Body language detection and microphone control

Abstract

A system includes a gimbal, a gun microphone 12 coupled to the gimbal 14, a camera 26, and at least one processor. The at least one processor is configured to receive data indicative of an image or video feed from the camera 26. The at least one processor is further configured to determine a primary human speaker among a group of humans 50 and a location of the primary human speaker based on the data indicative of the image or video feed. The at least one processor is further configured to control the gimbal 14 to direct the gun microphone 12 to the location of the primary human speaker.

Description

Background Art

[0001] This section is intended to introduce the reader to various aspects of the technology that may be related to various aspects of the present disclosure, which are described and / or claimed below. It is believed that this discussion helps to provide background information for the reader in order to promote a better understanding of various aspects of the present disclosure. Therefore, it is understood that these statements are to be read from this perspective and not as an admission of prior art.

[0002] Entertainment venues (such as theme parks, amusement parks, theaters, cinemas, stadiums, concert halls, and the like) have been created to provide a variety of immersive experiences to a group of customers. These entertainment venues may include performance attractions (e.g., movies, plays, rides, games) that provide immersive experiences to customers. For example, traditional performance attractions can enable customers to interact with various performance elements of traditional performance attractions. However, it is now recognized that traditional performance attractions are not fully designed to enable accurate and / or continuous interaction of specific customers in the audience with various performance elements of traditional performance attractions. For example, ambient noise from the audience may reduce the flexibility or range of interaction of specific customers with performance elements of traditional performance attractions. Accordingly, it is now recognized that improved interactive performance attractions are desired. Summary of the invention

[0003] The following summarizes certain embodiments that are commensurate in scope with the originally claimed subject matter. These embodiments are not intended to limit the scope of the present disclosure, but rather, these embodiments are intended only to provide a brief overview of certain disclosed embodiments. Indeed, the present disclosure may encompass various forms that may be similar or different from the embodiments set forth below.

[0004] In one embodiment, a system includes a gimbal, a shotgun microphone coupled to the gimbal, a camera, and at least one processor. The at least one processor is configured to: receive data indicating an image or video feed from the camera; determine a location of a primary human speaker based on the image video feed; and actuate the gimbal to point the shotgun microphone toward the location of the primary human speaker.

[0005] In one embodiment, a system includes a microphone assembly, a camera, and at least one processor. The at least one processor is configured to: receive data indicating an image or video feed from the camera; and determine a primary human speaker among a human group and a location of the primary human speaker based on the data indicating the image or video feed. The at least one processor is also configured to control the microphone assembly based on the location of the primary human speaker.

[0006] In one embodiment, one or more tangible non-transitory computer readable media include instructions thereon that, when executed by at least one processor, cause the at least one processor to perform various operations. The operations include receiving data from a camera indicating an image or video feed capturing a human group. The operations also include determining a primary human speaker among the human group via a body language detection algorithm receiving the data indicating the image or video feed. The operations also include controlling a motorized gimbal to point a shotgun microphone toward the primary human speaker among the human group. The operations also include receiving data via the shotgun microphone indicating sounds captured by the shotgun microphone. The operations also include determining commands issued by the primary human speaker based on the data indicating the sounds captured by the shotgun microphone. The operations also include controlling performance elements based on the commands. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] These and other features, aspects and advantages of the present disclosure will become better understood when the following detailed description is read with reference to the accompanying drawings, in which like characters refer to like parts throughout the drawings, and in which:

[0008] Figure 1 is a schematic illustration of a performance attraction according to an aspect of the present disclosure, the performance attraction including a control assembly configured to identify a primary human speaker among a human group and to control positioning of a shotgun microphone directed toward the primary human speaker;

[0009] Figure 2 According to one aspect of the present disclosure Figure 1 a schematic illustration of a performance attraction of wherein the control assembly is configured to identify a new primary human speaker among the human group and control the shotgun microphone to point to a new location of the new primary human speaker;

[0010] Figure 3 According to one aspect of the present disclosure Figure 1 a schematic perspective view of a portion of a performance attraction of , wherein the control assembly is configured to control an aspect of the performance attraction based on commands received from a primary human speaker via a shotgun microphone;

[0011] Figure 4 is a method for identifying a primary human speaker according to an aspect of the present disclosure Figure 1 A schematic illustration of a body language detection algorithm employed in a control assembly of a performance attraction;

[0012] Figure 5 is a diagram illustrating a control method according to one aspect of the present disclosure Figure 1 A flow chart of a method for a performance attraction to identify a primary human speaker, direct a shotgun microphone toward the location of the primary human speaker, and control performance elements of the performance attraction;

[0013] Figure 6 is a schematic illustration of a performance attraction including a control assembly configured to identify a primary human speaker among a human group and to select a microphone from an array of microphones corresponding to the primary human speaker according to an aspect of the present disclosure;

[0014] Figure 7 is a diagram illustrating a control method according to one aspect of the present disclosure Figure 6 A flow chart of a method of a performance attraction identifying a primary human speaker, selecting a microphone from an array of microphones corresponding to the primary human speaker, and controlling a performance element of the performance attraction; and

[0015] Figure 8 is a schematic illustration of a teleconferencing system including a control assembly configured to identify a primary human speaker among a human group and to select a microphone from an array of microphones corresponding to the primary human speaker according to an aspect of the present disclosure. DETAILED DESCRIPTION

[0016] One or more specific embodiments will be described below. In an effort to provide a concise description of these embodiments, not all features of an actual implementation are described in this specification. It should be appreciated that in the development of any such actual implementation, as in any engineering or design project, many implementation-specific decisions must be made to achieve the developer's specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another. Moreover, it should be appreciated that such development work may be complex and time consuming, but will be nothing more than a routine matter of design, fabrication, and manufacturing for those of ordinary skill who benefit from this disclosure.

[0017] When introducing elements of various embodiments of the present disclosure, the articles "a," "an," and "the" are intended to mean that there are one or more of the elements. The terms "comprising," "including," and "having" are intended to be inclusive and mean that there may be additional elements in addition to the listed elements. Furthermore, it should be understood that references to "one embodiment" or "an embodiment" of the present disclosure are not intended to be interpreted as excluding the existence of additional embodiments that also incorporate the recited features.

[0018] The present disclosure generally relates to a show attraction system configured to capture commands from a primary human speaker among a human group and control show elements of the show attraction based on the commands from the primary human speaker. More specifically, the present disclosure relates to a control assembly that identifies a primary human speaker among a human group (e.g., via processing of an image or video feed of the human group), directs a shotgun microphone at the identified primary human speaker, and controls one or more show elements of the show attraction based on commands received from the identified primary human speaker via the shotgun microphone.

[0019] Entertainment venues may include various performance attractions (e.g., movies, plays, rides, games) that enable interaction between patrons attending the performance attractions and various performance elements of the performance attractions. For example, a patron may issue a command that is received by a microphone of the performance attraction, and a control assembly of the performance attraction may implement changes to one or more performance elements (e.g., physical performance props, electronic screens, performance lights, and the like) based on the command. Unfortunately, utilizing voice commands may be problematic due to ambient noise that interferes with voice commands. For example, a group of patrons may attend a performance attraction, where a subset of the group (such as a single patron) is assigned the task of issuing commands that are captured by a microphone and executed by the performance attraction. Separating commands from ambient noise may be difficult due to ambient noise generated by other patrons and / or other sources.

[0020] According to the present disclosure, a camera may be used by a performance attraction to capture an image or video feed of a group of patrons (hereinafter referred to as a human group). A controller may receive data indicative of the image or video feed from the camera and identify a primary human speaker of the human group based on the data indicative of the image or video feed. For example, one or more persons of the human group may be assigned the task of issuing commands implemented by the performance attraction at multiple intervals of the performance attraction when the human group may be engaged in conversation or otherwise generate noise throughout the duration of the performance attraction. The controller may execute a body language detection algorithm that receives data indicative of the image or video feed and identifies a primary human speaker (e.g., a speaker issuing commands) from the human group based on the data. In practice, the body language detection algorithm may be used to detect various body languages ​​indicative of a primary (e.g., active, controlling, or dominant) human speaker, such as facial expressions, hand gestures, head postures, body postures, body movements, body orientations, body positions, and the like. That is, certain types of body language may indicate a primary (eg, active, controlling, or dominant) speaker, while other types of body language may indicate a secondary (eg, passive, suppressed, or submissive) speaker or a non-speaker.

[0021] In some embodiments, a performance attraction may require (or otherwise initiate) certain body language indicating a primary human speaker being requested to issue a command. For example, the performance attraction may instruct or otherwise request a patron to wave her hand or nod her head, which may be detected via a body language detection algorithm executed by the controller based on data indicating an image or video feed. Additionally or alternatively, the performance attraction may instruct or otherwise request a patron to wave a wand or other prop, where the waving motion may be detected via a body language detection algorithm executed by the controller based on data indicating an image or video feed to identify a primary human speaker from a group of humans. In addition to identifying a primary human speaker, the controller may also identify a location of the primary human speaker based on data indicating an image or video feed. For example, various components of the performance attraction (e.g., a camera) may include a fixed position or origin known by the controller and configured to enable the controller to determine or infer the location of a primary human speaker within the performance attraction.

[0022] After identifying the primary human speaker and the location of the primary human speaker, the controller may control various performance elements of the performance attraction and / or a motorized gimbal (or other motion platform) coupled to a shotgun microphone to point the shotgun microphone toward the primary human speaker. Focusing first on the various performance elements of the performance attraction, the controller may control, for example, electronic displays, physical performance props, and / or performance lights based on the identification of the primary human speaker and its location. For example, an electronic display may be controlled to present a digital avatar having specific characteristics corresponding to the primary human speaker (such as a specific shape, color, size, brightness, directionality, or the like). Physical performance props may be controlled to a position, for example, adjacent to the location of the primary human speaker. For example, performance lights may be controlled to illuminate a spotlight toward the location of the primary human speaker. According to the present disclosure, other performance elements that are controlled based on the identification of the primary human speaker and the location of the primary human speaker may be employed.

[0023] As noted above, the controller also controls a motorized gimbal (or other motion platform) coupled to the shotgun microphone to point the shotgun microphone toward a primary human speaker (also referred to as a primary speaker). As will be understood by those of ordinary skill in the art, a "shotgun microphone" is used in the present disclosure to refer to a class of relatively high-directional microphones configured to capture sounds in a limited area and / or in a limited directional range. A shotgun microphone may be contrasted with other types of microphones (such as omnidirectional microphones) that are configured to capture sounds from many directions. Because other types of microphones capture sounds from many directions with relatively comparable intensities, they are susceptible to capturing ambient noise that interferes with the target sound (e.g., a command from a primary speaker) that is intended to be captured. Accordingly, a shotgun microphone may provide the advantage of excluding ambient noise and better capturing the target sound (e.g., a command from a primary speaker). Further, sound signals captured via other types of microphones may require relatively intensive and expensive processing software to filter ambient noise from the target sound. Accordingly, according to the present embodiment, signal processing of sound signals captured by a shotgun microphone may be relatively cost-effective and efficient.

[0024] As a non-limiting example, a shotgun microphone may include a relatively long tube (e.g., a tube having a length of approximately 6 inches [15.2 centimeters] to 30 inches [76.2 centimeters]), a set of phase cancelling holes or slots extending through the tube, and a diaphragm disposed on the inside of the tube. The diaphragm may receive sound from the phase cancelling holes or slots and, in some embodiments, from the open front end of the tube. In general, sound originating from the location at which the shotgun microphone is pointed is in phase and is captured to a greater extent than sound originating from other locations that are out of phase and are captured to a lesser extent (or not at all). As a result, shotgun microphones are generally better at rejecting ambient noise than other types of microphones, such as omnidirectional microphones.

[0025] After the shotgun microphone is pointed at the identified primary human speaker, the shotgun microphone may capture sounds generated by the primary human speaker and transmit data indicating the captured sounds to the controller. The controller may determine the commands issued by the primary human speaker based on the data indicating the captured sounds. For example, the controller may execute a speech recognition algorithm that receives data indicating the captured sounds to determine the commands issued by the primary human speaker. Based on the commands, the controller may control one or more performance elements of the performance attraction, such as an electronic screen, a physical performance prop, a performance light, or other performance element. As a non-limiting example, the primary human speaker may issue a command to change the color of a digital avatar presented on an electronic screen, change the position of a physical performance prop, or change the direction, intensity, or color of a performance light. Other commands associated with the control of performance elements may also be employed in accordance with the present disclosure.

[0026] In some embodiments, control of a performance element based on the identification of a primary human speaker (or its location) and control of a performance element based on a command issued by the primary human speaker may be implemented in combination or sequentially. As a non-limiting example, a controller may cause a digital avatar presented on an electronic display to include a shape (e.g., a triangle) corresponding to the identification of the primary human speaker, and the controller may cause the digital avatar presented on the electronic display to adjust a separate characteristic (e.g., change to a larger size) corresponding to a command issued by the primary human speaker. Thus, the digital avatar presented on the electronic screen may include a larger sized triangular shape after the command issued by the primary human speaker is executed. The present disclosure may also employ other control features, such as those described in detail below with reference to the accompanying drawings. In general, the presently disclosed embodiments operate to improve the interaction of patrons attending a performance attraction with a performance element of a performance attraction, reduce the cost or processing complexity associated with the above interaction, and / or improve the customer experience by way of the above interaction relative to conventional embodiments. These and other features are described in detail below with reference to the accompanying drawings.

[0027] Figure 1 1 is a schematic illustration of an embodiment of a performance attraction 10 that includes a control assembly 11 configured to identify a primary human speaker among a human group and to control the positioning of a shotgun microphone 12 directed toward the primary human speaker. In the illustrated embodiment, among other features, the control assembly 11 also includes a shotgun microphone 12 coupled to a gimbal 14 having a motor 16. As will be appreciated in light of the description below, the shotgun microphone 12 is used in accordance with the present disclosure to improve the capture of sound from a particular patron among the patrons by excluding ambient noise associated with the patrons and other sources. In general, the shotgun microphone 12 is a type of relatively highly directional microphone that is configured to capture sound in a limited area and / or a limited range of directions. The shotgun microphone 12 can be contrasted with other types of microphones (such as omnidirectional microphones) that are configured to capture sound from many directions. Because other types of microphones (such as omnidirectional microphones) capture sound from many directions, they are susceptible to capturing ambient noise that interferes with the target sound that is intended to be captured. Accordingly, the shotgun microphone 12 may provide the advantages of rejecting ambient noise, better capturing target sounds, and requiring less intensive and expensive signal processing relative to other types of microphones that capture higher levels of ambient noise.

[0028] As a non-limiting example, the shotgun microphone 12 may include a tube 13 (e.g., a tube having a length of approximately 6 inches [15.2 centimeters] to 30 inches [76.2 centimeters]), a set of phase cancellation holes or slots 15 extending through the tube 13, and a septum 17 disposed inside the tube 13. The septum 17 may receive sound from the phase cancellation holes or slots 15 and, in some embodiments, from an open front end 19 of the tube 13. In general, sound originating from the localization at which the shotgun microphone 12 is directed is in phase and is captured to a greater extent than sound originating from other localizations that are out of phase and are captured to a lesser extent (or not at all). As a result, the shotgun microphone 12 is generally better at rejecting ambient noise than other types of microphones, such as omnidirectional microphones. As described in detail below, the performance attraction 10 includes a control assembly 11 configured to identify a primary human speaker among a group of humans, direct the shotgun microphone 12 toward the primary human speaker, and perform various control features of a performance element of the performance attraction 10. Thus, the shotgun microphone 12 captures the sound generated by the primary human speaker without high levels of ambient noise relative to other types of microphones.

[0029] For example, the performance attraction 10 includes a controller 18 having a processing circuit 20, a memory circuit 22, and a communication circuit 24. The memory circuit 22 includes instructions stored thereon that, when executed by the processing circuit 20, cause the processing circuit 20 to perform various operations described in detail below. The communication circuit 24 is configured to enable communication between the controller 18 and various other aspects of the performance attraction 10. For example, the communication circuit 24 may enable communication between the controller 18 and the motor 16 of the gimbal 14, the shotgun microphone 12 coupled to the gimbal 14, the camera 26 of the control assembly 11, the show lights 28, the additional microphone 30 (e.g., an omnidirectional microphone) of the control assembly 11, the show prop motor 32 of the physical show prop 34 (e.g., a train, a cart, or an animated figure), the electronic screen 36, or any combination thereof.

[0030] According to the present disclosure, the camera 26 is configured to provide the controller 18 with data indicative of an image or video feed of a stage area 38 of the performance attraction 10. Patrons (e.g., a first person 40, a second person 42, a third person 44, a fourth person 46, and a fifth person 48) may be located in the stage area 38 and captured in an image or video feed by the camera 26. The first person 40, the second person 42, the third person 44, the fourth person 46, and the fifth person 48 may be collectively referred to as a human group 50. The controller 18 may identify a primary human speaker among the human group 50 based on the data indicative of the image or video feed received from the camera 26. For example, the controller 18 may execute a body language detection algorithm that receives the data indicative of the image or video feed, wherein the body language detection algorithm identifies a primary human speaker among the human group 50. As will be appreciated in light of the discussion that follows, a primary human speaker may be identified via execution of a body language detection algorithm based on detected facial expressions indicative of a primary (or active) human speaker, hand gestures indicative of a primary (or active) human speaker, head posture indicative of a primary (or active) human speaker, body posture indicative of a primary (or active) human speaker, body movement indicative of a primary (or active) human speaker, body orientation indicative of a primary (or active) human speaker, and the like. Indeed, certain types of body language may naturally indicate a primary (e.g., active, controlling, or dominant) speaker, while other types of body language (or the lack of detected body language) may indicate a secondary (e.g., passive, suppressed, or submissive) speaker or a non-speaker.

[0031] Further, in some embodiments, the show attraction 10 may require (or otherwise initiate) certain body language indicative of the primary human speaker. For example, the show attraction 10 may instruct or otherwise require the primary human speaker to wave her hand, wave a wand or other prop, nod her head, or the like, which may be detected via a body language detection algorithm executed by the controller 18 based on data indicative of an image or video feed received from the camera 26. Still further, in some embodiments, in addition to the data indicative of the image or video feed, audio captured by an additional microphone 30 (e.g., an omnidirectional microphone) may also be analyzed by the controller 18 to facilitate identification of the primary human speaker. That is, while the audio captured by the additional microphone 30 may not be used to determine commands issued by the primary human speaker, the audio captured by the additional microphone 30 may be used in combination with the data indicative of the image or video feed to facilitate identification of the primary human speaker.

[0032] In the illustrated embodiment, the controller 18 determines that the third person 44 among the human group 50 is the primary human speaker based on a gesture (e.g., waving), and ascertains the location of the primary human speaker relative to the shotgun microphone 12 (or the origin of the shotgun microphone 12). In practice, the camera 26 may be arranged at a fixed location so that the location of the identified primary human speaker relative to the camera 26 is known. Further, the location of the shotgun microphone 12 (or the origin of the shotgun microphone 12) may also be known so that the location of the primary human speaker relative to the shotgun microphone 12 (or the origin of the shotgun microphone 12) may be determined, inferred, or interploated based on the location of the primary human speaker relative to the camera 26. Other location techniques may also be used in accordance with the present disclosure. For example, the stage area 38 may include various unique indicators 39 having known locations distributed around the stage area 38 and captured by the camera 26 in an image or video feed. The location of a primary human speaker, such as third person speaker 44 , may be determined based on the primary human speaker's proximity to one of the unique indicators 39 .

[0033] According to the present disclosure, the controller 18 controls the positioning of the shotgun microphone 12 toward the third person 44 based on the identification of the third person 44 as the primary human speaker and its positioning. The shotgun microphone 12 can be controlled to rotate in a first circumferential direction 41 around a first axis 43, in a second circumferential direction 45 around a second axis 47, and in a third circumferential direction 49 around a third axis 51 via the gimbal 14 and the corresponding motor 16. The shotgun microphone 12 can also be controlled to translate along the first axis 43, the second axis 47, and the third axis 51 via the gimbal 14 and the corresponding motor 16.

[0034] In an embodiment, multiple instances of the motor 16 may be used to achieve the above-described movement of the shotgun microphone 12 via the gimbal 14. Further, it should be noted that the gimbal 14, as used herein, may refer to a mounting structure on any structure that enables translation and / or rotation of the shotgun microphone 12 (e.g., via actuation by one or more motors 16). Still further, it should be noted that the shotgun microphone 12, the gimbal 14, and the motor 16 may be collectively referred to as a microphone assembly 53. In general, the above-described rotation and / or translation of the shotgun microphone 12 via the gimbal 14 and corresponding motor(s) 16 may enable the shotgun microphone 12 to be directed toward any or substantially any location included in the stage area 38. In the illustrated embodiment, the shotgun microphone 12 is directed toward the third person 44 based on the third person 44 being identified as the primary human speaker. Accordingly, the sound captured by the shotgun microphone 12 includes the sound generated by the third person 44 and excludes (or includes to a lesser extent) the ambient noise generated by the first person 40, the second person 42, the fourth person 46 and the fifth person 48 and / or other ambient noise sources.

[0035] Before continuing with the discussion of the capture of commands issued by the primary human speaker (e.g., the third person 44 in the illustrated embodiment) by the shotgun microphone 12, it should be noted that the performance elements of the performance attraction 10 can be controlled based on the identification of the primary human speaker and its location. For example, the controller 18 can control the electronic screen 36 to present the digital avatar 54 corresponding to the third person 44 being the primary human speaker. In the illustrated embodiment, the triangular shape of the digital avatar 54 corresponds to the third person 44, while other shapes of the digital avatar 54 can correspond to the first person 40 (e.g., circle), the second person 42 (e.g., rectangle), the fourth person 46 (e.g., star), and the fifth person 48 (e.g., pentagon). Additionally or alternatively, other characteristics of the digital avatar 54 can be controlled to correspond to the identification of the primary human speaker. For example, in one embodiment, the directionality of the digital avatar 54 can be controlled based on the identification of the primary human speaker (e.g., so that the digital avatar 54 faces the primary human speaker). Further, in one embodiment, the digital avatar 54 may include a digital representation of a human, robot, animal, or some other creature, and may be presented on the electronic screen 36 such that it faces the location of the primary human speaker.

[0036] Still other performance elements may be controlled based on the identification of the primary human speaker and its location. For example, controller 18 may control performance lights 28 corresponding to the identification of third person 44 as the primary human speaker, such as controlling performance lights 28 so that a spotlight illumination circle is directed toward third person 44. Further, controller 18 may control physical performance prop 34 (e.g., a train, cart, or animated figure) to move physical performance prop 34 (e.g., along track 52) to a position adjacent to the identified primary human speaker, as shown.

[0037] Figure 2 An example of controlling performance elements differently based on the primary human speaker deviating from the third person 44 is illustrated in FIG. Figure 2 , a fourth person 46 is identified as a primary human speaker from the human group 50 based on a facial expression (such as a smile) indicative of a primary human speaker. Figure 2 Based on the identification of the fourth person 46 as the primary human speaker in the video, the controller 18 controls the physical performance prop 34 (e.g., a train, a cart, or an animated figure) such as along the track 52 to a position adjacent to the fourth person 46. Figure 2 The controller 18 also controls the electronic screen 36 to display a digital avatar 54 (e.g., having a star shape) corresponding to the fourth person 46, and controls the performance light 28 to illuminate the spotlight circle on the fourth person 46.

[0038] like Figure 1 and Figure 2 As shown in both, the shotgun microphone 12 is directed toward the identified primary human speaker (e.g., Figure 1 The third party and Figure 2 The controller 18 may receive data from the shotgun microphone 12 indicative of the sound captured by the shotgun microphone 12. As previously described, due to the directional nature of the shotgun microphone 12, a relatively large portion of the sound captured by the shotgun microphone 12 may originate from the primary human speaker at which the shotgun microphone 12 is directed, as opposed to sources of ambient noise (e.g., other persons in the human group 50). It should be noted that in an embodiment, the directionality of the shotgun microphone 12 may be adjusted at least in part based on the sound captured by the shotgun microphone 12. For example, the shotgun microphone 12 may first be controlled based on the identification of the primary human speaker and its location. If the sound captured by the shotgun microphone 12 includes ambient noise with an intensity above an ambient noise threshold, the directionality of the shotgun microphone 12 may be controlled (e.g., adjusted) in increments to locate a location where the ambient noise is reduced to below the ambient noise threshold. As will be appreciated in view of the description below, the controller 18 may determine the command issued by the primary human speaker based on the data indicative of the sound captured by the shotgun microphone 12, and then execute the command.

[0039] For example, Figure 3 yes Figure 1 1 is a schematic illustration of an embodiment of a portion of a performance attraction 10 in which a control assembly 11 is configured to control an aspect of the performance attraction 10 based on commands received from a primary human speaker. As previously described, a controller 18 of the control assembly 11 may receive instructions from a primary human speaker. Figure 1 and 2The computer program product 10 may include a data input 70 of sounds captured by the shotgun microphone 12 in the electronic screen 36 and execute a speech recognition algorithm that determines or infers a command based on the data input 70. The command may include an instruction to control one of the show elements of the show attraction 10. For example, the command may include an instruction to control a characteristic of the digital avatar 54 presented on the electronic screen 36 (such as the size, shape, color, brightness, or directionality of the digital avatar 54, the position or other characteristic of the physical show prop 34 (e.g., a train, cart, or animated figure), and the direction, color, intensity, brightness, or other characteristic of the show lights 28).

[0040] In one embodiment, one or more of the performance elements may be controlled based on both the identification of the primary human speaker (or its location) and the commands issued by the primary human speaker in combination or sequentially. For example, as previously described, Figure 1 The digital avatar 54 presented on the electronic screen 36 in the video may include a triangular shape corresponding to the identification of the third person 44 as the primary human speaker. The command issued by the primary human speaker (e.g., the third person 44) may include an instruction to increase the size of the digital avatar 54 so that the electronic screen 36 presents a larger triangular mark 72 corresponding to the digital avatar 54, or an instruction to move the position of the digital avatar 54 so that the electronic screen 36 presents a differently placed triangle 74 corresponding to the digital avatar 54.

[0041] According to the present disclosure, other changes (e.g., changes to shape, orientation, directionality, etc.) of the digital avatar 54 based on commands from the primary human speaker may also be employed. As another example, the digital avatar 54 may include a digital human, robot, or animal that is controlled to face the third person 44 based on the identification of the third person 44 as the primary human speaker and may be controlled to emote or react (e.g., smile, wave, jump, laugh) in response to commands issued by the third person 44 as the primary human speaker. Other performance elements of the performance attraction 10 may also be controlled based on the identification of the primary human speaker and the commands issued by the primary human speaker. For example, a physical performance prop 34 (e.g., a train, a cart, or an animated figure) may be moved (e.g., along the track 52) to different performance prop locations 76 via the performance prop motor 32 based on commands, and the direction 78 of the spotlight illumination circle generated by the performance light 28 may be changed based on commands. The combined control of show elements based on both the identification of the primary human speaker (and its location) and the commands issued by the primary human speaker may enable an enhanced immersive experience for human group 50 in show attraction 10 relative to conventional systems and methods.

[0042] As previously described, a primary human speaker may be identified from the human group 50 based on analysis of the image or video feed via a body language detection algorithm employed by the controller 18 . Figure 4 is Figure 1 Schematic illustration of an embodiment of a body language detection algorithm 90 for identifying a primary human speaker in a performance attraction 10 of FIG. In the illustrated embodiment, the body language detection algorithm 90 receives a data input (block 92) indicative of an image or video feed and includes a processing step of determining (block 94) body language characteristics of a group of humans captured in the image or video feed based on the data input 92. For example, the body language characteristics may include facial expressions 96 of each person, hand gestures 98 of each person, head postures 100 of each person, body postures 102 of each person, body movements 104 of each person, body orientations 106 of each person, body positions 108 of each person, and other body language characteristics 110. The body language characteristics may be determined based on the data input 70 based on, for example, computer vision techniques such as three-dimensional (3D) gesture analysis or estimation, motion analysis or estimation (e.g., tracking and / or optical flow), shape recognition, facial recognition, feature extraction, and the like.

[0043] The body language detection algorithm 90 then compares the detected body language characteristics (such as those described above) to reference body language characteristics (box 95). In the illustrated embodiment, the reference body language characteristics are stored to the database 112. The reference body language characteristics may include only characteristics indicative of a primary (e.g., active, controlling, or dominant) human speaker. Alternatively, the reference body language characteristics may include a first subset of characteristics indicative of a primary human speaker and a second subset of characteristics indicative of a secondary (e.g., passive, suppressed, or submissive) human speaker or non-speaker.

[0044] The body language detection algorithm 90 then identifies (block 114) a primary human speaker based on a comparison of the detected body language characteristics with the reference body language characteristics. In embodiments where the reference body language characteristics include those reference body language characteristics indicative of a primary human speaker and those reference body language characteristics indicative of a secondary human speaker (or a non-speaker), the body language detection algorithm 90 may be operable to exclude members of the group of humans identified as secondary human speakers (or non-speakers). Further, humans who are not exhibiting any detectable body language characteristics may be excluded by the detection algorithm 90 from being identified as primary human speakers. Additionally, the correspondence (or matching) of the detected body language characteristics with the reference body language characteristics indicative of a primary human speaker may be used by the body language detection algorithm 90 to identify the primary human speaker.

[0045] The body language detection algorithm 90 may also include aspects of machine learning or artificial intelligence. For example, the body language detection algorithm 90 may include an operation to verify (block 116) whether the determination of the primary human speaker is accurate. In one embodiment, the identification of the primary human speaker may be verified as accurate when a verifiable command issued by the identified primary human speaker is detected. Additionally or alternatively, the identification of the primary human speaker may be verified as inaccurate when a verifiable command issued by the identified primary human speaker is not detected. Other verification techniques may also be employed in accordance with the present disclosure. In verifying whether the identification of the primary human speaker is accurate, certain aspects employed in the body language detection algorithm 90 may be updated. For example, any of the data processing, comparison, or analysis in blocks 94, 95, and 114 may be updated. As an example, certain types of body language characteristics detected in block 94 may be added or removed in future iterations of the body language detection algorithm 90. Additionally or alternatively, the database 112 storing various reference body language characteristics for comparison with the detected body language characteristics may be updated based on the verification occurring in block 116. Updating the body language detection algorithm 90 based on the validation step at box 116 may enable adjustments to the body language detection algorithm 90. It should be noted that body language characteristics indicative of a primary human speaker may deviate based on unique cultural or regional expressions, based on the development of body language over time, and the like. By enabling the body language detection algorithm 90 to be updated or modified in light of the validation step at box 116, the body language detection algorithm 90 may be enhanced and / or customized over time to account for changes or differences in body language due to the above reasons.

[0046] In general, the body language detection algorithm 90 can be used as Figure 1 The method is part of a larger process employed in the performance attraction 10 of the present invention to identify a primary human speaker and control various performance elements of the performance attraction 10 based at least in part on the commands issued by the primary human speaker. For example, Figure 5 It is a graphic control Figure 1 1. A flow chart of a method 150 of identifying a primary human speaker, directing a shotgun microphone toward the location of the primary human speaker, and controlling a performance element of the performance attraction. Figure 5 The method 150 illustrated in FIG. 1 includes receiving (block 152) data indicating, via a controller and from a camera, capturing an image or video feed of a human group. For example, the human group may be located in a stage area of ​​a performance attraction and the camera may be configured to capture an image or video feed of the stage area.

[0047] The method 150 also includes determining (block 154) a primary human speaker (and its location) among the human group via a body language detection algorithm executed by the controller and receiving data indicative of the image or video feed. For example, Figure 4The body language detection algorithm 90 illustrated in FIG. 1 may be executed by a controller. In general, the body language detection algorithm is configured to detect various body language characteristics of each member of the human group, such as facial expressions, gestures, head postures, body postures, body movements, body orientations, body positions, and the like. As previously described, certain types of body language may indicate a primary (e.g., active, controlling, or dominant) speaker, while other types of body language may indicate a secondary (e.g., passive, suppressed, or submissive) speaker or a non-speaker. The body language detection algorithm may be configured to compare the detected body language characteristics with reference body language characteristics to identify a primary human speaker. In addition to detecting the primary human speaker, the controller may also ascertain the location of the primary human speaker, as previously described.

[0048] The method 150 also includes controlling (block 156) via a controller a configuration of a show element of a show attraction based on the identification of a primary human speaker, the location of the primary human speaker, or both. For example, the controller may be capable of controlling a particular show element to a plurality of different show element configurations. The controller may select a show element configuration from the plurality of different show element configurations based on the identification of the primary human speaker, the location of the primary human speaker, or both. As previously described, the controller may control an electronic display, a physical show prop (e.g., a train, cart, or animated figure), show lights, or a combination thereof based on the identification of the primary human speaker and / or its location. In one embodiment, the electronic display may be controlled to present a digital avatar having characteristics (e.g., size, shape, color, orientation, or the like) corresponding to the primary human speaker or its location.

[0049] As an example, the digital avatar may be controlled to include a first size based on a first customer identified as the primary human speaker, and a second size based on a second customer identified as the primary human speaker, wherein the first size is different from the second size. Additionally or alternatively, the controller may control a physical performance prop to a position corresponding to the primary human speaker or its location. Further, the controller may control the performance lights to illuminate the spotlight illumination circle on the primary human speaker. Other controls may also be employed in accordance with the present disclosure.

[0050] The method 150 also includes controlling (block 158) the motorized gimbal, via the controller, to point the shotgun microphone toward the location of the primary human speaker. For example, the motorized gimbal may be controlled to rotate and / or translate the shotgun microphone so that the shotgun microphone is directed toward the location of the primary human speaker. As previously described, the shotgun microphone is configured to capture the sound produced by the primary human speaker while excluding ambient noise. Relative to other types of microphones (such as omnidirectional microphones), the shotgun microphone may be better at excluding ambient noise (e.g., from other members of the human group). By better excluding ambient noise, the shotgun microphone may transmit the sound signal to the controller that does not require as intensive and expensive signal processing techniques as those associated with other types of microphones (such as omnidirectional microphones).

[0051] The method 150 also includes receiving (block 160) data indicating sounds captured by the shotgun microphone via the shotgun microphone. As previously described, the sounds captured by the shotgun microphone may correspond primarily to sounds produced by a primary human speaker, while ambient noise may be excluded and / or recorded at a relatively low intensity. The method 150 also includes determining (block 162) commands issued by the primary human speaker via the controller and based on the data indicating sounds captured by the shotgun microphone. As previously described, the controller may execute a speech recognition algorithm that determines commands issued by the primary human speaker based on the data indicating sounds captured by the shotgun microphone. In one embodiment, the speech recognition algorithm may detect a language associated with the command. In another embodiment, the language may be known and the speech recognition algorithm may be directed to the known language.

[0052] Method 150 also includes controlling (block 164) a show element based on the command via the controller. For example, an electronic screen, a physical show prop (e.g., a train, a cart, or an animated figure), a show light, another show element, or any combination thereof may be controlled based on the command issued by the primary human speaker. In some embodiments, control of the show element based on the identification of the primary human speaker or its location (e.g., at block 156) and control of the show element based on the command issued by the primary human speaker (e.g., at block 164) may be implemented in combination or sequentially. For example, the controller may cause a digital avatar presented on an electronic display to include a shape corresponding to the identification of the primary human speaker (e.g., a triangle), and the controller may cause the digital avatar presented on the electronic display to include a separate feature corresponding to the command issued by the primary human speaker (e.g., a larger sized triangle shape). Alternatively, control of the show element based on the command issued by the primary human speaker may be completely separate from control of the show element based on the identification of the primary human speaker. For example, an electronic screen may be controlled to present a digital avatar having certain characteristics based on the identity of the primary human speaker (or its location), while a physical performance prop may be controlled to a position based on commands issued by the primary human speaker.

[0053] Figure 6 is a schematic illustration of an embodiment of a performance attraction 10 including a control assembly 11 configured to identify a primary human speaker (e.g., third person 44) among a group of humans 50 (e.g., first person 40, second person 42, third person 44, fourth person 46, and fifth person 48). Further, Figure 6 The performance attraction 10 in the embodiment of the present invention includes a microphone array 200, which is referred to as a microphone assembly in certain examples of the present disclosure, and which employs multiple microphones, such as a first microphone 202, a second microphone 204, a third microphone 206, a fourth microphone 208, and a fifth microphone 210, wherein a controller 18 of the control assembly 11 selects one (or a subset) of the microphones 202, 204, 206, 208, 210 in the microphone array 200 based on an identification of a primary human speaker and / or its location.

[0054] For example, as previously described, the controller 18 may determine that the third person 44 is the primary human speaker based on a body language detection algorithm that processes data indicating an image or video feed received from the camera 26. Various body languages ​​(such as facial expressions, hand gestures, head postures, body postures, body movements, body orientations, body positions) may be detected and indicate a primary human speaker. Based on the detection of the third person 44 as the primary human speaker and the positioning of the third person 44, the controller 18 may select the third microphone 206 from the microphone array 200 based on the proximity, position, or orientation of the third microphone 206 relative to the third person 44 (or its positioning). For example, the first microphone 202 may correspond to the positioning of the first person 40, the second microphone 204 may correspond to the positioning of the second person 42, the third microphone 206 may correspond to the positioning of the third person 44, the fourth microphone 208 may correspond to the positioning of the fourth person 46, and the fifth microphone 210 may correspond to the positioning of the fifth person 48. However, it should be noted that the number of microphones in the microphone array 200 may be different from the number of people in the human group 50 located in the stage area 38.

[0055] In general, the microphones in the microphone array 200 are selected based on the primary human speaker and / or the location of the primary human speaker. The controller 18 may then receive data from the selected microphone 206 and determine the command issued by the primary human speaker (e.g., the third person 44) based on the data. In some embodiments, the unselected microphones 202, 204, 208, 210 may be disabled, unpowered, or otherwise controlled so that the controller 18 does not receive and / or does not consider data from the unselected microphones 202, 204, 208, 210. In this way, environmental or other noise (e.g., from the first person 40, the second person 42, the fourth person 46, and the fifth person 48) may be excluded so as not to interfere with the target audio captured by the third microphone 206. It should be noted that in some embodiments, a subset of the microphones 202, 204, 206, 208, 210 may be selected based on the identification of the primary human speaker. For example, in response to determining that the third person 44 is the primary human speaker, the controller 18 may receive data from the second microphone 204, the third microphone 206, and the fourth microphone 208, while excluding data from the first microphone 202 and the fifth microphone 210. It should also be noted that the microphones 202, 204, 206, 208, 210 of the microphone array 200 may be directional microphones or shotgun microphones. Further, the microphones 202, 204, 206, 208, 210 may be suspended or facing forward so that they are directed toward the stage area 38 without interfering with the performance attraction 10 and the corresponding customer experience. Other aspects of the illustrated performance attraction 10 (e.g., show lights 28, additional microphones 30, show props 34 and track 52, electronic screen 35, and unique indicators 39) may be connected to the stage area 38. Figure 1 , 2 The embodiment illustrated in FIG3 may be operated the same or similarly.

[0056] Figure 7 It is a graphic control Figure 6 Flowchart of an embodiment of a method 250 for identifying a primary human speaker, selecting a microphone from a microphone array corresponding to the primary human speaker, and controlling a performance element of the performance attraction. In the illustrated embodiment, the method 250 includes receiving (block 252) via a controller and from a camera data indicating an image or video feed capturing a human group. Block 252 may be associated with Figure 5 The method 250 also includes determining (block 254) a primary human speaker (and its location) among the human group via a body language detection algorithm executed by the controller and receiving data indicative of the image or video feed. Block 254 may be similar to block 152 in the method 150 illustrated in FIG. 1 and described in detail above. Figure 5The method 250 also includes controlling (block 256) the configuration of the performance elements of the performance attraction via the controller based on the identification of the primary human speaker, the location of the primary human speaker, or both. Block 256 may be the same as or similar to block 154 in the method 150 illustrated in FIG. 1 and described in detail above. Figure 5 The same or similar to block 156 in method 150 illustrated in FIG. 1 and described in detail above.

[0057] The method 250 also includes selecting (block 258), via the controller, and from the microphone array, a microphone (or a subset of microphones) corresponding to the detected primary human speaker. For example, as previously described, the microphone array may have a plurality of microphones pointed at various known locations of a stage area in which the human group resides. Based on an identification of the primary human speaker (and its location) among the human group, the controller may select the microphone corresponding to the primary human speaker. Other microphones of the microphone array (e.g., unselected microphones) may be disabled or otherwise excluded. Accordingly, the controller receives and processes audio captured by the selected microphone corresponding to the primary human speaker (or its location), which may capture a relatively small amount of ambient noise (e.g., relative to the other unselected microphones of the microphone array).

[0058] The method 250 also includes receiving (block 260), at the controller and from the selected microphone, data indicating sounds captured by the selected microphone. As previously described, the sounds captured by the selected microphone may correspond primarily to sounds produced by the primary human speaker, while ambient noise may be excluded and / or recorded at a relatively low intensity. The method 250 also includes determining (block 262), via the controller and based on the data indicating sounds captured by the selected microphone, commands issued by the primary human speaker. As previously described, the controller may execute a speech recognition algorithm that determines commands issued by the primary human speaker based on the data indicating sounds captured by the selected microphone. The method 250 also includes controlling (block 264), via the controller, a performance element based on the commands. Block 264 may be associated with Figure 5 The same or similar to block 164 in method 150 illustrated in FIG. 1 and described in detail above.

[0059] Figure 8302 (e.g., a conference room, a reception room, an auditorium, or some other place where a conference call or similar event is held). The conference call system 300 includes a control assembly 304 configured to identify a primary human speaker among a human group 306 and select a microphone 310 corresponding to the primary human speaker from a microphone array 308. The microphone array 308 may be referred to as a microphone assembly in certain examples of the present disclosure. The control assembly 304 also includes the microphone array 308, a camera assembly 312 (e.g., including one or more cameras) configured to capture video or images within the place 302, a controllable media device 314 (e.g., a television, a projector, a computer, a speaker, or any combination thereof), and a controller 316.

[0060] Controller 316 includes processor 318 and memory 320. Memory 320 includes instructions thereon that, when executed by processor 318, cause processor 318 to perform various functions. For example, controller 316 is configured to receive data from camera assembly 312 indicating an image or video feed captured by camera assembly 312. Further, controller 316 is configured to execute the body language detection algorithm described in detail above to determine a primary human speaker from group of humans 306 in place 302. In the illustrated embodiment, group of humans 306 includes thirteen persons 322, 324, 326, 328, 330, 332, 334, 336, 338, 340, 342, 344, 346. Seventh person 334 is identified as a primary human speaker based on a waving gesture identified by controller 316 (e.g., via the body language detection algorithm) as indicating a primary human speaker.

[0061] In response to determining that the seventh person 334 is the primary human speaker, the controller 316 may select the microphone 310 corresponding to the seventh person 334 (or its location) from the microphone array 308. In fact, the microphone 308 in the illustrated embodiment includes twelve microphones 310, 348, 350, 352, 354, 356, 358, 360, 362, 364, 366, 368 located at different locations and / or oriented in different directions. The controller 316 may select the microphone 310 from the microphone array 308 based on the proximity of the microphone 310 to the primary human speaker (e.g., the seventh person 334) and / or the directionality of the microphone 310 relative to the primary human speaker. Therefore, the controller 316 may receive data indicating the audio captured by the microphone 310, while excluding data indicating the audio captured by the unselected microphones 348, 350, 352, 354, 356, 358, 360, 362, 364, 366, 368. In this way, data indicative of audio received by controller 316 (e.g., from microphone 310 ) can highlight the sound generated by the primary human speaker (e.g., seventh person 334 ) as opposed to ambient noise generated by other members of human group 306 and / or other sources of sound in venue 302 .

[0062] In the illustrated embodiment, the number of microphones in the microphone array 308 is different from the number of people in the human group 306. However, the number of microphones in the microphone array 308 may be the same as the number of people in the human group 306. Further, in accordance with the present disclosure, each of the microphones 310, 348, 350, 352, 354, 356, 358, 360, 362, 364, 366, 368 in the microphone array 308 may be part of a corresponding larger device (such as a computer, mobile phone, or laptop computer) that is communicatively coupled to the controller 316. For example, in an embodiment, the selected microphone 310 may be part of a laptop computer corresponding to the seventh person 334 identified as the primary human speaker. Still further, the camera assembly 312 may include a plurality of cameras associated with respective larger devices (e.g., computers, mobile phones, laptop computers) corresponding to the human group 306. In this way, the control assembly 304 may include devices corresponding to the human group 306, wherein each device includes a corresponding microphone of the microphone array 308 and a camera of the camera assembly 312. Further, in some embodiments, the teleconference system 300 can be used to broadcast a teleconference to various devices (e.g., computers, laptops) over a network. Thus, the audio captured by the selected microphone 310 (or a subset of microphones) can be broadcast to various connected devices via the network.

[0063] According to the present disclosure, the controller 316 may be communicatively coupled to the media device 314 and configured to control the media device 314 based on the audio captured by the selected microphone 310. For example, the media device 314 may include a speaker configured to amplify the audio captured by the microphone 310 and received by the controller 316. Further, the media device 314 may correspond to a computer or laptop computer connected to the teleconference system 300 from a location (e.g., via a network) away from the venue 302, and the audio captured by the selected microphone 310 may be played through the speaker of the media device 314 at the remote location. Additionally or alternatively, the controller 316 may determine the command issued by the primary human speaker based on the audio captured by the microphone 310. As previously described, a speech recognition algorithm may be used to determine the command. In one embodiment, the command may correspond to the desired control of the media device 314. For example, the media device 314 may include a projector or television on which a presentation is presented. Controller 316 may control media device 314 to change slides or pages of the presentation, initiate video or other graphics associated with the presentation, or otherwise control the presentation based on commands issued by the primary human speaker.

[0064] The above-described systems and methods may provide technical benefits over conventional systems and methods. For example, the presently disclosed performance attraction systems and methods may enable improved interaction between a group of patrons (e.g., a particular audience member in the group of patrons) and a performance element of a performance attraction relative to conventional systems and methods. Further, the presently disclosed systems and methods may enable improved audio capture of commands from one or more patrons in the audience, which reduces inaccurate interactions through inaccurate performance element controls, reduces processing resources (e.g., complexity and cost) required to determine commands issued by the one or more patrons in the audience (thus, thereby improving related computing operations), and improves the customer experience.

[0065] Although only certain features have been illustrated and described herein, many modifications and changes will occur to those skilled in the art. It is, therefore, to be understood that the appended claims are intended to cover all such modifications and changes as fall within the true spirit of the disclosure.

[0066] The technology presented and claimed herein is cited and applied to specific examples and substantial objects that arguably improve the practical nature of the art, and as such is not abstract, intangible, or purely theoretical. Further, if any claim appended to the end of this specification contains one or more elements designated as "means for [performing] ... [function]" or "steps for [performing] ... [function]," it is intended that such elements be interpreted in accordance with 35 U.S.C. 112(f). However, for any claim containing elements designated in any other manner, it is intended that such elements not be interpreted in accordance with 35 U.S.C. 112(f).

Claims

1. A system comprising: Gimbal; a shotgun microphone coupled to the gimbal; camera; as well as at least one processor configured to: receiving data indicative of an image or video feed from the camera; determining a primary human speaker among a human group and a location of the primary human speaker based on the data indicative of the image or video feed; and The gimbal is controlled to point the shotgun microphone toward the location of the primary human speaker.

2. The system of claim 1, comprising an electronic screen configured to output a digital avatar, wherein: The at least one processor is configured to: determining a characteristic of the digital avatar based on identification of the primary human speaker, the location of the primary human speaker, or both; and The electronic screen is controlled to output the digital avatar having the characteristics.

3. The system of claim 1, comprising a performance element actuatable between a plurality of performance element positions, wherein: The at least one processor is configured to: determining a performance element position from among said plurality of performance element positions based on identification of said primary human speaker, said location of said primary human speaker, or both; and The performance element is actuated to the performance element position.

4. The system of claim 1 including a stage area having a plurality of locations including the location of the primary human speaker and additional locations of secondary persons among the human group, wherein The at least one processor is configured to determine the primary human speaker by excluding the secondary persons based on the data indicative of the image or video feed.

5. The system of claim 1 , wherein the at least one processor is configured to determine the primary human speaker and the location of the primary human speaker based on the data indicative of the image or video feed by: executing a body language detection algorithm to analyze said data indicative of said image or video feed; identifying the primary human speaker as a result of executing the body language detection algorithm to analyze the data indicative of the image or video feed; as well as Responsive to identifying the primary human speaker, the location of the primary human speaker is determined.

6. The system of claim 5, wherein: The at least one processor is configured to execute the body language detection algorithm to identify a gesture indicative of the primary human speaker based on the data indicative of the image or video feed.

7. The system of claim 5, wherein: The at least one processor is configured to execute the body language detection algorithm to identify a facial expression indicative of the primary human speaker based on the data indicative of the image or video feed.

8. The system of claim 1, wherein: The at least one processor is configured to: After determining the location of the primary human speaker, controlling the gimbal to direct the shotgun microphone toward the location of the primary human speaker; And then receiving, via the shotgun microphone, data indicative of sound captured by the shotgun microphone; determining, based on the data indicative of the sound captured by the shotgun microphone, a command issued by the primary human speaker; as well as The commands are executed by controlling the performance elements of the system.

9. The system of claim 8, wherein: The at least one processor is configured to execute the commands by controlling characteristics of a digital avatar displayed on an electronic screen corresponding to the performing element of the system.

10. The system of claim 1, wherein: The gimbal includes a motor, and the at least one processor is configured to control the gimbal to point the shotgun microphone toward the location of the primary human speaker by controlling the motor of the gimbal.

11. A system comprising: Microphone assembly; camera; as well as at least one processor configured to: receiving data indicative of an image or video feed from the camera; determining a primary human speaker among a human group and a location of the primary human speaker based on the data indicative of the image or video feed; and The microphone assembly is controlled based on the positioning of the primary human speaker.

12. The system of claim 11, wherein: The microphone assembly includes a gimbal and a shotgun microphone coupled to the gimbal, and the at least one processor is configured to control the microphone assembly based on the location of the primary human speaker by controlling the gimbal to point the shotgun microphone toward the location of the primary human speaker.

13. The system of claim 12, wherein: The gimbal includes a motor and the at least one processor is configured to control the motor of the gimbal to point the shotgun microphone toward the location of the primary human speaker.

14. The system of claim 11, wherein: The microphone assembly comprises a microphone array, and the at least one processor is configured to: identifying, from the microphone array, a first microphone that does not correspond to the location of the primary human speaker; and The first microphone is deactivated.

15. The system of claim 14, wherein: The at least one processor is configured to: identifying, from the microphone array, a second microphone corresponding to the location of the primary human speaker; and Data indicative of audio captured by the second microphone is received from the second microphone.

16. The system of claim 11, comprising a speaker, wherein: The at least one processor is configured to: receiving, from the microphone assembly, data indicative of audio captured by a microphone of the microphone assembly; as well as The speaker is controlled to output the audio.

17. The system of claim 11, comprising an electronic screen, wherein: The at least one processor is configured to: receiving, from the microphone assembly, data indicative of audio captured by a microphone of the microphone assembly; as well as Based on the data indicative of the audio captured by the microphone of the microphone assembly, a visual presentation displayed on the electronic screen is controlled.

18. One or more tangible, non-transitory computer-readable media comprising instructions thereon that, when executed by at least one processor, cause the at least one processor to: receiving data from a camera indicating an image or video feed capturing a human group; determining, via a body language detection algorithm receiving said data indicative of said image or video feed, a primary human speaker and a location of said primary human speaker; controlling a motorized gimbal to direct a shotgun microphone toward said location of said primary human speaker; receiving, via the shotgun microphone, data indicative of sound captured by the shotgun microphone; determining, based on the data indicative of the sound captured by the shotgun microphone, a command issued by the primary human speaker; as well as Performance elements are controlled based on the commands.

19. The one or more tangible, non-transitory computer-readable media of claim 18, wherein: The instructions, when executed by the at least one processor, cause the at least one processor to control the performance element or additional performance elements based on identification of the primary human speaker, the location of the primary human speaker, or both.

20. The one or more tangible, non-transitory computer-readable media of claim 19, wherein: When the instructions are executed by the at least one processor, the at least one processor: controlling a first characteristic of the performance element based on the identification of the primary human speaker, the location of the primary human speaker, or both; A second characteristic of the performance element is controlled based on the command, so that the performance element includes both the first characteristic and the second characteristic.

Images