. However, it will be apparent to those skilled in the art that these embodiments can be practiced without these specific details. Further, well - known features may be omitted or simplified so as not to obscure the described embodiments.

[0006] The systems and methods described herein may be used by, but are not limited to, non-autonomous vehicles, semi-autonomous vehicles (e.g., in one or more adaptive driver assistance systems (ADAS)), manned and unmanned robots or robotic platforms, warehouse vehicles, off-road vehicles, vehicles coupled to one or more trailers, airships, ships, shuttles, emergency response vehicles, electric or motorized bicycles, aircraft, construction vehicles, submarines, drones, and / or other vehicle types. Further, the systems and methods described herein may be used for a variety of purposes, by way of example and not limitation, such as machine control, machine movement, machine operation, synthetic data generation, model training, perception, augmented reality, virtual reality, mixed reality, robotics, safety monitoring, simulation and digital twins, autonomous or semi-autonomous machine applications, deep learning, environmental simulation, simulation and / or digital twins of objects or actors, data center processing, conversational AI, optical transport simulation (e.g., ray tracing, path tracing, etc.), co-creation of 3D asset content, cloud computing, and / or any other suitable applications.

[0007] The disclosed embodiments may be included in various different systems such as automotive systems (e.g., infotainment or mobile information terminal systems for autonomous or semi-autonomous vehicles), systems implemented using robots, aviation systems, medical systems, marine systems, smart area monitoring systems, systems for performing deep learning operations, systems for performing simulation operations, systems for performing digital twin operations, systems implemented using edge devices, systems incorporating one or more virtual machines (VMs), systems for performing synthetic data generation operations, systems implemented at least partially in a data center, systems for performing conversational AI operations, systems for performing optical transport simulations, systems for performing collaborative content creation of 3D assets, systems implemented using at least partially cloud computing resources, and / or other types of systems.

[0008] The disclosed embodiments can infer emotions from utterances made or audio data uttered by a speaker, such as a person, that can be captured in audio data using, for example, a microphone or an audio capture device that can convert a captured audio signal into digital audio data. While speaking, aspects of a person's utterance can change at least in part based on the emotional state, much like the expression on a person's face can change. For example, FIG. 1 shows images of four exemplary emotional states that a person can exhibit while uttering the same passage of speech. This includes image 100 indicating that the person is in a happy state, image 102 indicating that the person is in an angry state, image 104 indicating that the person is in a disgusted state, and image 106 indicating that the person is in a sad state. Just as the expression on a person's face changes with emotion, the vocal expression of the utterance will similarly change with these changes in emotion. In various operations, it can be beneficial to accurately and automatically identify these emotions from the captured audio data. In an exemplary use case where the emotion data is used to generate facial animations, being able to accurately identify or infer the emotional state of a person while speaking can help ensure that appropriate facial expressions for rendering the animation, such as those shown in FIG. 1, are used. The emotional state data can also be useful in other scenarios, such as corresponding to a call in a call center, at least in part based on the detected emotional state or change in emotional state of at least one of the parties to the call. For example, a prompt, script, or summary automatically generated for a call may be dynamically updated based on the detected emotional state of the caller.

[0009] As shown in FIG. 2A, an emotion determination system according to at least one embodiment receives input audio data 200. This audio data 200 can include utterances made by a speaker, such as at least one person, which may have been captured using an audio capture device. This audio data may be pre-processed to at least some extent, such as reduction of background noise, removal of silent or non-speaking segments, or segmentation of the audio into audio segments each containing an utterance made by a single speaker. This audio data can be passed as input to an emotion determination module, device, system, or process that attempts to determine or infer the emotional state of the person speaking in that audio clip. In this example, the audio data 200 is passed to an algorithm that can classify the type of emotion or emotional state reflected in the utterance made, using a trained deep learning model or neural network, at least with respect to those emotional states or classes for which the model or network was trained. The neural network 202 can infer one or more emotion labels 204 for the input audio 200, which can then be provided as the output of the emotion determination process. This can include, among other options, a single emotion label for an individual portion of the audio data 200, or one or more emotion labels or determinations for the entire input audio data (which may correspond to specific sections (such as words or sentences) of the received audio).

[0010] In at least one embodiment, the neural network 202 may be a transformer-based network. This may include, for example, a network having a Wav2Vec2.0 or UniSpeech neural architecture. Transformer neural networks can accurately and efficiently solve sequence-to-sequence tasks, including those with long-term dependencies. Such a network can take audio data in an audio file format as input without first converting the audio to an image-based representation such as a spectrogram or mel spectrogram, as was required in prior approaches (which have also been found to result in less accurate results and higher instability). For example, the audio data may correspond to an uncompressed audio file format (e.g., WAV, AIFF, AU, raw, etc.), a lossless compressed audio file format (FLAC, WavPack, TTA, ATRAC, MPEG-4, WMA lossless, SHN, etc.), or a lossy compressed audio file format (e.g., Opus, MP3, Vorbis, Musepack, AAC, ATRAC, WMA lossy, etc.). By using the audio file format, as opposed to converting the audio file format to a non-audio file format (e.g., an image format), higher accuracy and fitness in the predictions of the transformer-based neural network 202 are made possible, as well as making the network 202 more robust to different speakers. Also, as described, since preprocessing of the audio data into a non-audio-based format such as an image is not required, the runtime of the system is reduced.

[0011] In at least one embodiment, such a network can output a probability distribution, confidence level, and / or another output type indicating the likelihood that an utterance represented by input audio data corresponds to one or more of several emotion classes. This can be as few as two emotion classes (in which case a Boolean output may be generated by the network), or as many emotion classes (or combinations of classes) as can be distinguished without unduly affecting performance in a given operation, application, or use case and that can be used to train the network. In at least one embodiment, such a network outputs a distribution over six emotion classes represented in a (e.g., publicly available) dataset that can be used for training, including anger, disgust, fear, joy, neutral (or no detectable emotion), and sadness. If other datasets are used, the set of emotions may be larger or smaller, or may include different emotion options, at least partially based on the classifications or labels used in these datasets. It may be desirable to select different datasets if it is possible to obtain various examples representing different emotions. In at least one embodiment, the transformer-based neural network 202 outputs a vector with values for each emotion, where these values correspond to a probability, confidence level, or other metric indicating whether the utterance included in the input audio (e.g., extracted from a video clip) was made by a person having a particular emotional state or attempting to convey that emotion. These values may be normalized to values between 0 and 1 (or between 0% and 100%) such that they all sum to an absolute probability value, such as 1.0 (or 100%, in which case the sum of the probability values cannot exceed the maximum probability for any individual emotion). For an utterance determined to be all a single emotion, the probability vector may have a value of [1,0,0,0,0,0], and for an utterance determined to have equal probabilities for two different emotions, it may have a value of [0,0.5,0,0.5,0,0].Typical outputs can have at least some probability for most or all emotions, such as those corresponding to the values [0.9, 0.02, 0.01, 0.02, 0.02, 0.03]. Other such values or outputs indicating emotional states can be provided as well within the scope of various embodiments.

[0012] In an example where two or more emotional states can be expressed, each emotional state having a probability or confidence level exceeding a threshold can be identified as an emotional class expressed by the speaker. If it is determined that there are two or more emotional state classes, the output values corresponding to each emotion may be used to weight the salience of one emotion with respect to another. For example, when animating a virtual actor or virtual entity using emotional states, when there is a higher confidence in anger than in sadness, the virtual actor or virtual entity may be generated to show more of the emotion of anger than the emotion of sadness, which can be reflected using various facial and / or body features. Similarly, when the emotional state is used to indicate the emotion of the speaker for purposes other than animating a virtual actor or virtual entity, the intensity or confidence level of different emotions may be shown to the user or system, such as "the speaker is feeling more anger than sadness" or "anger: 70%, sadness: 30%".

[0013] Often, a person's emotional state does not remain exactly the same while making an utterance of several words or while making other vocalizations. Even when the emotional class may remain substantially the same, there may be periods when it is mixed with other emotions or exhibits a particular emotion more strongly. To account for these and other such variations, an emotion determination system can attempt to determine the emotional state at different (time) points or timings of the input audio, which may be within the same utterance made by a single speaker. These "points" may correspond to emotion keyframes determined for different timestamps of the audio track. An emotion detection algorithm can then output at least one emotion classification for each emotion keyframe. In the operation of receiving this emotion keyframe data, decisions can then be made or actions can be executed based at least in part on these changes in emotions over time.

[0014] Figure 2B shows one exemplary approach for determining an emotion classification for a sequence of emotion keyframes that may be used according to at least one embodiment. In this example, a fixed hop size 256 and window size 258 may be used to determine the emotional state for a sequence of frames 250, 252, 254 represented by input audio data 260. In an embodiment, the hop size (or stride) can also be considered as the distance of the stride point sense determined for the audio track, and the stride point may be determined at a regular frequency to obtain the desired overlap and spacing of the sliding window of individual frames. In at least one embodiment, a source (e.g., a user, an application, or an operation) can specify the hop size (or stride) 256 and the size of the sliding window 258 used to analyze the audio data. For input audio with a sample rate of 16,000 Hz, the exemplary window size and stride values can be set to approximately 15,000, or values between 5,000 and 16,000. In this embodiment, each frame of the audio can be analyzed using several passes through the audio data. For each pass, the audio at a given position of the window 258 can be analyzed to determine the probability values for the set of emotion classes within that time window. In various embodiments, the window length needs to be long enough to represent sufficient audio data for accurate emotion inference, but not too long as it can result in inaccurate probability determination across the entire window as it is likely to contain different emotional states. For each pass, the sliding window 258 can be advanced in time according to the specified hop size 256. The hop size 256 may be set to allow at least some overlap between window positions to help avoid missing relatively short emotional states that may have at least two windows for most points within the audio. The hop size 256 can also be made long enough to avoid unnecessary processing or an excessive number of passes through the audio.In at least one embodiment, the hop size can be at most half the size of the sliding window size and at least one tenth the length of the window size in order to obtain sufficient but not excessive overlap between window positions. Similarly, in at least one embodiment, a threshold or range relative to the window size may be set, such as at least one tenth or at most nine tenths of the frame size, in which case the frame can be anywhere from about 0.1 seconds to about 10 seconds. In at least one embodiment, after determining the probabilities of the various emotion classes for each of these sliding window positions in a given frame, these probabilities can be combined to determine an overall probability for that frame. This can then be provided as an emotion vector for this emotion keyframe, which can be considered to be located at a start point, midpoint, or other location within the individual frame. In this example, since the frames are all the same size, the keyframes will be of relatively regular timing, with an output of an emotion vector or emotion classification for each of these emotion keyframes.

[0015] In other embodiments, the frame size and the location of the key frames may vary at least in part based on the audio content. In at least one embodiment, the audio content is analyzed to segment the audio at least per speaker, such that the audio clip may contain or consist primarily of utterances made by a single speaker (this may include editing the audio to filter out utterances by other actors). In some embodiments, this may be further divided, for example, per sentence or word contained within the audio. Among other options, other factors such as pauses within the utterance, changes in volume, or changes in the speed of the uttered speech may also be used. In at least some embodiments, a threshold may be applied to determine the window size and the hop size, or an algorithm that may depend at least in part on the frame size may be used to determine these sizes. In some embodiments, the audio (e.g., 16 kHz audio) may be analyzed until a change in emotion is detected, or until a change meets or exceeds a change threshold (e.g., confidence in a different emotion greater than a threshold confidence, confidence in a different emotion greater than the current emotion confidence by a threshold amount, confidence in a different emotion greater than the current emotion confidence in an iteration exceeding a threshold number, etc.) or meets another selection criterion, after which a new key frame may be initiated. The previous key frame may then be analyzed using some of the paths described above to determine the emotion vector for that emotion key frame or to determine the emotion classification.

[0016] The emotion labels or classifications determined for individual emotion keyframes can be provided as input to a system, service, process, application, and / or operation that performs one or more tasks based at least in part on this emotion input data. An example of one such system is the audio-driven face animation system 300 as shown in FIG. 3. This exemplary system can provide automated audio-driven animation with variable emotion control, such as full 3D face animation. In at least one embodiment, among a number of options, a set of speech performances of one or more actors performing speech (e.g., a particular sentence) can be captured, including various emotions, levels of emotion, combinations of emotions, or styles of presentation. Emotions supported by such a system can include any suitable emotion (or similar behavior or state) that can be at least partially expressed through character animation, image synthesis, or rendering, such as, among others, joy, anger, surprise, sadness, pain, or fear. The data collection process can include the capture of 4D data, including multi-view 3D data over at least a certain period during which the speech is performed. The reconstruction of this captured facial behavior can be performed not only on the facial skin (or such a surface), but also on other components, elements, or features that can express or be controlled to move, such as teeth, eyeballs, head, and tongue. The reconstruction can provide geometric deformation data in the time domain for facial (or other body part) components or regions modeled separately (or at least somewhat separately) each. Such a reconstruction can provide a full dataset for use in training a deep neural network to perform tasks such as 3D face animation.

[0017] In at least one embodiment, the deep neural network 306 to be trained can be based on a U-net, a generative adversarial network (GAN), or a recurrent neural network (RNN) based architecture. The sequence-to-sequence mapping can be used to obtain a sufficiently long temporal context, which can be beneficial in generating physically or behaviorally accurate animations, particularly for upper face motion. In the exemplary system 300 of FIG. 3, segments of audio data, such as frames or segments of audio within the current audio window 302, may be provided as input to the deep neural network 306, and the deep neural network 306 can analyze the audio and encoded features representing the features of the audio within the audio window 302 that may correspond to a portion of the utterance using the analysis network portion 308. This analysis network portion 308 may include a shared audio decoder and encoder for encoding the audio features into an audio feature vector, and the audio feature vector may be provided as input to the articulation network portion 310 of the deep neural network 306. In this example, an emotion vector 322 (or an emotion label, etc.) may be provided as input. As discussed in more detail elsewhere herein, the emotion vector 322 may be generated using an emotion inference network 320, such as the transformer-based network 202 of FIG. 2A, that can infer emotions from the input audio for each audio frame, window, or segment. The emotion vector 322 may correspond to an emotion keyframe that is used to determine how one or more frames of the face animation are to be rendered.The emotion vector 322 may include data (such as probability, confidence, etc.) about one or more emotions applied to the utterances within the audio used for training, such as the emotion that the voice actor was instructed to use when making the utterances captured in the audio data. In some cases, this may include data about a single emotion label such as "anger", or data about multiple emotions such as "anger" and "sadness", and sometimes may include the relative weighting or probability for these two emotions.

[0018] In at least one embodiment, the style vector may be provided as an input to this network during training. The style vector can include data regarding any aspect of the animation or facial component motion that modifies how one or more points of one or more facial components should move for a given emotion or emotion vector. This may include affecting the motion of specific features or facial components, or providing the style of the overall animation used, such as "intense" or "professional". The style vector can also be regarded as providing a more fine-grained control over the emotion, where the emotion vector provides the label of the emotion to be used, and the style provides a more refined control over how the emotion is to be expressed through the animation. Other approaches for determining style data can also be used, such as those discussed in more detail elsewhere in this specification. In different implementations, a single set of emotion and style vectors may be provided for a given audio clip, or a set of vectors can be provided for each frame of the generated animation, or a set of vectors can be provided for specific points or frames of the animation (such as emotion keyframes), and at least one emotion or style value or setting is modified with respect to the previous frame.

[0019] In this system 300, among other things, the emotion vector 322 is input into the motion representation part 310 of the deep neural network 306 at multiple levels that at least include the start and end of the network in order to help condition the network. The network 306 may use a shared audio encoder and multiple decoders for various face components (e.g., facial skin, jaw, tongue, eyeballs, and head). During training, the output network part 312 of the deep neural network 306 can generate a set of vertex positions 314 and / or motion vectors (or other motion or deformation) for individual feature points of the face components, among a number of options, specifically for each of such feature points or only for those that have changed relative to the previous frame or relative to the previous frame. During training, these vertex positions can be compared to "ground truth" data, such as the original reconstructed face data from the capture of the 4D image, in order to calculate an overall loss value. In at least one example, a loss such as L2 loss can be used for both the position and velocity of the feature points in the output data representation. In at least one example, the loss function used to determine the loss value can include terms for position, motion, and adversarial loss. This loss value can be used during backpropagation to update the network parameters of the deep neural network 306. When it is determined that the network has converged or another training termination criterion is met (e.g., processing all training data or performing the target number / maximum number of training iterations), a trained network 306 for inference can be provided. During inference, the network may receive only the audio data 302 as input and may infer a set of vertex positions 314 for various face components (e.g., head, face, eyeballs, jaw, tongue). Subsequently, this set of vertex positions 314 can be input into a renderer 316 (e.g., the rendering engine of an animation or video compositing system) to generate a frame 318 of an animation, which can be one of a series of frames that provide an animation during presentation or playback.The original audio data used by the deep neural network 306 may be the same as the original audio data used by the transformer-based neural network 202 of FIG. 2A to determine the emotional state or class corresponding to the audio data. In various embodiments, the format of the audio data used by the DNN 306 and the transformer-based neural network 202 may be different or the same. For example, both networks 306 and 202 may use audio without conversion to an image-based format, or network 306 may use an image-based format (e.g., spectrogram) and network 202 may use an audio format without conversion, such as those described herein.

[0020] As discussed in more detail elsewhere in this specification, for communicating a particular style or facial behavior used when inferring the vertex position 314, etc., if the vertex position generated in some form is modified regarding how the deep neural network 306 can typically infer the vertex position based on audio data, emotion vector data may also be provided. In some embodiments, the deep neural network 306 may receive emotion vectors at least when available and determine how to animate the face using these vectors, or attempt to use this vector in combination with its own emotion determination to provide a smoother and more accurate animation. Providing different emotion vectors for different emotion keyframes can help the emotional expression of the rendered face change dynamically over time to correspond to the emotion conveyed in the corresponding utterance data. The advantage of the transformer-based neural network 202 as described herein is that it can generalize utterance audio from many different speakers, so that the operator does not need to obtain different models trained for each speaker or type of speaker.

[0021] In at least one embodiment, the change in emotion in a frame or audio segment may be expressed in different forms. For example, if a first emotion is detected in the first half of a segment and a second emotion is detected in the second half of that segment, two emotion vectors may be provided that indicate the respective emotions in each time frame or for each emotion keyframe. In another example, a single keyframe may be generated that indicates the probabilities or values for both emotions for that segment, such as those having substantially equal probabilities. In yet another example, the system may examine the emotion values of adjacent (e.g., preceding and succeeding) segments and attempt to integrate or modify the segment based at least in part on the similarity or difference in emotion determination.

[0022] In some embodiments, all emotion classes can be made to have the same weighting (or no weighting at all) so that the determined probabilities can be used directly. In some embodiments, the user (or other source) can be enabled to specify at least one emotion label, in which case this can affect the weighting of at least one emotion class or the output emotion vector or value. For example, the user may specify that a given audio segment be associated with the emotion of "sadness". During analysis, the emotion detection network may detect the probabilities of other emotions such as anger or disgust. In at least one embodiment, these values can be used to adjust the probabilities of the emotion vector by, among other things, adjusting the weights applied to the various probabilities to weight the emotion state of "sadness" more highly, or by mixing or averaging the determined probabilities using the probability of sadness as a whole based on user input. In some embodiments, the user may also have the option to adjust the probabilities or values in the vector to modify the result based at least in part on a given emotion vector.

[0023] The ability to determine emotion from speech or voice data can have various other uses and advantages in other scenarios. For example, in the operation of a call center, the ability to determine the emotion of a call center employee during a call can help determine whether the employee has a tendency to exhibit certain emotions outside the expected or average range, and can help identify employees who may benefit from additional training or support. The ability to detect strong emotions of anger or sadness can trigger a request for that employee to take a break or handle different tasks, or can help improve the emotional state of that employee or potentially connect that employee to different calls that may better match their emotional state. It is also possible to log emotion state data about a call, and when a customer lodges a complaint about an employee being angry or rude during a call, the emotion state data can be analyzed to determine whether the complaint may be valid.

[0024] Such data can be beneficial in analyzing the speech of customers or people outside the call center. For example, if it can be determined that the caller is getting angry during the call, the call center may decide to connect the call to different employees, such as managers or people skilled in handling certain emotions or emotional states. Similarly, the data recorded about the call can be used to verify the emotional state of the caller during the call, which can be useful for tasks such as verifying complaint-related information or training employees at least partially based on the emotional state of the caller during the call. If the emotional state can be determined through an initial menu of options that the customer navigates through voice commands, the call can be initially connected based on the caller's emotional state, or information about that emotional state can be provided to call center employees in advance, which can help the employees prepare and respond more appropriately to the call. In the case of a call center where employees read at least a portion of their responses from a script, the emotional state can be useful in selecting a more accurate script for the current situation, such as using kinder language if the customer is inferred to be angry or more supportive language if the customer is judged to be sad. The emotional state of the caller can be useful in determining where to connect the call, at least initially, if the call center uses a virtual bot or virtual assistant. For example, instead of continuing a completely automated call, if the caller is determined to be irritated, angry, frustrated, etc., the call may be transferred to a human agent.

[0025] In at least some embodiments, the ability to change the emotional state associated with individual keyframes, or to adjust the location or frequency of these keyframes, can result in emotional changes that do not appear natural when displayed. For example, a speaker may start a long sentence in a sad state rather than an angry state, but then transition to an angry state rather than a sad state. Also, during a sentence, it may be determined that for a given keyframe, the speaker has an emotion different from the rest of the sentence. However, sudden changes in emotion may have an unpleasant transition or may not at least somewhat match actual human behavior where the emotional transition can be at least somewhat gradual. Approaches in at least some embodiments can attempt to smooth out inaccurate predictions of the model and achieve a more natural transition between emotional states by utilizing one or more of several heuristics or post-processing operations (e.g., it is rare for a person to instantaneously transition from 100% sadness to 100% anger in the middle of a sentence). In at least one embodiment, this may include using a sliding window approach, such as the approach discussed with respect to audio data. However, the sliding window is used with respect to the keyframes determined for the audio. This can include performing smoothing for at least non-neutral emotions over several keyframes, and the number of those keyframes (e.g., 2 - 10) can be specified, among other options, by the user or application, or can be determined based at least in part on the number or frequency of keyframes determined for the audio clip.

[0026] In one embodiment, the system can enable a user, an application, or other such source to specify or adjust an emotional intensity value. For example, a user can select a ratio from 0 to 1 that represents the emotional intensity. In at least one embodiment, a larger emotional intensity value corresponds to a higher level of expressiveness of the corresponding emotion. If the intensity is set to 0, this may indicate that the lack of expressiveness of that emotion is being used. For example, in a video game, it may be desirable for a villain character not to show any sadness or happiness, and the user can specify a value of 0 for the emotional intensity for these emotions, and it is determined that the character expresses things only with, for example, anger, disgust, or neutral emotions. If the character is to be a very happy character, the user can set the emotional intensity for the emotion of happiness close to 1 (for example, 0.9) and may set the values of other emotional intensities much lower. Such an approach can not only achieve smoothness in emotion determination but also make a more appropriate emotion determination for a given character.

[0027] Available heuristics may also enable the specification or adjustment of prior sentiment. In this context, "prior" sentiment does not refer to sentiment previously determined or presented within the audio file, but rather, for example, to sentiment or a sentiment state determined prior to dynamic analysis by a transformer-based neural network 202. This may include, for example, sentiment specified for a given instance of an utterance within the audio data by a user, application, or action. For example, if sentiment determination is used to generate facial animations, the user may specify that the character to be animated during this utterance should look sad. However, as noted above, using only a single sentiment throughout an instance of an utterance may not appear natural. In that case, the system enables the user (or other such source) to specify the prior sentiment to be used for the instance of the utterance, but also infers changes in sentiment for various keyframes within that utterance. The sentiment and current sentiment values may be mixed such that the character appears generally sad at various times as if showing the prior sentiment, or appears somewhat angry over a portion of the utterance, etc., where this sentiment may be mixed with different sentiments at different times during the utterance. To enable some degree of control over this mixing, a prior sentiment intensity value may also be supplied. This can function as a kind of weighting indicating to what degree this prior sentiment value should be mixed with the sentiment determined by the neural network, where a prior sentiment intensity of 0.9 may cause the sentiment value to primarily reflect the prior sentiment, while a prior sentiment intensity of approximately 0.3 may cause the sentiment value to at least somewhat reflect the prior sentiment throughout the utterance, enabling at least some degree of smoothing of the sentiment determination throughout the utterance.

[0028] Figures 4A and 4B show exemplary states 400, 450 of a user interface that can be used to, among other things, indicate sentiment about training data and provide style or modification data for sentiment determination during inference. When specifying or modifying sentiment data, an animation, rendering, or reconstruction representing one or more determined sentiment probability values 406 may be displayed. A user viewing this interface may make any value adjustments that are determined to be appropriate. For example, the sentiment determination may primarily be determined to be anger, but a listener may also interpret the speech pattern of this utterance as sounding somewhat sad. To more accurately label the data, the user may adjust the applied labels so that the network learns to more accurately interpret sentiment within the audio data. As shown, a time point 404 (e.g., the location of a keyframe) can be indicated within the audio data 402 to which these settings are applied. As described above, a single setting may be used for an audio clip or segment, but in other situations, the sentiment state may change within such a clip or segment at various time points and / or for / at specific frames of an animation, which may be referred to herein as sentiment keyframes. A sentiment keyframe can indicate the timing at which one or more values for sentiment or style change, and corresponding input vectors having these values can be provided as input to the network during training to learn these changes.

[0029] The user of this interface can also specify a prior emotion 408 to be mixed into the emotion determination. The user can also specify a prior emotion intensity 410 that can be used to determine the mixing weight for the determined emotion for that prior emotion. As shown in FIG. 4A, the prior emotion value of "anger" has a corresponding prior emotion intensity value of 0.0. Thus, the emotional state indicated by the rendered image 412 is determined to be mainly joy according to the determined emotion setting 406 or probability. As shown in FIG. 4B, when the user adjusts the prior emotion intensity value 452 to 0.6, an emotion of anger mixed with the emotion determination of joy (and neutral) occurs, whereby, as shown in the rendered image 454, an emotional state of equal mixing of joy and anger is obtained, such as when the user is satisfied with the result but dissatisfied with the approach used to obtain the result. As described above, an emotion intensity may also be provided for each individual emotion, which can be used, among other things, for smoothing emotions or modifying emotion determinations. The interface, such as that shown in FIG. 4A, may also allow the user to adjust the values for emotions and / or prior emotions, as well as related values, at different keyframes or points 404 within the audio. Such an interface may also allow the user to select any values that can be used to modify or control which heuristics should be applied to a given audio clip and the form in which these heuristics are applied.

[0030] As described above, such an interface can be used as a kind of post - processing process during inference and, in at least some embodiments, can also be used for continuous learning. For example, a user can view the generated animation playback through this interface, where the animation of the character is presented. In FIG. 4B, if the user believes that the degree of intensity included in the animation for the situation is too high, the user can adjust the intensity style selector to reduce the intensity and re - render the frames of the animation. If the user notices a slight sadness not captured in the animation within the character's speech, the user can also make adjustments to that setting. In some embodiments, the user may also be able to make adjustments to specific feature points or facial components on the display as a kind of style input. For example, the user can use a pointer to grab and move the position of the character's lips, and this information can be used as style input for re - rendering the animation. Other changes can also be made, such as head movement, head tilt, eye movement and focus, or other such changes that can be communicated through emotion or style input for re - rendering (or updated rendering or composition) of the animation. Various other animation control parameters that can affect the final rendering can likewise be specified through such an interface.

[0031] In some embodiments, the transformer-based neural network 202 and the deep neural network 306 may be trained in an end-to-end manner, and the output from the deep neural network 306 may be used not only for the network 306 but also to update the parameters of the network 202. For example, the probability or confidence for a particular segment of audio data was determined to be very high for anger (e.g., 0.9), but if the animated character animated using 0.9 anger as input to the network 306 appears to have too rich an expression or not look human, this feedback may be used to adjust the parameters of the network 202 and instead train the network 202 to predict a lower anger confidence (e.g., 0.7) or probability for a similar utterance type. In this way, the emotional state or class (and corresponding confidence) can be fine-tuned to assist the network 306 in generating animations that more accurately or precisely mimic the emotion.

[0032] Figure 5 shows an exemplary process 500 for inferring emotion from an input audio clip that can be used according to at least one embodiment. For this process and other processes presented herein, unless otherwise specified, within the scope of various embodiments, additional, fewer, or alternative steps may be performed in a similar order or in an alternative order, or at least partially in parallel. In this process, audio data representing an utterance made by at least one speaker, such as at least one human making an utterance during a conversation, is obtained 502. This utterance may have been captured by an audio capture device, such as at least one microphone or microphone array, and then converted to digital audio data. This audio data can be segmented 504 into segments of utterances that have been made or labeled as corresponding to individual speakers (e.g., if there are multiple speakers but one speaker stands out). An audio segment for emotion analysis may be selected 506, and this audio segment can be provided as input to a transformer-based neural network, or other such emotion determination network or algorithm 508. One or more frames of the segment can be analyzed using the neural network to infer probability (or other) values for a set of emotions 510. These can include, among other options, a fixed set of emotions for which the neural network was trained, as well as, optionally, additional emotions learned by the network through continuous learning. The number of frames in the segment can depend on several factors, such as the length or content of the segment, and the window or stride size for analysis. For each frame of the segment, an emotion vector indicating the probability for a set of emotions or at least a subset of emotions can be received 512. A determination can be made as to whether some heuristic should be applied to the emotion vector 514.If determined to be applicable, one or more of these heuristics can be applied to the vector, among a number of options, to perform smoothing or sentiment determination adjustment, for example 516. In some embodiments, this may include adjusting the sentiment probability value based on the prior sentiment and / or sentiment intensity, as discussed herein. After any heuristics, the sentiment vector can be provided to an application (or other recipient or destination) for use in performing one or more sentiment-based tasks or analyses 518. A determination may be made as to whether there is a further segment to be analyzed 520, and if there is a further segment, the process may continue to the next segment. In some embodiments, the segment analysis may be performed in parallel for at least a portion of the segment. After the sentiment vector is provided, the user may be enabled to review the values in these sentiment vectors and modify them as appropriate, such as by performing adjustments deemed appropriate by the user for a given sentiment-based task 522.

[0033] As an example, the sentiment vector may be provided to a face animation process, which attempts to generate animations having realistic behavior for various emotional states for various different character types. This can include, for example, audio-driven full three-dimensional (3D) face animations with emotion control. In such an approach, realistic animations can be generated, which, while possible if desired, do not require any manual input or post-processing. Automating such animations can help significantly reduce the time, experience, and cost required for manual (or at least partially manual) character animation. Audio-driven face animation can achieve an efficient form of generating face animations compared to conventional approaches, as only audio data is required to animate a given character's face.

[0034] Various systems can also support retargeting. In retargeting, the motion of one character can be mapped to the motion of another character, thereby generating similar animations for similar emotions and / or styles. Interfaces, such as those shown in FIGS. 4A and 4B, can be even more beneficial when remapping context in cases where different characters may express emotions and styles in slightly different ways. A user can load different characters into this interface, view how the retargeted rendering looks for that character, and then modify one or more aspects or styles of motion or behavior for that particular character, or type of character.

[0035] As discussed, aspects of the various approaches presented herein can be made lightweight enough to be executed in real time or near real time on devices such as client devices, such as personal computers and gaming consoles. Such processing can be performed on content received from external sources (e.g., a rendered version of a unique asset), such as streaming sensor data or other content generated on or received by that client device, or received via at least one network. In some cases, the processing and / or determination of this content may be performed by one of these other devices, systems, or entities and then provided to the client device (or another such recipient) for presentation or other such use.

[0036] In one example, FIG. 6 shows an exemplary network configuration 600 that can be used to provide, generate, modify, encode, and / or transmit data or other such content. In at least one embodiment, client device 602 can generate or receive data for a session using components of content application 604 on client device 602 and data stored locally on that client device. In at least one embodiment, content application 624 running on server 620 (e.g., a cloud server or an edge server) can start a session associated with at least one client device 602, using user data stored in session manager and user database 634 to cause content manager 626 to determine content 632. Content manager 626 may cooperate with audio-face module 628 for determining a face animation corresponding to input audio, and emotion application 630 that can execute one or more tasks using the determined emotion data. This may include, for example, using audio data, within an acceptable range determined by rights manager 630 or other such component or service, to generate an image, video, or other visual presentation using an asset (e.g., a character mesh) from asset database 632. At least a portion of the generated content (separate and different from the asset itself) may be transmitted to client device 602 using appropriate transmission manager 622 for sending via download, streaming, or another such transmission channel. An encoder may be used to encode and / or compress at least a portion of this data before transmitting it to client device 602.In at least one embodiment, a client device 602 that receives such content can provide this content to a corresponding content application 604, which may in turn or alternatively include a graphical user interface 610, an audio-visual component 612, and an emotion application 614 for use in performing emotion-based tasks. Also, a decoder may be used to decode data received via network 640 for presentation via client device 602, such as image or video content via display 606, and audio such as sound or music via at least one audio playback device 608 such as a speaker or headphones. In at least one embodiment, at least a portion of this content may already be stored on client device 602, rendered on client device 602, or accessible to client device 602, such that transmission via network 640 is not required for at least that portion of the content, such as when the content has been previously downloaded or may be stored locally on a hard drive or optical disk. In at least one embodiment, a transmission mechanism such as data streaming can be used to transfer this content from server 620, or user database 634, to client device 602. In at least one embodiment, at least a portion of this content can be obtained or streamed from another source such as a third-party service 660 that may also include a content application 662 for generating or providing the content, or another client device 650. In at least one embodiment, a portion of this functionality can be performed using multiple processors within one or more computing devices, which may include a combination of multiple computing devices, or a CPU and GPU.

[0037] In this example, these client devices can include any suitable computing device, and these computing devices can include, among other numerous options, desktop computers, laptop computers, set-top boxes, streaming devices, gaming consoles, smartphones, tablet computers, VR / AR / MR headsets, VR / AR / MR goggles, wearable computers, or smart TVs, etc. Each client device can send requests via at least one wired or wireless network, and these networks can include, among several options, especially the Internet, Ethernet (registered trademark), local area network (LAN), or cellular network, etc. In this example, these requests can be sent to an address associated with a cloud provider, and the cloud provider can operate or control one or more electronic resources within a cloud provider environment that may include a data center or a server farm, etc. In at least one embodiment, the requests may be received or processed by at least one edge server located on the network edge and outside of at least one security layer associated with the cloud provider environment. In this way, latency can be reduced by enabling the client device to interact with a closer server while improving the security of the resources within the cloud provider environment.

[0038] In at least one embodiment, such a system can be used to perform graphical rendering operations. In other embodiments, such a system can be used for other purposes, such as providing image or video content for testing or validating autonomous machine applications, or performing deep learning operations. In at least one embodiment, such a system can be implemented using edge devices, or may incorporate one or more virtual machines (VMs). In at least one embodiment, such a system can be implemented at least partially within a data center or using at least partially cloud computing resources.

[0039] Inference and training logic FIG. 7A shows inference and / or training logic 715 used to perform inference and / or training operations with respect to one or more embodiments. Details regarding the inference and / or training logic 715 are provided below in conjunction with FIGS. 7A and / or 7B.

[0040] In at least one embodiment, the inference and / or training logic 715 may include, but is not limited to, code and / or data storage 701 for storing forward propagation and / or output weights, and / or input / output data, and / or other parameters for constructing neurons or layers of a neural network that are trained and / or used to infer in one or more embodiments of the aspects. In at least one embodiment, the training logic 715 may include, or be coupled to, code and / or data storage 701 for storing graph code or other software for controlling timing and / or order, and the code and / or data storage 701 has weight and / or other parameter information loaded to configure logic including an integer and / or floating point unit (collectively referred to as an arithmetic logic unit (ALU)). In at least one embodiment, code such as graph code loads weight or other parameter information to the processor ALU based on the architecture of the neural network to which the code corresponds. In at least one embodiment, the code and / or data storage 701 stores the weight parameters and / or input / output data of each layer of the neural network that is trained or used in conjunction with one or more embodiments during forward propagation of the input / output data and / or weight parameters during training and / or inference using one or more embodiments of the aspects. In at least one embodiment, any portion of the code and / or data storage 701 may be included with the L1, L2, or L3 cache of the processor, or other on-chip or off-chip data storage including system memory.

[0041] In at least one embodiment, any portion of the code and / or data storage 701 may be internal or external to one or more processors or other hardware logic devices or circuits. In at least one embodiment, the code and / or the code and / or data storage 701 may be cache memory, dynamic randomly addressable memory (“DRAM”), static randomly addressable memory (“SRAM”), non-volatile memory (e.g., flash memory), or other storage. In at least one embodiment, the choice of whether the code and / or the code and / or data storage 701 is internal or external to, for example, a processor, or the choice of whether it consists of DRAM, SRAM, flash, or some other type of storage, may be determined according to on-chip versus off-chip available storage, the latency requirements of the training and / or functions being performed, the batch size of the data used for neural network inference and / or use, or any combination of these factors.

[0042] In at least one embodiment, the inference and / or training logic 715 may include, but is not limited to, backpropagation and / or output weights corresponding to neurons or layers of a neural network that are trained and / or used for inference in one or more embodiments, and / or code and / or data storage 705 for storing input / output data. In at least one embodiment, the code and / or data storage 705 stores the weight parameters and / or input / output data of each layer of a neural network that is trained or used in conjunction with one or more embodiments while backpropagating the input / output data and / or weight parameters during training and / or inference using aspects of one or more embodiments. In at least one embodiment, the training logic 715 may include or be coupled to code and / or data storage 705 for storing graph code or other software for controlling timing and / or order, and the code and / or data storage 705 has weight and / or other parameter information loaded therein to configure logic including integer and / or floating point units (collectively referred to as arithmetic logic units (ALUs)). In at least one embodiment, code such as graph code loads weight or other parameter information into the processor ALU based on the architecture of the neural network to which the code corresponds. In at least one embodiment, any portion of the code and / or data storage 705 may be included with the L1, L2, or L3 cache of the processor, or other on-chip or off-chip data storage including system memory. In at least one embodiment, any portion of the code and / or data storage 705 may be internal or external to one or more processors, or other hardware logic devices or circuits. In at least one embodiment, the code and / or data storage 705 may be cache memory, DRAM, SRAM, non-volatile memory (e.g., flash memory), or other storage.In at least one embodiment, the selection of whether the code and / or data storage 705 is, for example, internal or external to the processor, or the selection of whether it is composed of DRAM, SRAM, flash, or some other type of storage, may be determined according to the on-chip versus off-chip available storage, the latency requirements of the training and / or inference functions being executed, the batch size of the data used in the neural network inference and / or training, or any combination of these factors.

[0043] In at least one embodiment, the code and / or data storage 701 and the code and / or data storage 705 may be separate storage structures. In at least one embodiment, the code and / or data storage 701 and the code and / or data storage 705 may be the same storage structure. In at least one embodiment, the code and / or data storage 701 and the code and / or data storage 705 may be partially the same storage structure and partially separate storage structures. In at least one embodiment, any part of the code and / or data storage 701 and the code and / or data storage 705 may be included together with the L1, L2, or L3 cache of the processor, or other on-chip or off-chip data storage including system memory.

[0044] In at least one example, the inference and / or training logic 715 may include one or more arithmetic logic units (ALUs) 710 including integer and / or floating point units to perform logical and / or arithmetic operations based at least in part on and / or indicated by training and / or inference code (e.g., graph code), the result of which may generate activations (e.g., output values from a layer or neuron within a neural network) stored in activation storage 720, which are a function of code and / or data storage 701 and / or input / output and / or weight parameter data stored in code and / or data storage 705. In at least one example, the activations stored in activation storage 720 are generated in accordance with linear algebra computations and / or matrix-based computations performed by ALU 710 in response to executing instructions or other code, where the weight values stored in code and / or data storage 705 and / or code and / or data storage 701 are used as operands along with other values such as bias values, gradient information, momentum values, or other parameters or hyperparameters, any or all of which may be stored in code and / or data storage 705, or code and / or data storage 701, or another storage on-chip or off-chip.

[0045] In at least one embodiment, the ALU 710 may be included within one or more processors or other hardware logic devices or circuits. In another embodiment, the ALU 710 may be external to the processor or other hardware logic device or circuit that uses it (e.g., a co-processor). In at least one embodiment, the ALU 710 may be included within the execution unit of a processor, or may be otherwise included within an ALU bank accessible by an execution unit of a processor that is either within the same processor or distributed among different types of different processors (e.g., a central processing unit, a graphics processing unit, a fixed function unit, etc.) within the same or different processors. In at least one embodiment, the code and / or data storage 701, the code and / or data storage 705, and the activation storage 720 may be in the same processor or other hardware logic device or circuit. In another embodiment, they may be in different processors or other hardware logic devices or circuits, or in any combination of the same processor or other hardware logic device or circuit and different processors or other hardware logic devices or circuits. In at least one embodiment, any portion of the activation storage 720 may be included with the L1, L2, or L3 cache of the processor, or other on-chip or off-chip data storage including system memory. Further, the inference and / or training code may be stored together with other code accessible to the processor or other hardware logic or circuit, and may be fetched and / or processed using the fetch, decode, scheduling, execution, retirement, and / or other logic circuits of the processor.

[0046] In at least one embodiment, the activation storage 720 may be cache memory, DRAM, SRAM, non-volatile memory (e.g., flash memory), or other storage. In at least one embodiment, the activation storage 720 may be wholly or partially internal or external to one or more processors or other logic circuits. In at least one embodiment, the choice of whether the activation storage 720 is internal or external to, for example, a processor, or the choice of being composed of DRAM, SRAM, flash, or some other type of storage, may be determined according to on-chip versus off-chip available storage, latency requirements of the training and / or inference functions being executed, the batch size of the data used in the neural network inference and / or training, or any combination of these factors. In at least one embodiment, the inference and / or training logic 715 shown in FIG. 7a may be used in conjunction with an application-specific integrated circuit (ASIC) such as a TensorFlow® processing unit from Google, an inference processing unit (IPU) from Graphcore®, or a Nervana® (e.g., "Lake Crest") processor from Intel Corp. In at least one embodiment, the inference and / or training logic 715 shown in FIG. 7a may be used in conjunction with other hardware such as central processing unit (CPU) hardware, graphics processing unit (GPU) hardware, or field programmable gate array (FPGA).

[0047] FIG. 7b shows inference and / or training logic 715 according to at least one or more embodiments. In at least one embodiment, the inference and / or training logic 715 may include, but is not limited to, hardware logic in which computing resources are dedicated to or otherwise used only in conjunction with weight values or other information corresponding to one or more layers of neurons in a neural network. In at least one embodiment, the inference and / or training logic 715 shown in FIG. 7b may be used in conjunction with an application-specific integrated circuit (ASIC) such as a TensorFlow® processing unit from Google, an inference processing unit (IPU) from Graphcore®, or a Nervana® (e.g., "Lake Crest") processor from Intel Corp. In at least one embodiment, the inference and / or training logic 715 shown in FIG. 7b may be used in conjunction with other hardware such as central processing unit (CPU) hardware, graphics processing unit (GPU) hardware, or a field programmable gate array (FPGA). In at least one embodiment, the inference and / or training logic 715 may include, but is not limited to, code and / or data storage 701, and code and / or data storage 705, which may be used to store code (e.g., graph code), weight values, and / or bias values, gradient information, momentum values, and / or other information including other parameters or hyperparameter information. In at least one embodiment shown in FIG. 7b, each of code and / or data storage 701 and code and / or data storage 705 is associated with dedicated computing resources such as computing hardware 702 and computing hardware 706, respectively. In at least one embodiment, each of computing hardware 702 and computing hardware 706 comprises one or more ALUs that execute mathematical functions, such as linear algebra functions, only on the information stored in code and / or data storage 701 and code and / or data storage 705, respectively, the results of which are stored in activation storage 720.

[0048] In at least one embodiment, each of code and / or data storage 701 and 705, and corresponding compute hardware 702 and 706, respectively corresponds to different layers of a neural network, such that the activation resulting from one “storage / compute pair 701 / 702” of code and / or data storage 701 and compute hardware 702 is provided as an input to a “storage / compute pair 705 / 706” of code and / or data storage 705 and compute hardware 706 in order to reflect the conceptual organization of the neural network. In at least one embodiment, each of storage / compute pairs 701 / 702 and 705 / 706 may correspond to more than one neural network layer. In at least one embodiment, additional storage / compute pairs (not shown) may be included in inference and / or training logic 715 after or in parallel with storage / compute pairs 701 / 702 and 705 / 706.

[0049] Data center FIG. 8 shows an exemplary data center 800 that may be used in at least one embodiment. In at least one embodiment, data center 800 includes a data center infrastructure layer 810, a framework layer 820, a software layer 830, and an application layer 840.

[0050] As shown in FIG. 8, in at least one embodiment, the data center infrastructure layer 810 may include a resource orchestrator 812, grouped computing resources 814, and node computing resources (“node C.R.”) 816(1) to 816(N), where “N” represents any positive integer. In at least one embodiment, the node C.R. 816(1) to 816(N) may include, but are not limited to, any number of central processing units (“CPU”) or other processors (including accelerators, field programmable gate arrays (FPGA), graphics processors, etc.), memory devices (e.g., dynamic read-only memory), storage devices (e.g., solid state drives or disk drives), network input / output (“NW I / O”) devices, network switches, virtual machines (“VM”), power modules, and cooling modules. In at least one embodiment, one or more of the node C.R. 816(1) to 816(N) may be servers having one or more of the computing resources described above.

[0051] In at least one embodiment, the grouped computing resources 814 may include separate groups of node C.R.s housed within one or more racks (not shown), or multiple racks housed in a data center at various graphical locations (also not shown). Separate groups of node C.R.s within the grouped computing resources 814 may include grouped computing resources, network resources, memory resources, or storage resources that may be configured or allocated to support one or more workloads. In at least one embodiment, some node C.R.s including a CPU or processor may be grouped within one or more racks to provide computing resources for supporting one or more workloads. In at least one embodiment, one or more racks may also include any number of power modules, cooling modules, and network switches in any combination.

[0052] In at least one embodiment, the resource orchestrator 812 may configure or otherwise control one or more node C.R.s 816(1)-816(N) and / or the grouped computing resources 814. In at least one embodiment, the resource orchestrator 812 may include a software design infrastructure ("SDI") management entity for the data center 800. In at least one embodiment, the resource orchestrator may include hardware, software, or some combination thereof.

[0053] As shown in FIG. 8, in at least one embodiment, the framework layer 820 includes a job scheduler 822, a configuration manager 824, a resource manager 826, and a distributed file system 828. In at least one embodiment, the framework layer 820 may include a framework for supporting software 832 of the software layer 830 and / or one or more applications 842 of the application layer 840. In at least one embodiment, the software 832 or the application 842 may each include web-based service software or an application, such as those provided by Amazon Web Services, Google Cloud, and Microsoft Azure. In at least one embodiment, the framework layer 820 may be a kind of free and open-source software web application framework, such as Apache Spark (registered trademark) (hereinafter "Spark") that can use the distributed file system 828 for large-scale data processing (e.g., "big data"), but is not limited thereto. In at least one embodiment, the job scheduler 822 may include a Spark driver to facilitate scheduling of workloads supported by various layers of the data center 800. In at least one embodiment, the configuration manager 824 may be able to configure different layers, such as the software layer 830 and the framework layer 820 including Spark and the distributed file system 828 for supporting large-scale data processing. In at least one embodiment, the resource manager 826 may be able to manage clustered or grouped computing resources mapped or allocated to support the distributed file system 828 and the job scheduler 822. In at least one embodiment, the clustered or grouped computing resources may include grouped computing resources 814 in the data center infrastructure layer 810.In at least one embodiment, the resource manager 826 may manage these mapped or allocated computing resources in cooperation with the resource orchestrator 812.

[0054] In at least one embodiment, the software 832 included in the software layer 830 may include software used by at least a portion of the node C.R. 816(1)-816(N), the grouped computing resources 814, and / or the distributed file system 828 of the framework layer 820. One or more types of software may include, but are not limited to, Internet web page search software, email virus scan software, database software, and streaming video content software.

[0055] In at least one embodiment, the application 842 included in the application layer 840 may include one or more types of applications used by at least a portion of the node C.R. 816(1)-816(N), the grouped computing resources 814, and / or the distributed file system 828 of the framework layer 820. One or more types of applications may include, but are not limited to, any number of genomics applications, cognitive compute, and software for training or inference, machine learning applications including machine learning framework software (e.g., PyTorch, TensorFlow, Caffe, etc.), or other machine learning applications used in conjunction with one or more embodiments.

[0056] In at least one embodiment, any one of configuration manager 824, resource manager 826, and resource orchestrator 812 may perform any number and type of self-correcting actions based on any amount and type of data obtained in any technically feasible manner. In at least one embodiment, the self-correcting actions may prevent the data center operator of data center 800 from determining configurations that may be defective and, optionally, may eliminate portions of the data center that are not being fully utilized and / or have low performance.

[0057] In at least one embodiment, data center 800 may include tools, services, software, or other resources for training one or more machine learning models or for predicting or inferring information using one or more machine learning models according to one or more embodiments described herein. For example, in at least one embodiment, a machine learning model may be trained by calculating weight parameters according to a neural network architecture using the software and computing resources described above with respect to data center 800. In at least one embodiment, a trained machine learning model corresponding to one or more neural networks may be used to infer or predict information using the resources described above with respect to data center 800 by using the weight parameters calculated by one or more of the training techniques described herein.

[0058] In at least one embodiment, the data center may use a CPU, an application specific integrated circuit (ASIC), a GPU, an FPGA, or other hardware to perform training and / or inference using the resources described above. Additionally, one or more of the software and / or hardware resources described above may be configured as a service to enable a user to perform training or inference of information, such as image recognition, speech recognition, or other artificial intelligence services.

[0059] Inference and / or training logic 715 is used to perform inference and / or training operations associated with one or more embodiments. Details regarding the inference and / or training logic 715 are provided below in conjunction with FIGS. 7A and / or 7B. In at least one embodiment, the inference and / or training logic 715 may be used in the system of FIG. 8 for inference or prediction operations, at least in part based on weight parameters calculated using the training operations of the neural network, the functionality and / or architecture of the neural network, or the use cases of the neural network described herein.

[0060] Such components can be used to determine one or more sentiment values from audio data.

[0061] Computer system FIG. 9 is a block diagram showing an exemplary computer system, which may be a system 900 having interconnected devices and components, a system-on-a-chip (SoC), or some combination thereof, formed with a processor that may include an execution unit for executing instructions, according to at least one embodiment. In at least one embodiment, computer system 900 may include components such as processor 902 for using an execution unit that includes logic for executing algorithms for processing data in accordance with the present disclosure, such as in the embodiments described herein, although not limited thereto. In at least one embodiment, computer system 900 may include a processor such as a PENTIUM® processor family, Xeon™, Itanium® from Intel Corporation of Santa Clara, California, XScale™ and / or StrongARM™, Intel® Core™, or Intel® Nervana™ microprocessor, although other systems (including PCs having other microprocessors, engineering workstations, set-top boxes, etc.) may be used. In at least one embodiment, computer system 900 may execute a version of the WINDOWS® operating system available from Microsoft Corporation of Redmond, Washington, although other operating systems (e.g., UNIX® and Linux), embedded software, and / or graphical user interfaces may be used.

[0062] Embodiments may be used in other devices such as portable devices and embedded applications. Some examples of portable devices include cellular phones, Internet Protocol devices, digital cameras, personal digital assistants (PDAs), and laptop PCs. In at least one embodiment, the embedded application may include a microcontroller, a digital signal processor (DSP), a system-on-chip, a network computer (NetPC), a set-top box, a network hub, a wide area network (WAN) switch, or any other system capable of executing one or more instructions according to at least one embodiment.

[0063] In at least one embodiment, the computer system 900 may include, without limitation, a processor 902, which may include, without limitation, one or more execution units 908 for performing training and / or inference of a machine learning model by the techniques described herein. In at least one embodiment, the computer system 900 is a single-processor desktop or server system, while in another embodiment, the computer system 900 may be a multi-processor system. In at least one embodiment, the processor 902 may include, without limitation, a complex instruction set computer (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a processor implementing a combination of instruction sets, or any other processor device, such as a digital signal processor. In at least one embodiment, the processor 902 may be coupled to a processor bus 910, which may transmit data signals between the processor 902 and other components within the computer system 900.

[0064] In at least one embodiment, the processor 902 may include, without limitation, a level 1 (L1) internal cache memory (cache) 904. In at least one embodiment, the processor 902 may have a single internal cache or multiple levels of internal caches. In at least one embodiment, the cache memory may be external to the processor 902. Other embodiments may also include a combination of both internal and external caches, depending on the particular implementation and requirements. In at least one embodiment, the register file 906 may store different types of data in various registers, including, without limitation, integer registers, floating-point registers, status registers, and instruction pointer registers.

[0065] In at least one embodiment, although not limited thereto, an execution unit 908 including logic for performing integer and floating point operations is also in the processor 902. In at least one embodiment, the processor 902 may also include a read only memory (ROM) for storing microcode (u-code) for certain macro instructions. In at least one embodiment, the execution unit 908 may include logic for handling a packed instruction set 909. In at least one embodiment, by including the packed instruction set 909 in the instruction set of the general purpose processor 902 along with the associated circuitry for executing the instructions, operations used by many multimedia applications can be executed using the packed data of the general purpose processor 902. In one or more embodiments, by performing operations on packed data using the full width of the processor's data bus, many multimedia applications can be accelerated and executed more efficiently, thereby eliminating the need to transfer smaller units of data between the processor's data buses to perform one or more operations on one data element at a time.

[0066] In at least one embodiment, the execution unit 908 may also be used in microcontrollers, embedded processors, graphics devices, DSPs, and other types of logic circuits. In at least one embodiment, the computer system 900 may include, although not limited thereto, a memory 920. In at least one embodiment, the memory 920 may be implemented as a dynamic random access memory (DRAM) device, a static random access memory (SRAM) device, a flash memory device, or other memory device. In at least one embodiment, the memory 920 may store instructions 919 and / or data 921 represented by data signals that can be executed by the processor 902.

[0067] In at least one embodiment, a system logic chip may be coupled to a processor bus 910 and a memory 920. In at least one embodiment, the system logic chip may include, but is not limited to, a memory controller hub (“MCH”) 916, and the processor 902 may communicate with the MCH 916 via the processor bus 910. In at least one embodiment, the MCH 916 may provide a high-bandwidth memory path 918 to the memory 920 for storing instructions and data, as well as for storing graphics commands, data, and textures. In at least one embodiment, the MCH 916 may direct data signals between the processor 902, the memory 920, and other components of the computer system 900, and may bridge data signals between the processor bus 910, the memory 920, and the system I / O interface 922. In at least one embodiment, the system logic chip may provide a graphics port for coupling to a graphics controller. In at least one embodiment, the MCH 916 may be coupled to the memory 920 via the high-bandwidth memory path 918, and the graphics / video card 912 may be coupled to the MCH 916 via an Accelerated Graphics Port (“AGP”) interconnect 914.

[0068] In at least one embodiment, computer system 900 may use a system I / O 922, which is a proprietary hub interface bus for coupling MCH 916 to an I / O controller hub (“ICH”) 930. In at least one embodiment, ICH 930 may provide direct connections to several I / O devices via a local I / O bus. In at least one embodiment, the local I / O bus may include, but is not limited to, a high-speed I / O bus for connecting peripheral devices to memory 920, the chipset, and processor 902. Examples may include, but are not limited to, an audio controller 929, a firmware hub (“Flash BIOS”) 928, a wireless transceiver 926, data storage 924, a legacy I / O controller 923 including a user input and keyboard interface 925, a serial expansion port such as a Universal Serial Bus (“USB”), and a network controller 934. Data storage 924 may comprise a hard disk drive, a floppy (registered trademark) disk drive, a CD-ROM device, a flash memory device, or other mass storage device.

[0069] In at least one embodiment, FIG. 9 shows a system including interconnected hardware devices or “chips,” while in other embodiments, FIG. 9 may show an exemplary system-on-chip (“SoC”). In at least one embodiment, the devices may be interconnected by proprietary interconnects, standard interconnects (e.g., PCIe), or some combination thereof. In at least one embodiment, one or more components of computer system 900 may be interconnected using a Compute Express Link (CXL) interconnect.

[0070] Using inference and / or training logic 715, inference and / or training operations associated with one or more embodiments are performed. Details regarding the inference and / or training logic 715 are provided below in conjunction with FIGS. 7A and / or 7B. In at least one embodiment, the inference and / or training logic 715 may be used in the system of FIG. 9 for inference or prediction operations, at least in part based on the training operations of the neural network described herein, the functions and / or architecture of the neural network, or the weight parameters calculated using the use cases of the neural network.

[0071] Such components may be used to determine one or more sentiment values from audio data.

[0072] FIG. 10 is a block diagram showing an electronic device 1000 for using a processor 1010 according to at least one embodiment. In at least one embodiment, the electronic device 1000 may be, for example but not limited to, a notebook, a tower server, a rack server, a blade server, a laptop, a desktop, a tablet, a mobile device, a phone, an embedded computer, or any other suitable electronic device.

[0073] In at least one embodiment, system 1000 may include a processor 1010 communicatively coupled to any suitable number or type of components, peripherals, modules, or devices, including but not limited to. In at least one embodiment, processor 1010 is coupled using a bus or interface such as a 1°C bus, a system management bus (“SMBus”), a low pin count (“LPC”) bus, a serial peripheral interface (“SPI”), a high definition audio (“HDA”) bus, a serial advance technology attachment (“SATA”) bus, a universal serial bus (“USB”) (versions 1, 2, 3), or a universal asynchronous receiver / transmitter (“UART”) bus. In at least one embodiment, FIG. 10 shows a system including interconnected hardware devices or “chips,” although in other embodiments, FIG. 10 may show an exemplary system-on-chip (“SoC”). In at least one embodiment, the devices shown in FIG. 10 may be interconnected using proprietary interconnects, standard interconnects (e.g., PCIe), or some combination thereof. In at least one embodiment, one or more components of FIG. 10 may be interconnected using a Compute Express Link (CXL) interconnect.

[0074] In at least one embodiment, FIG. 10 shows a display 1024, a touch screen 1025, a touch pad 1030, a near field communications unit (NFC) 1045, a sensor hub 1040, a thermal sensor 1046, an express chipset (EC) 1035, a trusted platform module (TPM) 1038, a BIOS / firmware / flash memory (BIOS, FW flash) 1022, a DSP 1060, a drive 1020 such as a solid state disk (SSD) or a hard disk drive (HDD), a wireless local area network unit (WLAN) 1050, a Bluetooth unit 1052, a wireless wide area network unit (WWAN) 1056, a global positioning system (GPS) 1055, a camera such as a USB3.0 camera (USB3.0 camera) 1054, and / or a low power double data rate (LPDDR) memory unit (LPDDR3) 1015 implemented, for example, in accordance with the LPDDR3 standard. These components may each be implemented in any suitable manner.

[0075] In at least one embodiment, other components may be communicatively coupled to the processor 1010 through the components described above. In at least one embodiment, an accelerometer 1041, an ambient light sensor (ALS) 1042, a compass 1043, and a gyroscope 1044 may be communicatively coupled to the sensor hub 1040. In at least one embodiment, a thermal sensor 1039, a fan 1037, a keyboard 1046, and a touch pad 1030 may be communicatively coupled to the EC 1035. In at least one embodiment, a speaker 1063, headphones 1064, and a microphone ( "mic") 1065 may be communicatively coupled to an audio unit (audio codec and class D amplifier) 1062, and this audio unit may be communicatively coupled to the DSP 1060. In at least one embodiment, the audio unit 1064 may include, for example but not limited to, an audio coder / decoder ( "codec") and a class D amplifier. In at least one embodiment, a SIM card ( "SIM") 1057 may be communicatively coupled to the WWAN unit 1056. In at least one embodiment, components such as the WLAN unit 1050 and the Bluetooth unit 1052, as well as the WWAN unit 1056, may be implemented in a next generation form factor ( "NGFF": Next Generation Form Factor).

[0076] Using the inference and / or training logic 715, the operations of inference and / or training related to one or more embodiments are performed. Details regarding the inference and / or training logic 715 are provided below in conjunction with FIGS. 7a and / or 7b. In at least one embodiment, the inference and / or training logic 715 may be used in the system of FIG. 10 for the operation of inference or prediction, at least in part based on the weight parameters calculated using the training operations of the neural network, the functions and / or architectures of the neural network, or the use cases of the neural network described herein.

[0077] Such components can be used to determine one or more sentiment values from audio data.

[0078] FIG. 11 is a block diagram of a processing system according to at least one embodiment. In at least one embodiment, system 1100 includes one or more processors 1102 and one or more graphics processors 1108 and may be a single-processor desktop system, a multi-processor workstation system, or a server system having a number of processors 1102 or processor cores 1107. In at least one embodiment, system 1100 is a processing platform incorporated within a system-on-chip (SoC) integrated circuit for use in a mobile device, portable device, or embedded device.

[0079] In at least one embodiment, system 1100 may include or be incorporated within a server-based gaming platform, a game console including a game and media console, a mobile gaming console, a portable gaming console, or an online gaming console. In at least one embodiment, system 1100 is a mobile phone, smartphone, tablet computing device, or mobile Internet device. In at least one embodiment, processing system 1100 may also include, be coupled to, or be integrated within wearable devices such as smartwatch wearable devices, smart eyewear devices, augmented reality devices, or virtual reality devices. In at least one embodiment, processing system 1100 is a television or set-top box device having one or more processors 1102 and a graphical interface generated by one or more graphics processors 1108.

[0080] In at least one embodiment, each of one or more processors 1102 includes one or more processor cores 1107 for processing instructions that, when executed, perform operations for system and user software. In at least one embodiment, each of one or more processor cores 1107 is configured to process a particular instruction set 1109. In at least one embodiment, the instruction set 1109 may facilitate computing via a complex instruction set computing (CISC), reduced instruction set computing (RISC), or very long instruction word (VLIW). In at least one embodiment, each of the processor cores 1107 may process a different instruction set 1109, which may include instructions that facilitate emulation of other instruction sets. In at least one embodiment, the processor cores 1107 may also include other processing devices such as a digital signal processor (DSP).

[0081] In at least one embodiment, the processor 1102 includes a cache memory 1104. In at least one embodiment, the processor 1102 may have a single internal cache or multiple levels of internal caches. In at least one embodiment, the cache memory is shared among various components of the processor 1102. In at least one embodiment, the processor 1102 may also use an external cache (e.g., a level 3 (L3) cache or a last level cache (LLC)) (not shown), which may be shared among the processor cores 1107 using known cache coherence techniques. In at least one embodiment, a register file 1106 is further included in the processor 1102, and the register file may include different types of registers (e.g., integer registers, floating point registers, status registers, and instruction pointer registers) for storing different types of data. In at least one embodiment, the register file 1106 may include general purpose registers or other registers.

[0082] In at least one embodiment, one or more processors 1102 are coupled to one or more interface buses 1110 to transmit communication signals such as address, data, or control signals between the processor 1102 and other components within the system 1100. In at least one embodiment, the interface bus 1110 can be a processor bus such as a version of a Direct Media Interface (DMI) bus in one embodiment. In at least one embodiment, the interface 1110 is not limited to the DMI bus and may include one or more peripheral component interconnect buses (e.g., PCI, PCI Express), a memory bus, or other types of interface buses. In at least one embodiment, the processor 1102 includes an integrated memory controller 1116 and a platform controller hub 1130. In at least one embodiment, the memory controller 1116 facilitates communication between the memory device and other components of the system 1100, while the platform controller hub (PCH) 1130 provides connections to I / O devices via a local I / O bus.

[0083] In at least one embodiment, the memory device 1120 can be a dynamic random access memory (DRAM) device, a static random access memory (SRAM) device, a flash memory device, a phase change memory device, or any other memory device having suitable performance to serve as a process memory. In at least one embodiment, the memory device 1120 operates as a system memory for the system 1100 and can store data 1122 and instructions 1121 for use when one or more processors 1102 execute an application or process. In at least one embodiment, the memory controller 1116 is also coupled to an optional external graphics processor 1112, which may communicate with one or more graphics processors 1108 within the processor 1102 to perform graphics and media operations. In at least one embodiment, the display device 1111 can be connected to the processor 1102. In at least one embodiment, the display device 1111 can include one or more of an internal display device such as a mobile electronic device or a laptop device, or an external display device attached via a display interface (e.g., a display port, etc.). In at least one embodiment, the display device 1111 can include a head-mounted display (HMD) such as a stereoscopic display device for use in virtual reality (VR) applications or augmented reality (AR) applications.

[0084] In at least one embodiment, the platform controller hub 1130 enables peripheral devices to be connected to the memory device 1120 and the processor 1102 via a high-speed I / O bus. In at least one embodiment, the I / O peripheral devices include, but are not limited to, an audio controller 1146, a network controller 1134, a firmware interface 1128, a wireless transceiver 1126, a touch sensor 1125, and a data storage device 1124 (e.g., a hard disk drive, flash memory, etc.). In at least one embodiment, the data storage device 1124 can be connected via a storage interface (e.g., SATA) or a peripheral bus such as a Peripheral Component Interconnect bus (e.g., PCI, PCI Express). In at least one embodiment, the touch sensor 1125 can include a touch screen sensor, a pressure sensor, or a fingerprint sensor. In at least one embodiment, the wireless transceiver 1126 can be a WiFi transceiver, a Bluetooth transceiver, or a mobile network transceiver such as a 3G, 4G, or Long Term Evolution (LTE) transceiver. In at least one embodiment, the firmware interface 1128 enables communication with system firmware and can be, for example, a Unified Extensible Firmware Interface (UEFI). In at least one embodiment, the network controller 1134 can enable a network connection to a wired network. In at least one embodiment, a high-performance network controller (not shown) is coupled to the interface bus 1110. In at least one embodiment, the audio controller 1146 is a multi-channel high-definition audio controller. In at least one embodiment, the system 1100 includes an optional legacy I / O controller 1140 for coupling legacy (e.g., Personal System 2 (PS / 2)) devices to the system.In at least one embodiment, the platform controller hub 1130 can also be connected to one or more universal serial bus (USB) controller 1142 connected input devices, such as a combination of a keyboard and a mouse 1143, a camera 1144, or other USB input devices.

[0085] In at least one embodiment, instances of the memory controller 1116 and the platform controller hub 1130 may be integrated into a separate external graphics processor, such as the external graphics processor 1112. In at least one embodiment, the platform controller hub 1130 and / or the memory controller 1116 may be external to one or more processors 1102. For example, in at least one embodiment, the system 1100 can include an external memory controller 1116 and a platform controller hub 1130, which may be configured as a memory controller hub and a peripheral device controller hub in a system chipset that communicates with the processor 1102.

[0086] Using inference and / or training logic 715, inference and / or training operations associated with one or more embodiments are performed. Details regarding the inference and / or training logic 715 are provided below in conjunction with FIGS. 7A and / or 7B. In at least one embodiment, some or all of the inference and / or training logic 715 may be incorporated into the graphics processor 1500. For example, in at least one embodiment, the training and / or inference techniques described herein may use one or more of the ALUs embodied in the graphics processor. Further, in at least one embodiment, the inference and / or training operations described herein may be performed using logic other than the logic shown in FIGS. 7A or 7B. In at least one embodiment, the weight parameters may be stored in on-chip or off-chip memory and / or registers (shown or not shown) that configure the ALU of the graphics processor to execute one or more of the machine learning algorithms, neural network architectures, use cases, or training techniques described herein.

[0087] Such components can be used to determine one or more sentiment values from audio data.

[0088] FIG. 12 is a block diagram of a processor 1200 having one or more processor cores 1202A-1202N, an integrated memory controller 1214, and an integrated graphics processor 1208, according to at least one embodiment. In at least one embodiment, the processor 1200 can include fewer additional cores, including the additional core 1202N represented by the dashed rectangle. In at least one embodiment, each of the processor cores 1202A-1202N includes one or more internal cache units 1204A-1204N. In at least one embodiment, each processor core can also access one or more shared cache units 1206.

[0089] In at least one embodiment, internal cache units 1204A - 1204N, and shared cache unit 1206, represent a cache memory hierarchy within processor 1200. In at least one embodiment, cache memory units 1204A - 1204N may include at least one level of cache for instructions and data within each processor core, and one or more levels of shared intermediate - level cache such as level 2 (L2), level 3 (L3), level 4 (L4), or other levels of cache, where the highest level of cache before external memory is classified as the LLC. In at least one embodiment, cache coherence logic maintains coherence among the various cache units 1206 and 1204A - 1204N.

[0090] In at least one embodiment, processor 1200 may also include a set of one or more bus controller units 1216 and system agent core 1210. In at least one embodiment, one or more bus controller units 1216 manage a set of peripheral buses such as one or more PCI or PCI Express buses. In at least one embodiment, system agent core 1210 provides management functions for various processor components. In at least one embodiment, system agent core 1210 includes one or more integrated memory controllers 1214 for managing access to various external memory devices (not shown).

[0091] In at least one embodiment, one or more of the processor cores 1202A-1202N include support for simultaneous multithreading. In at least one embodiment, the system agent core 1210 includes components for coordinating and operating cores 1202A-1202N during multithreaded processing. In at least one embodiment, the system agent core 1210 may further include a power control unit (PCU) that includes logic and components for adjusting the power state of one or more of the processor cores 1202A-1202N and the graphics processor 1208.

[0092] In at least one embodiment, the processor 1200 further includes a graphics processor 1208 for performing graphics processing operations. In at least one embodiment, the graphics processor 1208 is coupled to a shared cache unit 1206 and a system agent core 1210 that includes one or more integrated memory controllers 1214. In at least one embodiment, the system agent core 1210 also includes a display controller 1211 for causing the output of the graphics processor to be provided to one or more attached displays. In at least one embodiment, the display controller 1211 may also be a separate module coupled to the graphics processor 1208 via at least one interconnect, or may be integrated within the graphics processor 1208.

[0093] In at least one embodiment, a ring-based interconnect unit 1212 is used to couple the internal components of the processor 1200. In at least one embodiment, alternative interconnect units such as point-to-point interconnects, switch interconnects, or other techniques may be used. In at least one embodiment, the graphics processor 1208 is coupled to the ring interconnect 1212 via an I / O link 1213.

[0094] In at least one embodiment, the I / O link 1213 represents at least one of a variety of I / O interconnects including an on-package I / O interconnect that facilitates communication between various processor components and a high-performance embedded memory module 1218 such as an eDRAM module. In at least one embodiment, each of the processor cores 1202A-1202N and the graphics processor 1208 uses the embedded memory module 1218 as a shared last-level cache.

[0095] In at least one embodiment, the processor cores 1202A-1202N are homogeneous cores that execute a common instruction set architecture. In at least one embodiment, the processor cores 1202A-1202N are heterogeneous from the perspective of an instruction set architecture (ISA), where one or more of the processor cores 1202A-1202N execute a common instruction set, but one or more other cores of the processor cores 1202A-1202N execute a subset of the common instruction set, or a different instruction set. In at least one embodiment, the processor cores 1202A-1202N are heterogeneous from the perspective of a microarchitecture, where one or more cores with a relatively high power consumption are coupled with one or more cores with a lower power consumption. In at least one embodiment, the processor 1200 can be implemented on one or more chips or as a SoC integrated circuit.

[0096] Inferences and / or training operations associated with one or more embodiments are performed using inference and / or training logic 715. Details regarding the inference and / or training logic 715 are provided below in conjunction with FIGS. 7a and / or 7b. In at least one embodiment, some or all of the inference and / or training logic 715 may be incorporated within the processor 1200. For example, in at least one embodiment, the training and / or inference techniques described herein may utilize one or more of the ALUs embodied in the graphics processor 1512, the graphics cores 1202A - 1202N, or other components of FIG. 12. Further, in at least one embodiment, the inference and / or training operations described herein may be performed using logic other than that shown in FIGS. 7A or 7B. In at least one embodiment, the weight parameters may be stored in on-chip or off-chip memory and / or registers (shown or not shown) that configure the ALU of the graphics processor 1200 to execute one or more of the machine learning algorithms, neural network architectures, use cases, or training techniques described herein.

[0097] Such components can be used to determine one or more sentiment values from audio data.

[0098] Virtual computing system FIG. 13 is an example data flow diagram of a process 1300 for generating and introducing an image processing and inference pipeline, according to at least one embodiment. In at least one embodiment, the process 1300 may be introduced for use with imaging devices, processing devices, and / or other types of devices at one or more facilities 1302. The process 1300 may be executed within a training system 1304 and / or within an introduction system 1306. In at least one embodiment, the training system 1304 may be used to train, introduce, and implement a machine learning model (e.g., a neural network, an object detection algorithm, a computer vision algorithm, etc.) for use in the introduction system 1306. In at least one embodiment, the introduction system 1306 may be configured to offload processing and computing resources across distributed computing environments to reduce infrastructure requirements at the facility 1302. In at least one embodiment, one or more applications within the pipeline may use or call services (e.g., inference, virtualization, computing, AI, etc.) of the introduction system 1306 during execution of the application.

[0099] In at least one embodiment, some of the applications used in the advanced processing and inference pipeline may use a machine learning model or other AI to perform one or more processing steps. In at least one embodiment, the machine learning model may be trained at the facility 1302 using data 1308 (such as imaging data) generated at the facility 1302 and stored in one or more image archive and communication system (PACS) servers at the facility 1302, may be trained using imaging or sequencing data 1308 from one or more other facilities, or may be a combination thereof. In at least one embodiment, the training system 1304 may be used to provide applications, services, and / or other resources for generating a practical and deployable machine learning model for the introduction system 1306.

[0100] In at least one embodiment, the model registry 1324 may be backed up by an object storage that can support version management and object metadata. In at least one embodiment, the object storage may be accessible, for example, from within a cloud platform, via a compatibility application programming interface (API) of cloud storage (e.g., cloud 1426 of FIG. 14). In at least one embodiment, the machine learning models within the model registry 1324 may be uploaded, listed, modified, or deleted by a developer or partner of the system interacting with the API. In at least one embodiment, the API may provide access to a way for a user with appropriate credentials to associate a model with an application, thereby enabling the model to be executed as part of running a containerized instance of the application.

[0101] In at least one embodiment, the training pipeline 1404 (FIG. 14) may include a situation where the facility 1302 is training its own machine learning model or has an existing machine learning model that needs to be optimized or updated. In at least one embodiment, imaging data 1308 generated by an imaging device, a sequencing device, and / or other types of devices may be received. In at least one embodiment, when the imaging data 1308 is received, AI-assisted annotation 1310 may be used to assist in generating annotations corresponding to the imaging data 1308 that will be used as ground truth data for the machine learning model. In at least one embodiment, the AI-assisted annotation 1310 may include one or more machine learning models (e.g., a convolutional neural network (CNN)), which may be trained to generate annotations corresponding to a particular type of imaging data 1308 (e.g., from a particular device). In at least one embodiment, the AI-assisted annotation 1310 may then be used directly to generate ground truth data or may be adjusted or fine-tuned using an annotation tool. In at least one embodiment, the AI-assisted annotation 1310, the labeled clinical data 1312, or a combination thereof may be used as ground truth data for training the machine learning model. In at least one embodiment, the trained machine learning model may be referred to as the output model 1316 and may be used by the introduction system 1306 described herein.

[0102] In at least one embodiment, training pipeline 1404 (FIG. 14) may include a situation where facility 1302 requires a machine learning model to execute one or more processing tasks for one or more applications within onboarding system 1306, but facility 1302 may not currently have such a machine learning model (or may not have a model optimized, efficient, or effective for such purposes). In at least one embodiment, an existing machine learning model may be selected from model registry 1324. In at least one embodiment, model registry 1324 may include machine learning models trained to perform various different inference tasks on imaging data. In at least one embodiment, the machine learning models of model registry 1324 may be trained on imaging data from a facility different from facility 1302 (e.g., a facility in a remote location). In at least one embodiment, the machine learning model may be trained on imaging data from one location, two locations, or any number of locations. In at least one embodiment, when trained on imaging data from a particular location, the training may be performed at that location, or at least in a manner that protects the confidentiality of the imaging data, or in a manner that restricts the transfer of the imaging data outside the facility. In at least one embodiment, when a model is trained or partially trained at one location, the machine learning model may be added to model registry 1324. In at least one embodiment, the machine learning model may then be retrained or updated at any number of other facilities, and the retrained or updated model may be made available in model registry 1324. In at least one embodiment, the machine learning model may then be selected from model registry 1324, may be referred to as output model 1316, and may be used in onboarding system 1306 to execute one or more processing tasks for one or more applications of the onboarding system.

[0103] In at least one example, training pipeline 1404 (FIG. 14) may include a situation where facility 1302 needs a machine learning model to execute one or more processing tasks for one or more applications within onboarding system 1306, but facility 1302 may not currently have such a machine learning model (or may not have a model optimized, efficient, or effective for such purposes). In at least one example, the machine learning model selected from model registry 1324 may not be fine-tuned or optimized for imaging data 1308 generated at facility 1302 because there may be differences in the population, the robustness of the training data used to train the machine learning model, the diversity of anomalies in the training data, and / or other issues associated with the training data. In at least one example, AI-assisted annotation 1310 may be used to assist in generating annotations corresponding to imaging data 1308 that will be used as ground truth data for retraining or updating the machine learning model. In at least one example, labeled data 1312 may be used as ground truth data for training the machine learning model. In at least one example, retraining or updating the machine learning model may be referred to as model training 1314. In at least one example, model training 1314, such as AI-assisted annotation 1310, labeled clinic data 1312, or a combination thereof, may be used as ground truth data for retraining or updating the machine learning model. In at least one example, the trained machine learning model may be referred to as output model 1316 and may be used by onboarding system 1306 described herein.

[0104] In at least one embodiment, the introduction system 1306 may include software 1318, services 1320, hardware 1322, and / or other components, features, and functions. In at least one embodiment, the introduction system 1306 may include a software “stack,” whereby the software 1318 may be built on top of the services 1320, may use the services 1320 to perform some or all of the processing tasks, and the services 1320 and software 1318 may be built on top of the hardware 1322 and may use the hardware 1322 to perform the processing, storage, and / or other computing tasks of the introduction system 1306. In at least one embodiment, the software 1318 may include any number of different containers, where each container may perform an instantiation of an application. In at least one embodiment, each application may perform one or more processing tasks of an advanced processing and inference pipeline (e.g., inference, object detection, feature detection, segmentation, image enhancement, calibration, etc.). In at least one embodiment, the advanced processing and inference pipeline may be defined based on a selection of different containers desired or required to process the imaging data 1308, in addition to the containers that receive and configure the imaging data used by each container and / or by the facility 1302 after processing through the pipeline (e.g., to re-convert the output to a usable type of data). In at least one embodiment, a combination of containers within the software 1318 (e.g., that make up the pipeline) may be referred to as a virtual appliance (described in more detail herein), and the virtual appliance may use the services 1320 and hardware 1322 to perform some or all of the processing tasks of the applications instantiated in the containers.

[0105] In at least one embodiment, the data processing pipeline may receive input data (e.g., imaging data 1308) in a particular format in response to an inference request (e.g., a request from a user of the introduction system 1306). In at least one embodiment, the input data may represent one or more images, videos, and / or other data representations generated by one or more imaging devices. In at least one embodiment, the data may undergo preprocessing as part of the data processing pipeline and be prepared so that it can be processed by one or more applications. In at least one embodiment, postprocessing may be performed on the output of one or more inference tasks or other processing tasks of the pipeline to prepare the output data for the next application and / or to prepare the output data for transmission and / or use by the user (e.g., in response to the inference request). In at least one embodiment, the inference task may be performed by one or more machine learning models, such as a trained or introduced neural network, which may include the output model 1316 of the training system 1304.

[0106] In at least one embodiment, the tasks of the data processing pipeline may be encapsulated in containers, each of which represents an individual fully functional instantiation of an application and a virtualized computing environment that can reference a machine learning model. In at least one embodiment, the container or application may be issued to a private (e.g., access-restricted) area of a container registry (described in more detail herein), and the trained or introduced model may be stored in the model registry 1324 and associated with one or more applications. In at least one embodiment, an image of the application (e.g., an image of the container) may be available in the container registry and, when selected by the user from the container registry for introduction into the pipeline, may be used to generate a container for instantiating the application so that it can be used on the user's system.

[0107] In at least one embodiment, a developer (e.g., a software developer, a clinician, a physician, etc.) may develop, publish, and store an application (e.g., as a container) to perform image processing and / or inference on the provided data. In at least one embodiment, the development, publication, and / or storage may be performed using a software development kit (SDK) associated with the system (e.g., to ensure that the developed application and / or container complies with or is compatible with the system). In at least one embodiment, the developed application may be tested locally (e.g., at a first facility, for data from the first facility) using an SDK that can support at least a portion of service 1320 as a system (e.g., system 1400 of FIG. 14). In at least one embodiment, a DICOM object can contain anywhere from one to hundreds of images or other types of data, and due to the variations in the data, the developer may be responsible for managing the extraction and preparation of the input data (e.g., setting up the configuration for the application, building the pre-processing into the application, etc.). In at least one embodiment, once the application is verified (e.g., for accuracy) by system 1400, it is made available in a container registry for selection and / or implementation by a user, and one or more processing tasks may be performed on the data at the user's facility (e.g., a second facility).

[0108] In at least one example, the developer may then share the application or container through a network so that it can be accessed and used by a user of the system (e.g., system 1400 of FIG. 14). In at least one example, the completed and verified application or container may be stored in a container registry, and the associated machine learning model may be stored in a model registry 1324. In at least one example, a requesting entity that issues an inference or image processing request may browse the container registry and / or the model registry 1324 to search for applications, containers, datasets, machine learning models, etc., select a desired combination of elements for inclusion in a data processing pipeline, and send an imaging processing request. In at least one example, the request may include the input data (and in some examples, the associated patient data) necessary to execute the request and / or may include the selection of an application and / or a machine learning model that will be executed when processing the request. In at least one example, the request may then be passed to one or more components of an onboarding system 1306 (e.g., the cloud) to execute the processing of the data processing pipeline. In at least one example, the processing by the onboarding system 1306 may include referring to elements (e.g., applications, containers, models, etc.) selected from the container registry and / or the model registry 1324. In at least one example, when the pipeline generates a result, the result may be returned to and viewed by the user (e.g., viewed in a viewing application suite running locally, on an in-premises workstation or terminal).

[0109] In at least one embodiment, Service 1320 may be utilized to assist in processing or executing an application or container in a pipeline. In at least one embodiment, Service 1320 may include a computing service, an artificial intelligence (AI) service, a visualization service, and / or other types of services. In at least one embodiment, Service 1320 may provide common functionality to one or more applications of Software 1318, whereby the functionality may be abstracted with respect to services that can be called or utilized by the applications. In at least one embodiment, the functionality provided by Service 1320 may be executed dynamically and more efficiently, and at the same time, may scale well by enabling an application to process data in parallel (e.g., using parallel computing platform 1430 (FIG. 14)). Instead of requiring each application sharing the same functionality provided by Service 1320 to have its own instance of Service 1320, Service 1320 may be shared among various applications. In at least one embodiment, the service may include an inference server or engine that may be used, as a non-limiting example, to perform detection or segmentation tasks. In at least one embodiment, a model training service capable of providing a function for training and / or retraining a machine learning model may be included. In at least one embodiment, a data augmentation service capable of providing extraction, resizing, scaling, and / or other augmentation of GPU-accelerated data (e.g., DICOM, RIS, CIS, REST-compliant, RPC, raw, etc.) may be further included. In at least one embodiment, a visualization service capable of adding image rendering effects such as ray tracing, rasterization, noise removal, sharpening, etc. may be used to add a sense of reality to two-dimensional (2D) and / or three-dimensional (3D) models. In at least one embodiment, a virtual device service capable of realizing beamforming, segmentation, inference, imaging, and / or support for other applications within a pipeline of virtual devices may be included.

[0110] In at least one embodiment, when service 1320 includes an AI service (e.g., an inference service), one or more machine learning models may be executed by calling (as an API call) the inference service (e.g., an inference server) to execute the machine learning model or its processing as part of application execution. In at least one embodiment, when another application includes one or more machine learning models for a segmentation task, the application may call the inference service to execute a machine learning model for performing one or more of the processing operations associated with the segmentation task. In at least one embodiment, software 1318 implementing an advanced processing and inference pipeline including a segmentation application and an anomaly detection application may be rationalized because each application may call the same inference service to perform one or more inference tasks.

[0111] In at least one embodiment, the hardware 1322 may include a GPU, a CPU, a graphics card, an AI / deep learning system (e.g., an AI supercomputer such as NVIDIA's DGX), a cloud platform, or a combination thereof. In at least one embodiment, different types of hardware 1322 may be used to provide efficient and dedicated support for the software 1318 and services 1320 of the introduction system 1306. In at least one embodiment, the use of GPU processing for local (e.g., at the facility 1302) processing may be implemented within an AI / deep learning system, a cloud system, and / or other processing components of the introduction system 1306 to improve the efficiency, accuracy, and effectiveness of image processing and image generation. In at least one embodiment, the software 1318 and / or services 1320 may be optimized for GPU processing related to deep learning, machine learning, and / or high-performance computing, by way of non-limiting example. In at least one embodiment, at least a portion of the computing environment of the introduction system 1306 and / or the training system 1304 may be executed using GPU-optimized software (e.g., a combination of hardware and software of NVIDIA's DGX system) in one or more supercomputers or high-performance computing systems of a data center. In at least one embodiment, the hardware 1322 may include any number of GPUs, which may be called to perform parallel processing of data as described herein. In at least one embodiment, the cloud platform may further include GPU processing for GPU-optimized execution of deep learning tasks, machine learning tasks, or other computing tasks. In at least one embodiment, the cloud platform (e.g., NVIDIA's NGC) may be executed using an AI / deep learning supercomputer (e.g., provided by NVIDIA's DGX system) and / or GPU-optimized software as a platform for hardware abstraction and scaling.In at least one embodiment, the cloud platform may integrate a plurality of GPU application container clustering systems or orchestration systems (e.g., KUBERNETES) to enable seamless scaling and load balancing.

[0112] FIG. 14 is a system diagram showing an example system 1400 for generating and introducing an imaging introduction pipeline according to at least one embodiment. In at least one embodiment, system 1400 may be used to implement process 1300 of FIG. 13 and / or other processes including advanced processing and inference pipelines. In at least one embodiment, system 1400 may include a training system 1304 and an introduction system 1306. In at least one embodiment, training system 1304 and introduction system 1306 may be implemented using software 1318, services 1320, and / or hardware 1322 as described herein.

[0113] In at least one embodiment, system 1400 (e.g., training system 1304 and / or introduction system 1306) may be implemented in a cloud computing environment (e.g., cloud 1426). In at least one embodiment, system 1400 may be implemented locally with respect to a healthcare service facility or as a combination of cloud and local computing resources. In at least one embodiment, access to the API of cloud 1426 may be limited to authorized users via established security measures or protocols. In at least one embodiment, the security protocol may include a web token, which may be signed by an authentication (e.g., AuthN, AuthZ, Gluecon, etc.) service and may have appropriate permissions. In at least one embodiment, the API of the virtual device (described herein) or other instantiations of system 1400 may be limited to a set of public IPs that have been inspected or permitted for the interaction.

[0114] In at least one embodiment, the various components of system 1400 may communicate with each other using any of a variety of different types of networks, including but not limited to local area networks (LANs) and / or wide area networks (WANs) via wired and / or wireless communication protocols. In at least one embodiment, communication between the facility and the components of system 1400 (e.g., to send an inference request, to receive the result of an inference request, etc.) may be communicated via one or more data buses, wireless data protocols (Wi-Fi), wired data protocols (e.g., Ethernet (registered trademark)), etc.

[0115] In at least one example, the training system 1304 may execute a training pipeline 1404 similar to that described herein with respect to FIG. 13. In at least one example, when one or more machine learning models are to be used in the introduction pipeline 1410 by the introduction system 1306, the training pipeline 1404 may be used to train or retrain one or more (e.g., pre-trained) models and / or implement one or more of the pre-trained models 1406 (e.g., without the need for retraining or updating). In at least one example, as a result of the training pipeline 1404, an output model 1316 may be generated. In at least one example, the training pipeline 1404 may include any number of processing steps, including but not limited to the conversion or adaptation of imaging data (or other input data). In at least one example, different training pipelines 1404 may be used for different machine learning models used by the introduction system 1306. In at least one example, a training pipeline 1404 similar to the first example described with respect to FIG. 13 may be used for the first machine learning model, a training pipeline 1404 similar to the second example described with respect to FIG. 13 may be used for the second machine learning model, and a training pipeline 1404 similar to the third example described with respect to FIG. 13 may be used for the third machine learning model. In at least one example, any combination of tasks within the training system 1304 may be used depending on what is required for each respective machine learning model. In at least one example, one or more of the machine learning models may already be trained and ready for introduction, such that the machine learning models may not undergo any processing by the training system 1304 and may be implemented by the introduction system 1306.

[0116] In at least one embodiment, output model 1316 and / or pre-trained model 1406 may include any type of machine learning model, depending on the implementation or embodiment. In at least one embodiment, by way of non-limiting example, the machine learning model used by system 1400 may include linear regression, logistic regression, decision trees, support vector machines (SVMs), naive Bayes, k-nearest neighbor (Knn), k-means clustering, random forests, dimensionality reduction algorithms, gradient boosting algorithms, neural networks (e.g., autoencoders, convolutional, recurrent, perceptron, long / short term memory (LSTM), Hopfield, Boltzmann, deep belief, deconvolutional, adversarial generation, liquid state machines, etc.), and / or other types of machine learning models.

[0117] In at least one embodiment, the training pipeline 1404 may include AI-assisted annotation, described in more detail herein with respect to at least FIG. 15B. In at least one embodiment, the labeled data 1312 (e.g., conventional annotation) may be generated by any number of techniques. In at least one embodiment, the labels or other annotations may be generated within a drawing program (e.g., an annotation program), a computer-aided design (CAD) program, a labeling program, an annotation or other type of program suitable for generating ground truth labels, and / or in some instances, may be handwritten. In at least one embodiment, the ground truth data may be generated synthetically (e.g., generated from a computer model or rendering), generated realistically (e.g., designed and generated from real-world data), machine-automated (e.g., using feature analysis and learning to extract features from data and then generate labels), human-annotated (e.g., a labeler, or annotation expert may define the location of the labels), and / or combinations thereof. In at least one embodiment, for each instance of the imaging data 1308 (or other type of data used by a machine learning model), there may be corresponding ground truth data generated by the training system 1304. In at least one embodiment, in addition to or instead of the AI-assisted annotation included in the training pipeline 1404, the AI-assisted annotation may be performed as part of the introduction pipeline 1410. In at least one embodiment, the system 1400 may include a multi-layer platform, which may include a software layer (e.g., software 1318) of a diagnostic application (or other type of application) capable of performing one or more medical imaging and diagnostic functions. In at least one embodiment, the system 1400 may be communicatively coupled (e.g., via an encrypted link) to a PACS server network of one or more facilities.In at least one embodiment, system 1400 is configured to access and reference data from a PACS server to perform operations such as training of a machine learning model, introduction of a machine learning model, image processing, inference, and / or other operations.

[0118] In at least one embodiment, the software layer may be implemented as a secure, encrypted, and / or authenticated API through which an application or container may be invoked (e.g., called) from an external environment (e.g., facility 1302). In at least one embodiment, the application may then call or execute one or more services 1320 to perform computing, AI, or visualization tasks associated with each application, and software 1318 and / or services 1320 may utilize hardware 1322 to perform processing tasks in an effective and efficient manner.

[0119] In at least one embodiment, the introduction system 1306 may execute an introduction pipeline 1410. In at least one embodiment, the introduction pipeline 1410 may include any number of applications, which may be applied continuously, discontinuously, or otherwise to imaging data (and / or other types of data) generated by imaging devices, sequencing devices, genomics devices, etc., including the AI-assisted annotation described above. In at least one embodiment, the introduction pipeline 1410 for an individual device may be referred to as a virtual device for the device (e.g., a virtual ultrasound device, a virtual CT scan device, a virtual sequencing device, etc.). In at least one embodiment, depending on the information required for the data generated by the device, there may be more than one introduction pipeline 1410 for one device. In at least one embodiment, if anomaly detection is required for an MRI machine, a first introduction pipeline 1410 may exist, and if image enhancement is required for the output of the MRI machine, a second introduction pipeline 1410 may exist.

[0120] In at least one embodiment, the image generation application may include processing tasks that include the use of a machine learning model. In at least one embodiment, a user may desire to use their own machine learning model or select a machine learning model from the model registry 1324. In at least one embodiment, a user may implement their own machine learning model or select a machine learning model to include in the application to perform a processing task. In at least one embodiment, the application may be selectable and customizable, and by defining the structure of the application, the introduction and implementation of an application for a particular user is presented as a more seamless user experience. In at least one embodiment, by utilizing other features of the system 1400, such as the services 1320 and the hardware 1322, etc., the onboarding pipeline 1410 can become even more user-friendly, achieve easier integration, and produce more accurate, efficient, and timely results.

[0121] In at least one embodiment, the onboarding system 1306 may include a user interface 1414 (e.g., a graphical user interface, a web interface, etc.), which may be used to select an application to include in the onboarding pipeline 1410, configure the application, modify or change the application or its parameters or structure, use and interact with the onboarding pipeline 1410 during setup and / or onboarding, and / or interact with the onboarding system 1306 in other ways. In at least one embodiment, although not shown with respect to the training system 1304, the user interface 1414 (or a different user interface) may be used to select a model to use in the onboarding system 1306, select a model to train or retrain in the training system 1304, and / or interact with the training system 1304 in other ways.

[0122] In at least one embodiment, in addition to the application orchestration system 1428, a pipeline manager 1412 may be used to manage the interaction between the applications or containers of the onboarding pipeline 1410 and the services 1320 and / or the hardware 1322. In at least one embodiment, the pipeline manager 1412 may be configured to facilitate interaction from application to application, from an application to the service 1320, and / or from an application or service to the hardware 1322. In at least one embodiment, although shown as being included in the software 1318, this is not intended to be limiting, and in some cases (such as, for example, that shown in FIG. 12cc), the pipeline manager 1412 may be included in the service 1320. In at least one embodiment, the application orchestration system 1428 (such as, for example, Kubernetes, DOCKER, etc.) may include a container orchestration system that can group applications into containers as logical units for coordination, management, scaling, and onboarding. In at least one embodiment, rather than associating applications (such as, for example, reconfigured applications, segmented applications, etc.) from the onboarding pipeline 1410 with individual containers, each application can execute within a self - contained environment (such as, for example, at the kernel level) to improve speed and efficiency.

[0123] In at least one embodiment, each application and / or container (or its image) may be developed, modified, and introduced individually (e.g., a first user or developer may develop, modify, and introduce a first application, and a second user or developer may develop, modify, and introduce a second application separately from the first user or developer), thereby enabling concentration and attention on the tasks of one application and / or container without being interrupted by the tasks of another application or container. In at least one embodiment, communication and cooperation between different containers or applications may be assisted by a pipeline manager 1412 and an application orchestration system 1428. In at least one embodiment, as long as the predicted inputs and / or outputs of each container or application are known to the system (e.g., based on the structure of the application or container), the application orchestration system 1428 and / or the pipeline manager 1412 can facilitate communication between each of the applications or containers and sharing of resources between them. In at least one embodiment, since one or more of the applications or containers in the introduction pipeline 1410 can share the same services and resources, the application orchestration system 1428 may orchestrate services or resources, perform load balancing, and determine sharing between different applications or containers. In at least one embodiment, a scheduler may be used to track the resource requirements of applications or containers, the current or planned usage of these resources, and the availability of resources. In at least one embodiment, the scheduler may thus allocate resources to different applications and distribute resources between applications considering the system's requirements and availability.In some examples, the scheduler (and / or other components of the application orchestration system 1428) may determine resource availability and allocation based on constraints imposed on the system (e.g., user constraints), such as quality of service (QoS), the urgency of data output required (e.g., to determine whether to perform real-time processing or deferred processing).

[0124] In at least one embodiment, the services 1320 utilized and shared by the applications or containers of the introduction system 1306 may include computing services 1416, AI services 1418, visualization services 1420, and / or other types of services. In at least one embodiment, an application may call (e.g., execute) one or more of the services 1320 to perform processing operations for the application. In at least one embodiment, the computing service 1416 may be utilized by an application to perform supercomputing or other high-performance computing (HPC) tasks. In at least one embodiment, parallel processing may be performed using the computing service 1416 (e.g., using the parallel computing platform 1430) to substantially simultaneously process data through one or more of the applications and / or to substantially simultaneously process one or more tasks of one application. In at least one embodiment, the parallel computing platform 1430 (e.g., NVIDIA's CUDA) may enable general-purpose computing on graphics processing units (GPGPUs) (e.g., GPU 1422). In at least one embodiment, the software layer of the parallel computing platform 1430 may provide a virtual instruction set and access to the parallel computing elements of the GPU to execute computing kernels. In at least one embodiment, the parallel computing platform 1430 may include memory, and in some embodiments, the memory may be shared among multiple containers and / or between different processing tasks within one container. In at least one embodiment, inter-process communication (IPC) calls may be generated for multiple containers and / or multiple processes within a container to use the same data from the shared segment of the memory of the parallel computing platform 1430 (e.g., when multiple different stages of an application or multiple applications process the same information).In at least one embodiment, instead of creating a copy of the data and moving the data to a different location in memory (e.g., read / write operations), the same data in the same location in memory may be used for any number of processing tasks (e.g., at the same timing, different timings, etc.). In at least one embodiment, when data is used and new data is generated as a result of processing, this information about the new location of the data may be stored and shared among various applications. In at least one embodiment, the location of the data and the location of the updated or modified data may be part of the definition of how the payload is understood within the container.

[0125] In at least one embodiment, the AI service 1418 may be utilized to execute an inference service for executing a machine learning model associated with an application (e.g., tasked with performing one or more processing tasks of the application). In at least one embodiment, the AI service 1418 may utilize the AI system 1424 to execute a machine learning model (e.g., a neural network such as a CNN) for segmentation, reconstruction, object detection, feature detection, classification, and / or other inference tasks. In at least one embodiment, the application of the ingestion pipeline 1410 may perform inferences on imaging data using one or more of the output model 1316 from the training system 1304 and / or other models of the application. In at least one embodiment, two or more instances of inferences using the application orchestration system 1428 (e.g., a scheduler) may be available. In at least one embodiment, the first category may include a high-priority / low-latency path that can achieve a higher service-level agreement, such as for performing inferences for emergency requests in an emergency or for a radiologist during a diagnosis. In at least one embodiment, the second category may include a standard-priority path that can be used for non-emergency requests or when the analysis may be performed later. In at least one embodiment, the application orchestration system 1428 may allocate resources (e.g., the service 1320 and / or the hardware 1322) based on the priority paths for different inference tasks of the AI service 1418.

[0126] In at least one embodiment, the shared storage may be attached to the AI service 1418 within the system 1400. In at least one embodiment, the shared storage may operate as a cache (or other type of storage device) and may be used to process inference requests from the application. In at least one embodiment, when an inference request is sent, the request may be received by a set of API instances of the ingress system 1306, and one or more instances may be selected (e.g., for best fit, load balancing, etc.) for the request to be processed. In at least one embodiment, to process the request, the request may be placed in a database, and the machine learning model may be identified from the model registry 1324 if it is not yet in the cache, and the verification step may ensure that the appropriate machine learning model is loaded into the cache (e.g., shared storage) and / or a copy of the model is saved in the cache. In at least one embodiment, if the application is not yet running or there are not sufficient instances of the application, a scheduler (e.g., the pipeline manager 1412) may be used to start the application referenced in the request. In at least one embodiment, if the inference server for running the model is not yet started, the inference server may be started. Any number of inference servers may be started per model. In at least one embodiment, in a pull model where the inference servers are clustered, the model may be cached whenever load balancing is advantageous. In at least one embodiment, the inference server may be statically loaded onto the corresponding distributed server.

[0127] In at least one embodiment, the inference may be performed using an inference server that runs within a container. In at least one embodiment, an instance of the inference server may be associated with a model (optionally with multiple versions of the model). In at least one embodiment, when a request to perform an inference on a model is received, if no instance of the inference server exists, a new instance may be loaded. In at least one embodiment, when starting the inference server, the model may be passed to the inference server, such that as long as the inference server is running as a different instance, the same container may be used to serve different models.

[0128] In at least one embodiment, during the execution of an application, an inference request may be received for a given application, a container (e.g., hosting an instance of an inference server) may be loaded (if not already loaded), and a start procedure may be called. In at least one embodiment, the preprocessing logic of the container may load, decode, and / or perform any additional preprocessing on the input data (e.g., using a CPU and / or GPU). In at least one embodiment, once the data is prepared for inference, the container may perform an inference on the data as needed. In at least one embodiment, this may include a single inference call for one image (e.g., an X-ray of a hand), or may request inferences for hundreds of images (e.g., a chest CT). In at least one embodiment, the application may summarize the results before completion, which may include, but is not limited to, generating a single confidence score, pixel-level segmentation, voxel-level segmentation, visualization, or text for summarizing the findings. In at least one embodiment, different models or applications may be assigned different priorities. For example, there may be models with real-time (TAT < 1 minute) priority and models with low priority (e.g., TAT < 10 minutes). In at least one embodiment, the model execution time may be measured from the requesting facility or entity and may include cross-partner network latency in addition to the execution on the inference service.

[0129] In at least one embodiment, the transfer of requests between the service 1320 and the inference application may be hidden behind the software development kit (SDK), and robust transfer may be provided through a queue. In at least one embodiment, a combination of individual application / tenant IDs is requested, the request is queued via the API, and the SDK pulls the request from the queue and provides the request to the application. In at least one embodiment, the name of the queue may be provided in the environment where the SDK picks up the request. In at least one embodiment, asynchronous communication via the queue may be useful because when the communication becomes available, any instance of the application can pick up the work by that communication. The result may be returned via the queue to prevent data loss. In at least one embodiment, the highest-priority work can proceed to the queue with most instances of the application connected to the queue, while the lowest-priority work can proceed to the queue that processes tasks in the order received with one instance connected to the queue, so the queue can also segment the work. In at least one embodiment, the application may be executed on a GPU-accelerated instance generated in the cloud 1426, and the inference service may perform inference on the GPU.

[0130] In at least one embodiment, the visualization service 1420 may be utilized to generate visualizations for viewing the output of the application and / or the onboarding pipeline 1410. In at least one embodiment, the GPU 1422 may be utilized by the visualization service 1420 to generate the visualizations. In at least one embodiment, rendering effects such as ray tracing may be implemented by the visualization service 1420 to generate higher quality visualizations. In at least one embodiment, the visualizations may include, but are not limited to, rendering of 2D images, rendering of 3D volumes, reconstruction of 3D volumes, 2D tomography slices, virtual reality displays, augmented reality displays, etc. In at least one embodiment, a virtual interactive display or interactive environment (e.g., a virtual environment) for a user of the system (e.g., a doctor, a nurse, a radiologist, etc.) to interact with may be generated using a virtualized environment. In at least one embodiment, the visualization service 1420 may include an internal visualizer, cinematics, and / or other rendering or image processing capabilities or functions (e.g., ray tracing, rasterization, internal optics, etc.).

[0131] In at least one embodiment, the hardware 1322 may include a GPU 1422, an AI system 1424, a cloud 1426, and / or any other hardware used to execute the training system 1304 and / or the introduction system 1306. In at least one embodiment, the GPU 1422 (e.g., NVIDIA's TESLA and / or QUADRO GPUs) may include any number of GPUs, which may be used to execute processing tasks for the computing service 1416, the AI service 1418, the visualization service 1420, other services, and / or any features or functions of the software 1318. For example, with respect to the AI service 1418, pre-processing may be performed on the imaging data (or other types of data used by the machine learning model) using the GPU 1422, post-processing may be performed on the output of the machine learning model, and / or inference may be performed (e.g., the machine learning model may be executed). In at least one embodiment, the cloud 1426, the AI system 1424, and / or other components of the system 1400 may use the GPU 1422. In at least one embodiment, the cloud 1426 may include a GPU-optimized platform for deep learning tasks. In at least one embodiment, the AI system 1424 may use a GPU, and at least a portion assigned the role of the cloud 1426, or deep learning or inference, may be executed using one or more AI systems 1424. Thus, although the hardware 1322 is shown as individual components, this is not intended to be limiting, and any component of the hardware 1322 may be combined with and utilized by any other component of the hardware 1322.

[0132] In at least one embodiment, the AI system 1424 may include a dedicated computing system (e.g., a supercomputer or HPC) configured for inference, deep learning, machine learning, and / or other artificial intelligence tasks. In at least one embodiment, the AI system 1424 (e.g., NVIDIA's DGX) may include GPU-optimized software (e.g., a software stack), which may be executed using multiple GPUs 1422 in addition to a CPU, RAM, storage, and / or other components, features, or functions. In at least one embodiment, one or more AI systems 1424 may be implemented in the cloud 1426 (e.g., in a data center) to perform some or all of the AI-based processing tasks of the system 1400.

[0133] In at least one embodiment, cloud 1426 may include a GPU-accelerated infrastructure (e.g., NVIDIA's NGC), which may provide a GPU-optimized platform for executing the processing tasks of system 1400. In at least one embodiment, cloud 1426 may include an AI system 1424 (e.g., as a platform for hardware abstraction and scaling) for executing one or more of the AI-based tasks of system 1400. In at least one embodiment, cloud 1426 may utilize multiple GPUs and be integrated with an application orchestration system 1428 to enable seamless scaling and load balancing between applications and services 1320. In at least one embodiment, cloud 1426 may be tasked with executing at least a portion of the services 1320 of system 1400, including the computing service 1416, AI service 1418, and / or visualization service 1420 described herein. In at least one embodiment, cloud 1426 may perform large and small batch inferences (e.g., execution of NVIDIA's TensorRT), provide an accelerated parallel computing API and platform 1430 (e.g., NVIDIA's CUDA), execute an application orchestration system 1428 (e.g., KUBERNETES), provide a graphics rendering API and platform (e.g., ray tracing for generating high-quality cinematics, 2D graphics, 3D graphics, and / or other rendering techniques), and / or provide other functions for system 1400.

[0134] FIG. 15A shows a data flow diagram of a process 1500 for training, retraining, or updating a machine learning model according to at least one embodiment. In at least one embodiment, process 1500 may be executed using the system 1400 of FIG. 14 as a non-limiting example. In at least one embodiment, process 1500 may utilize the service 1320 and / or the hardware 1322 of the system 1400 described herein. In at least one embodiment, the refined model 1512 generated by process 1500 may be executed by the introduction system 1306 for one or more containerized applications within the introduction pipeline 1410.

[0135] In at least one embodiment, model training 1314 may include retraining or updating an initial model 1504 (e.g., a pre-trained model) using new training data (e.g., a customer dataset 1506 and / or new input data such as new ground truth data associated with the input data). In at least one embodiment, to retrain or update the initial model 1504, the output or loss layer of the initial model 1504 may be reset, may be deleted, and / or may be replaced with an updated or new output or loss layer. In at least one embodiment, the initial model 1504 may have parameters (e.g., weights and / or biases) remaining from a previous pre-training that were previously fine-tuned, such that training or retraining 1314 does not take as long or require as much processing as training the model from scratch. In at least one embodiment, during model training 1314, by having a reset or replaced output or loss layer of the initial model 1504, the parameters may be updated or readjusted for the new dataset based on the calculation of a loss associated with the accuracy of the output or loss layer when generating predictions for the new customer dataset 1506 (e.g., the image data 1308 of FIG.  13).

[0136] In at least one embodiment, the pre-trained model 1406 may be stored in a data store or registry (e.g., the model registry 1324 of FIG. 13). In at least one embodiment, the pre-trained model 1406 may be trained at least in part at one or more facilities different from the facility that executes process 1500. In at least one embodiment, to protect the privacy and rights of patients, subjects, or clients of different facilities, the pre-trained model 1406 may be trained on-premises using customer or patient data generated on-premises. In at least one embodiment, the pre-trained model 1406 may be trained using the cloud 1426 and / or other hardware 1322, but private and confidential patient data cannot be transferred to any component of the cloud 1426 (or other off-premises hardware), cannot be used by those components, or may be inaccessible. In at least one embodiment, when the pre-trained model 1406 is trained using patient data from two or more facilities, the pre-trained model 1406 may be trained individually for each facility and then trained on patient or customer data from another facility. In at least one embodiment, if customer or patient data is released from privacy concerns (e.g., by waiver for experimental use) or if customer or patient data is included in a public dataset, etc., the pre-trained model 1406 may be trained on-premises and / or off-premises using customer or patient data from any number of facilities, such as a data center or other cloud computing infrastructure.

[0137] In at least one embodiment, when selecting an application to use in the import pipeline 1410, the user can also select a machine learning model that will be used with the particular application. In at least one embodiment, the user may not have a model to use, and thus, the user may select a pre-trained model 1406 to use with the application. In at least one embodiment, the pre-trained model 1406 may be optimized to produce accurate results for the customer data set 1506 of the user's facility (e.g., based on patient diversity, demographics, type of medical imaging device used, etc.). In at least one embodiment, before introducing the pre-trained model 1406 into the import pipeline 1410 for use with an application, the pre-trained model 1406 may be updated, retrained, and / or fine-tuned for use in each facility.

[0138] In at least one embodiment, the user may select a pre-trained model 1406 that will be updated, retrained, and / or fine-tuned, and the pre-trained model 1406 may be referred to as an initial model 1504 for training the system 1304 within the process 1500. In at least one embodiment, model training 1314 (including, but not limited to, transfer learning) may be performed on the initial model 1504 using a customer data set 1506 (e.g., imaging data, genomics data, sequencing data, or other types of data generated by the facility's devices) to generate a refined model 1512. In at least one embodiment, ground truth data corresponding to the customer data set 1506 may be generated by the training system 1304. In at least one embodiment, the ground truth data may be at least partially generated by clinicians, scientists, physicians, and practitioners at the facility (e.g., as the labeled clinic data 1312 of FIG. 13).

[0139] In at least one embodiment, AI-assisted annotation 1310 may be used in some examples to generate ground truth data. In at least one embodiment, AI-assisted annotation 1310 (implemented, for example, using an AI-assisted annotation SDK) may utilize a machine learning model (e.g., a neural network) to generate ground truth data that is suggested or predicted for a customer dataset. In at least one embodiment, user 1510 may use an annotation tool within a user interface (graphical user interface (GUI)) on computing device 1508. <0> <0>

[0140] <0> In at least one embodiment, user 1510 may interact with the GUI via computing device 1508 to edit or fine-tune (automated) annotations. In at least one embodiment, a polygon editing function may be used to move polygon vertices to more accurate or fine-tuned locations. <0> <0>

[0141] <0> In at least one embodiment, when customer dataset 1506 obtains associated ground truth data, the ground truth data (from, for example, AI-assisted annotation, manual labeling, etc.) may be used during model training 1314 to generate refined model 1512. In at least one embodiment, customer dataset 1506 may be applied to initial model 1504 any number of times, and the ground truth data may be used to update the parameters of initial model 1504 until an acceptable level of accuracy for refined model 1512 is achieved. In at least one embodiment, once refined model 1512 is generated, refined model 1512 may be introduced into one or more deployment pipelines 1410 at a facility to perform one or more processing tasks on medical imaging data. <0> <0>

[0142] <0> In at least one embodiment, the refinement model 1512 may be uploaded to a pre-trained model 1406 of a model registry 1324 that will be selected by another facility. In at least one embodiment, this process may be completed at any number of facilities, whereby the refinement model 1512 may be further refined any number of times for a new dataset to generate a more universal model.

[0143] FIG. 15B is an exemplary diagram of a client-server architecture 1532 for enhancing an annotation tool using a pre-trained annotation model according to at least one embodiment. In at least one embodiment, an AI-assisted annotation tool 1536 may be instantiated based on the client-server architecture 1532. In at least one embodiment, the annotation tool 1536 of the imaging application may assist, for example, a radiologist in identifying organs and abnormalities. In at least one embodiment, the imaging application may include a software tool that assists a user 1510 in identifying a few extreme points on a specific target organ in a raw image 1534 (such as, by way of non-limiting example, a 3D MRI or CT scan) and receives automatically annotated results for all 2D slices of a specific organ. In at least one embodiment, the results may be stored in a data store as training data 1538 and may be used as (for example, but not limited to) ground truth data for training. In at least one embodiment, when a computing device 1508 sends extreme points for AI-assisted annotation 1310, for example, a deep learning model may receive this data as input and may return an inference result of a segmented organ or abnormality. In at least one embodiment, a pre-instantiated annotation tool, such as the AI-assisted annotation tool 1536B of FIG. 15B, may be extended by making an API call (such as API call 1544) to a server, such as an annotation support server 1540, that can include a set of pre-trained models 1542 stored in an annotation model registry. In at least one embodiment, the annotation model registry may store pre-trained models 1542 (such as machine learning models, such as deep learning models) pre-trained to perform AI-assisted annotation for a specific organ or abnormality. These models may be further updated by using a training pipeline 1404.In at least one embodiment, a pre-installed annotation tool may be improved over time as new labeled clinic data 1312 is added.

[0144] Such components can be used to determine one or more sentiment values from audio data.

[0145] Other variations are within the scope of the present disclosure. Accordingly, while the disclosed techniques are capable of various modifications and alternative configurations, specific exemplary embodiments thereof have been shown in the drawings and described in detail above. However, there is no intention to limit the present disclosure to the specific one or more disclosed forms, and on the contrary, it is intended to cover all modifications, alternative configurations, and equivalents that fall within the spirit and scope of the disclosure as defined by the appended claims.

[0146] In the context of describing the disclosed embodiments (in particular, in the context of the following claims), the use of the terms "a", "an", and "the", as well as similar indicators, should be construed to cover both the singular and the plural, unless otherwise specified in this specification or clearly contradicted by the context, and should not be construed as a definition of the terms. The terms "comprising", "having", "including", and "containing" should be construed as open-ended terms (meaning "including but not limited to") unless otherwise specified. The term "connected" should be construed as being partially or fully enclosed within, attached to, or joined to each other, even if there is something intervening, when it refers to a physical connection without modification. The detailed description of a range of values herein is merely intended to function as a concise way of referring individually to each separate value within the range, unless otherwise specified herein or unless each separate value is incorporated into the specification as if it were individually detailed herein. The use of the term "set" (e.g., "a set of items") or "subset" should be construed as a non-empty set comprising one or more members, unless otherwise specified or contradicted by the context. Further, unless otherwise specified or contradicted by the context, the term "subset" of a corresponding set does not necessarily refer to a strict subset of the corresponding set, and the subset and the corresponding set may be equal.

[0147] Conjunctive terms such as "at least one of A, B, and C" or phrases in the form of "at least one of A, B, and C" are understood in the context generally used to indicate that items, terms, etc. are either A, B, or C, or a non-empty subset of any of the sets of A, B, and C, unless there is a specific description to the contrary or it is not clearly negated by the context. For example, in an illustrative example of a set having three members, the conjunctive phrases "at least one of A, B, and C" and "at least one of A, B, and C" refer to any of the following sets: {A}, {B}, {C}, {A,B}, {A,C}, {B,C}, {A,B,C}. Thus, such conjunctive terms do not generally imply that a particular embodiment requires the presence of at least one of each of A, at least one of B, and at least one of C. Further, unless otherwise stated or not clearly negated by the context, the term "plurality" indicates a plural state (e.g., "a plurality of items" indicates multiple items). A plurality means at least two items, but may be more if explicitly or indicated by the context. Further, unless otherwise stated or not clear from the context to the contrary, the phrase "based on" means "at least partially based on" and does not mean "based only on".

[0148] The operations of the processes described in this specification can be performed in any suitable order, unless otherwise specified in this specification or clearly precluded by the context. In at least one embodiment, a process, such as the processes described in this specification (or variations and / or combinations thereof), is performed under the control of one or more computer systems configured with executable instructions and is implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) executed collectively on one or more processors, by hardware, or by a combination thereof. In at least one embodiment, the code is stored in a computer-readable storage medium in the form of a computer program comprising a plurality of instructions executable by, for example, one or more processors. In at least one embodiment, the computer-readable storage medium excludes a transient signal (e.g., a propagating transient electrical or electromagnetic transmission), but includes a non-transitory computer-readable storage medium that includes non-transitory data storage circuits (e.g., buffers, caches, and queues) within a transceiver of the transient signal. In at least one embodiment, the code (e.g., executable code or source code) is stored in a set of one or more non-transitory computer-readable storage mediums, which storage mediums store executable instructions that, when executed by one or more processors of a computer system (i.e., as a result of execution), cause the computer system to perform the operations described in this specification (or have other memory for storing the executable instructions). The set of non-transitory computer-readable storage mediums comprises, in at least one embodiment, a plurality of non-transitory computer-readable storage mediums, where one or more of the individual non-transitory storage mediums of the plurality of non-transitory computer-readable storage mediums do not have all of the code, but the plurality of non-transitory computer-readable storage mediums collectively store all of the code.In at least one embodiment, executable instructions are executed such that different instructions are executed by different processors. For example, a non-transitory computer-readable storage medium stores the instructions, a main central processing unit (“CPU”) executes some of the instructions, and a graphics processing unit (“GPU”) executes other instructions. In at least one embodiment, different components of a computer system have separate processors, and the different processors execute different subsets of instructions.

[0149] Accordingly, in at least one embodiment, a computer system is configured to implement one or more services that perform the operations of the processes described herein, either alone or in combination, and such a computer system is composed of applicable hardware and / or software that enables the execution of the operations. Further, a computer system implementing at least one embodiment of the present disclosure can be a single device, or in another embodiment, a distributed computer system comprising multiple devices operating in different ways, such that the distributed computer system performs the operations described herein without a single device performing all the operations.

[0150] The use of any examples or exemplary language (e.g., “such as”) provided herein is intended merely to clarify the embodiments of the present disclosure and does not limit the scope of the present disclosure unless otherwise claimed. No language in this specification should be construed as indicating any non-claimed element as essential to the practice of the present disclosure.

[0151] All references, including publications, patent applications, and patents, cited herein are hereby incorporated by reference to the same extent as if each reference had been individually and specifically indicated to be incorporated by reference and were set forth in its entirety herein.

[0152] In the specification and claims, the terms "coupled" and "connected" may be used along with their derivatives. It should be understood that these terms may not be intended as synonyms for each other. Rather, in certain instances, "connected" or "coupled" may be used to indicate that two or more elements are in direct or indirect physical or electrical contact with each other. Also, "coupled" may mean that two or more elements are not in direct contact with each other but still co-act or interact with each other.

[0153] Unless otherwise specifically stated, throughout the specification, terms such as "process", "calculate", "compute", or "determine" refer to actions and / or processes of a computer or computing system, or similar electronic computing device that operate and / or transform data represented as physical, such as electronic, quantities within a register and / or memory of the computing system into other data similarly represented as physical quantities within a memory, register, or other such information storage device, transmission device, or display device of the computing system.

[0154] Similarly, the term "processor" may refer to any device, or portion of a device, that processes electronic data from registers and / or memory and can transform that electronic data into other electronic data that can be stored in registers and / or memory. By way of non-limiting example, a "processor" may be a CPU or a GPU. A "computing platform" may comprise one or more processors. A "software" process as used herein may include software and / or hardware entities that perform work over time, such as tasks, threads, and intelligent agents. Also, each process may refer to multiple processes for executing instructions serially or in parallel, continuously or intermittently. The terms "system" and "method" are used interchangeably herein only insofar as a system can embody one or more methods and a method can be considered a system.

[0155] As used herein, references may be made to obtaining, acquiring, receiving, or inputting analog or digital data into a subsystem, computer system, or computer-implemented machine. Obtaining, acquiring, receiving, or inputting analog or digital data may be implemented in various ways, such as receiving data as parameters of a function call or a call to an application programming interface. In some implementations, the process of obtaining, acquiring, receiving, or inputting analog or digital data may be implemented by transferring data over a serial or parallel interface. In other implementations, the process of obtaining, acquiring, receiving, or inputting analog or digital data may be implemented by transferring data over a computer network from a providing entity to an acquiring entity. References may also be made to providing, outputting, transmitting, sending, or presenting analog or digital data. In various examples, the process of providing, outputting, transmitting, sending, or presenting analog or digital data may be implemented by transferring data as input or output parameters of a function call, an application programming interface, or an inter-process communication mechanism.

[0156] While the above discussion describes example implementations of the described techniques, other architectures may be used to implement the described functionality, and such other architectures are intended to be within the scope of this disclosure. Additionally, while for purposes of discussion, a specific distribution of responsibilities is defined above, the various functions and responsibilities may be distributed and divided differently depending on the circumstances.

[0157] Furthermore, although the subject matter has been described in language specific to structural features and / or methodological acts, it is to be understood that the subject matter claimed in the appended claims is not necessarily limited to the specific features or acts described. Rather, the specific features and acts are disclosed as exemplary forms of implementing the claims.

Claims

1. Calculating one or more values indicative of one or more emotions, at least partially based on audio data representing an utterance, using a transformer-based neural network; Determining that at least one of the one or more emotions corresponds to the utterance, at least partially based on the one or more values; Performing one or more actions, at least partially based on the at least one emotion; A computer-implemented method comprising.

2. The computer-implemented method of claim 1, wherein the one or more values include one or more probability values for each of the one or more emotions, and the one or more values are normalized and summed to an absolute value.

3. The computer-implemented method of claim 1, wherein the one or more emotions include at least one of anger, disgust, fear, joy, sadness, or a neutral emotion.

4. The computer-implemented method of claim 1, further comprising providing an interface for receiving user input corresponding to one or more adjustments of the one or more values.

5. The computer-implemented method of claim 4, further comprising receiving, via the interface, one or more emotion intensity values to be used when weighting the at least one emotion against at least one other emotion of the one or more emotions determined to correspond to the utterance.

6. Receiving one or more prior values corresponding to the one or more emotions, via the interface; Mixing the one or more prior values with the one or more values to generate one or more mixed values; Further comprising, The step of determining that the at least one of the one or more emotions corresponds to the utterance is at least partially based on the one or more mixed values, the computer-implemented method of claim 4.

7. The computer-implemented method of claim 6, further comprising receiving one or more prior emotion intensity values corresponding to the one or more emotions, the one or more prior emotion intensity values indicating one or more weights used when mixing the one or more prior values with the one or more values.

8. The method further includes determining, for each keyframe in a set of keyframes in the audio data, one or more probability values for one or more of the one or more emotions, the one or more probability values being determined using a sliding window of the audio data for a given audio segment, the computer-implemented method according to claim 1.

9. The computer-implemented method according to claim 8, further including smoothing the one or more values corresponding to the one or more emotions over a plurality of iterations.

10. The computer-implemented method according to claim 1, wherein the audio data is represented using an audio file format.

11. providing audio data in an audio file format as an input to a transformer neural network; using the transformer neural network to calculate one or more values indicative of one or more emotions corresponding to the audio data, based at least in part on the audio data; performing one or more operations based at least in part on a determination that at least one of the one or more emotions corresponds to the audio data One or more processing units A processor comprising.

12. The processor according to claim 11, wherein the one or more emotions include a set of predetermined emotions, the set of predetermined emotions including at least anger, disgust, fear, joy, sadness, or neutrality.

13. The one or more processing units are further weighting the one or more values based at least in part on one or more emotion intensity values corresponding to each of the one or more emotions; The processor according to claim 11, wherein the one or more operations are performed based at least in part on the weighted one or more values.

14. The one or more processing units are receiving one or more previous values corresponding to the one or more emotions; mixing the one or more previous values with the one or more values to generate one or more mixed values further performing The processor according to claim 11, wherein the determination that the at least one emotion among the one or more emotions corresponds to the audio data is at least partially based on the one or more mixed values.

15. The processor according to claim 11, wherein the audio file format includes at least one of an uncompressed audio file format, a lossless compressed audio file format, or a lossy compressed audio file format.

16. Using a transformer neural network, calculating one or more first values indicating the probability that one or more emotions correspond to the utterance, based at least in part on audio data representing the utterance; Using a neural network, calculating one or more second values indicating the position of one or more feature points corresponding to a virtual object, based at least in part on the one or more first values and the audio data; Rendering the virtual object based at least in part on the one or more second values; One or more processing units for performing A system comprising.

17. The system according to claim 16, wherein the audio data corresponds to an audio file format.

18. The system according to claim 16, wherein the audio data is processed in an audio file format using the transformer neural network, and the audio data is processed in an image file format using the neural network.

19. The system according to claim 16, wherein the one or more feature points correspond to one or more facial features or one or more body features of the virtual object.

20. The system is A system for performing simulation operations, A system for performing digital twin operations, A system for performing light transport simulation, A system for performing collaborative content creation of 3D assets A system for performing deep learning operations, A system implemented using an edge device, A system implemented using a robot, A system for performing conversational AI operations, A system for generating synthetic data, A system incorporating one or more virtual machines (VMs), A system implemented at least partially in a data center A system implemented at least partially using cloud computing resources The system according to claim 16, comprising at least one of the foregoing

Images