437 results about "Mouth lips" patented technology

The invention provides a virtual digital population type synchronization method, system and device, a medium and a program product, and the method comprises the following steps: analyzing an input voice signal, and obtaining a voice feature; taking the voice features as input of a lip movement prediction model, and predicting corresponding lip movement parameters; driving a face model of the virtual digital human to perform real-time rendering according to the lip movement parameters, and realizing fine movement control of lips; and obtaining user feedback data, and continuously optimizing and adjusting the lip movement prediction model based on the user feedback data. Through advanced technologies such as deep learning, voice analysis and lip movement prediction, accurate synchronization of the virtual digital population type and the voice content is realized, and the expression ability of the virtual character and the user interaction experience are improved.

Systems and methods for generating speaker video and audio in multiple languages for videoconferencing are provided. For example, a computing device can access a speaker speech audio signal that includes a speaker speech in a first language, a video of the speaker and a translated speech audio signal of the speaker speech in a second language. The computing device generates, based on the translated speech audio signal, a converted translated speech audio signal that includes a speech in the second language having voice characteristics in the speaker speech. The computing device further generates a lip-synched speaker video based on the video of the speaker and the converted translated speech audio signal. Lip movements in the lip-synched speaker video correspond to the converted translated speech audio signal. The converted translated speech audio signal and the lip-synched speaker video are transmitted to a video conference provider configured to host the video conference.

A container system is disclosed herein. The container system may include a body and a liner. The liner may be removably inserted into a recess of the body. The body may include a lip extending around the recess a distance from an opening to the recess. The liner may include a rim configured to contact the lip of the body when the liner is inserted into the recess. The liner may be configured to be turned inside out.

Introduced here are systems and methods to increase accuracy of speech recognition by utilizing multiple sensors placed at multiple speech transmission regions such as a user's lips, throat, ear canal, etc. The various speech transmission regions are better at transmitting certain phonemes, and a sensor placed close to a particular speech transition region can more accurately detect the phoneme transmitted through the particular speech transmission region. For example, a microphone placed close to the lips can better detect labial phonemes such as m, n, p, and b, than a microphone placed close to the throat. Further, disclosed here are ways to reduce energy consumption while performing speech recognition.

The invention relates to the technical field of bionic humanoid robots, in particular to a multi-expression driving bionic intelligent robot head which comprises an eyebrow movable layer, a cheekbone movable layer, an eye movable layer, an upper lip movable layer and a chin movable layer located below the upper lip movable layer, and the eyebrow movable layer, the cheekbone movable layer, the eye movable layer and the upper lip movable layer are spliced and assembled by hexagonal threaded copper columns through reserved hole positions. The robot head is composed of a shell, an aluminum alloy machining plate frame, a CNC metal part, a steering engine, a rail and a pull wire, and a camera module and a voice control module are arranged in the robot head. The shell can be customized according to different figure facial features, the shell is of a high-precision, compact and adjustable structure, 26 steering engines are integrated in a limited space to control opening and closing of the face including left and right eyeballs, upper and lower eyelids, canthus, eyebrows, cheeks, mouth corners and mouth and actions of lips, and the layered design and control mode of the head of the robot enable the robot to be more intelligent. And the mounting, the dismounting and the maintenance are more convenient.

A seal including: an annular jacket including a heel, a first lip, and a second lip defining an annular recess; and an insert including at least 3 prongs disposed within the annular recess contacting the heel, the first lip, and the second lip.

The invention discloses a human face mouth shape coordination generation method based on geometric constraints, and relates to the technical field of image generation, and the method comprises the steps: 1, synchronously generating face vertex index tables corresponding to mouth opening and closing spatial form matrixes one by one; 2, based on the facial vertex index table, mapping the lip and gum combined boundary constraint set to a unified coordinate system to form a geometric prior constraint tensor; 3, performing multi-modal topological cascade reversible mixed transformation on the geometric prior constraint tensor to obtain a high-dimensional tooth texture candidate tensor and constraint consistency confidence spectrum; and step 4, using the high-dimensional tooth texture candidate tensor and the constraint consistency confidence spectrum as input, completing anti-aliasing, illumination compensation and gamma correction on a unified rendering pipeline, and finally obtaining a mouth shape coordination synthetic frame sequence. According to the method, the sense of reality, geometric consistency and time sequence coherence of tooth textures in the mouth shape synthesis process are effectively improved, and the problem that lips and teeth are not coordinated in an existing method is solved.

The invention relates to the technical field of oral cavity detection, in particular to an oral cavity detection expanding device which comprises a connecting block, at least four expanding rods are universally connected to one side of the connecting block, the multiple expanding rods are divided into two groups, the ends, away from the connecting block, of the multiple expanding rods in one group are connected with the same expanding assembly, and the connecting block is connected with the expanding assembly. Expanding assemblies are correspondingly connected between the two groups of expanding support rods, the two groups of expanding support rods are used for abutting against teeth, and the two expanding assemblies are used for expanding lips. The oral cavity of a patient can be expanded according to actual operation conditions, so that detection is facilitated.

A water stop member includes an annular main body that is coaxially brought into contact with an annular wall surface on a circumference portion side of a through-hole of a flange of a base member, an annular outer circumferential lip that is protruded toward the circumference portion, bend-deforms at the attachment completion position, and is brought into close contact with an annular plane of the circumference portion over one circumference, and an annular inner circumferential lip protruded toward the circumference portion in such a manner as to get closer to a hole axis of the through-hole as coaxially getting closer to the circumference portion from an inner circumference portion side than the outer circumferential lip of the main body, bend-deforms at the attachment completion position, and is brought into close contact with the annular plane side of the circumference portion over one circumference.

Methods and devices including a skin or a lip and more particularly methods and devices that enhances absorption of fluid treatment media into tissue for cosmetic and therapeutic purposes.

The invention discloses a digital human voice lip synchronization method based on an adversarial texture enhancement network. The method comprises the following steps: acquiring input audio and video data, extracting audio features by adopting a Wav2Lip model, and realizing preliminary audio and video alignment; performing dynamic modeling on the extracted lip key point sequence by adopting a graph neural network (GCN) so as to capture the time consistency of lip movement; performing texture detail enhancement on the lip region image by using a generative adversarial network (GAN), and introducing an edge perception loss function to optimize the contour definition of the lip region; through a multi-modal fusion strategy, audio and visual features are subjected to joint alignment, and the accuracy of sound and lip synchronization is enhanced; and constructing an audio and video feature consistency evaluation module, and judging and optimizing the generated lip image region. According to the method, the authenticity of the lip movement of the digital human is improved, so that the lip movement better conforms to a real voice expression mode, and the method can be widely applied to the fields of virtual human video generation, film and television post-processing, game role animation, intelligent customer service and the like.

The invention relates to the field of tongue image viscera partitioning, and discloses a traditional Chinese medicine tongue image viscera partitioning method based on edge detection, and the method comprises the steps: collecting a tongue image through a built-in high-definition camera of a tongue diagnosis instrument; in order to avoid interference of other parts such as the face and the lip on tongue picture analysis, on the basis of manually marking a tongue body image area, a DeeplabV3 + semantic segmentation model is used to separate the tongue from the background; automatic batch processing is carried out through a customization algorithm, and after the tongue body is segmented and processed, the minimum bounding rectangle of the tongue body is determined; detecting the upper, lower, left and right edges of the tongue, determining left and right boundary points and top and bottom boundary key points of the tongue in the image, and drawing four tangent lines according to the edge form; and by taking the tangent line as a boundary, creating a mask according to a corresponding polygonal region, and completing region division and extraction. The method has the advantages that the problem that a traditional rectangular partitioning rule is insufficient in adaptability to the tongue shape is solved, the accuracy is higher, and the partitioning result is more reliable.

Examples relate to systems and methods for generating an avatar animation. The systems and methods access an audio file comprising speech, spoken by a user, captured by a microphone of a user system, and receive input that selects an avatar associated with the user. The systems and methods process the audio file and the avatar, selected by the received input, by a generative machine learning model to generate an animation of the avatar having lips moving to represent the avatar speaking the speech of the audio file. The systems and methods generate a video comprising a depiction of the generated animation of the avatar speaking the speech of the audio file.

The present disclosure relates to a solid cosmetic make-up composition of a keratin material, in particular the skin and / or the lips, comprising at least one pigment, and at least one cavity such that the composition has a porosity of greater than or equal to 20% by volume relative to the total volume of the solid composition, as well as to associated production methods.

The invention discloses a human head facial expression imitating robot and a mouth pouting mechanism integrated system device and a control method thereof, and relates to the field of human head facial expression imitating robots. The technical problems that an existing human head and face imitating robot is difficult to achieve by purely depending on the skin, the lips and a driving mechanism of the lips through pouting actions and incomplete in basic emotion expression when facial expressions and emotion behaviors are not full in emotion expression and the like are solved. According to the technical scheme, the device is composed of driving mechanisms for the orbicular orbicular muscle, the masseter muscle, the laughing muscle, the buccal muscle, the anorbital horn muscle, the chin muscle, the anorbital lower lip muscle, the zygomatic muscle, the zygomatic small muscle and the like which simulate the human face skin mouth and the periphery of the human face skin mouth, and the orbicular orbicular muscle driving mechanism is used for achieving the angular distortion action behavior main body. When the driving mechanisms for realizing actions such as cheeks and chin realize the active pouting action, the pouting action is realized by coordinating according to the principle of a facial expression coding system and cooperating with the motion of the orbicular orbicular muscle driving mechanism of the pouting action action. The orbicular orbicular muscle driving mechanism system comprises a soft rope which is pre-embedded in the orbicular orbicular muscle area of the simulated human face skin or connected to the back of the orbicular orbicular muscle area of the simulated human face skin, an elastic steel wire which is pre-embedded in the lip of the simulated human face skin or connected to the back of the lip, and a corresponding rope; the micro-miniature integrated servo motor and the driving and control unit of the micro-miniature integrated servo motor are arranged on the base; the micro-miniature integrated servo motors are all servo motors with position and speed sensors and planetary reducers.

The utility model relates to the technical field of robots, in particular to a mouth corner movement mechanism and a mouth device which are used for driving mouth corners of a robot to move. Comprising a first motor, a first connecting rod assembly, a second motor and a second connecting rod assembly; the input end of the first connecting rod assembly is connected to the output end of the first motor; the input end of the second connecting rod assembly is connected with the output end of the second motor. The output end of the second connecting rod assembly is rotationally connected with the output end of the first connecting rod assembly. The output end of the first connecting rod assembly is connected with the mouth corner through the connecting assembly and / or the output end of the second connecting rod assembly is connected with the mouth corner through the connecting assembly. By adopting the mode that the two motors are matched with the connecting rod for driving, one mouth corner of the lips can be driven to move up and down, forwards pushed, backwards pulled and the like, so that the mouth corner movement is more flexible and diversified.

The invention relates to a multifunctional micro-robot and method for precisely positioning cleft lip and palate repair surgery, and belongs to the technical field of medical auxiliary instruments. Comprising a pillow arranged at one end of a bed body, a supporting frame is inserted into the pillow in a damping mode, an extension block is fixedly arranged on one side of the supporting frame, a displayer is arranged on the extension block, a connecting frame is fixedly arranged on one side of the extension block, two lifting rods are adjustably arranged on the connecting frame, and electric push rods are fixedly arranged at the bottom ends of the lifting rods. The outer wall of the electric push rod and the output end of the electric push rod are each provided with a clamping plate used for clamping the lips. By means of the ingeniously-designed clamping plates, turning mechanisms, limiting columns, lifting adjusting mechanisms and the like, precise clamping and turning of lips are achieved, the comfort level and safety of an operation are greatly improved, meanwhile, powerful support is provided for sanitary guarantee of the operation due to the addition of the disinfection and cleaning functions, and the operation safety is improved. And smooth proceeding of an operation and rapid rehabilitation of a patient are ensured.

The present disclosure relates to a solid cosmetic composition for perfuming a keratin material, in particular the skin and / or the lips, comprising at least one perfuming agent, and one cavity, such that the composition has a porosity of greater than or equal to 20% by volume relative to the total volume of the solid composition, as well as to associated production methods.

To provide an oral training device that can simultaneously train tongue muscles and lip muscles.SOLUTION: An oral training device 2 comprises: a tongue training member 4 located above a tongue 12 of a user; a lip training member 6 connected to the tongue training member 4, and located between teeth 14 and lips 16 of the user; and a partition member 8 located between the teeth of an upper jaw and the teeth of a lower jaw of the user. The tongue training member 4 and the lip training member 6 are made hollow, and filled with fluid therein. When the tongue training member 4 is compressed, the fluid in the tongue training member 4 moves into the lip training member 6, and the lip training member 6 expands.SELECTED DRAWING: Figure 3

A therapeutic device with a breathing tool and a fidget spinner that can rotate, where the fidget spinner is attached to the breathing tool. The breathing tool has a proximal end with an opening that allows air to pass through an air passage and the proximal end can be enclosed in the lips of a person and allows the person to pass breathing air through the opening. The fidget spinner may encircle the air passage. The breathing tool may include: a top portion having a receiving passage; and a bottom portion with an end section adjacent to a narrow section. The fidget spinner may be adapted to rotate about the narrow section, and the end section can be received within the receiving passage of the top portion. The breathing tool, narrow section, end section, top portion, and the receiving passage of the top portion may have a cylindrical shape.

To provide a novel system for evaluating human vocalization.SOLUTION: A system comprises at least one computer device. The system comprises specification means that uses a machine-learned prediction model that takes video information containing images of a person's lip during vocalization, or information regarding the position of a specified point on an image of a person's lip during vocalization as input information, and takes evaluation information related to the vocalization as output information so as to identify evaluation information related to the user's vocalization based on video information containing an image of the user's lip at the user's vocalization, or information related to the position of predetermined point on an image of the user's lip at the user's vocalization.SELECTED DRAWING: Figure 5

A protective case for use with an electronic device includes a cavity for receiving the electronic device and an aperture permitting access to a touchscreen interface of the electronic device. The protective case also includes an attachment interface for attaching an accessory to a back of the protective case. The attachment interface has an insertion region having a first width and an attachment region having a second width that is smaller than the first width. The attachment region includes lips on opposing sides of the attachment region. The lips are configured to removably retain the accessory after the accessory is inserted into the insertion region of the attachment interface and moved to the attachment region of the attachment interface.

The utility model discloses a reciprocating type shaver head which comprises an arc-shaped shaver net and a shaver net fixing frame, the arc-shaped shaver net is formed by bending a plane shaver net through an upper die and a lower die of a die with the transverse section being in a full circle R and the longitudinal section being in an oval shape, and the longitudinal section of the top of the arc-shaped shaver net is in an oval shape or a parabola R or a non-full circle R; the transverse section of the top of the arc-shaped cutter net is a full circle R, the left and right sides of the vertex are nonlinear, and the lower end of the arc-shaped cutter net is connected with the cutter net fixing frame to form an arc-shaped nonlinear cutter head. According to the reciprocating type shaver head, the arc-shaped shaver net (the whole circle of the transverse section is R, and the longitudinal section is oval) is directly bent and shaped on a mold, the periphery of the arc-shaped shaver net is wrapped into an arc shape through injection molding, skin cannot be blocked when a sunken area of the jaw or the lip edge is trimmed, trimming is clean, efficiency is high, experience feeling is good, technical mold machining is simple, and cost is low.

A Kiddush cup assembly is disclosed. The assembly comprises(a) a Kiddush cup comprising a Kiddush fluid and having a first cover being configured to avoid damaging a lip, wherein the first cover is not stuck to the lip using an adhesive;(b) a container for containing an additional Kiddush fluid; and(c) at least one tampering reporting mechanism for disqualifying the Kiddush cup assembly when tampered.

The invention relates to the field of intelligent speech recognition, in particular to a spoken English pronunciation correction auxiliary system based on speech recognition, which comprises a data acquisition module, a speech recognition module, a pronunciation analysis module and a pronunciation correction module, according to the visual motion feature extraction method based on dimension fusion and feature simplification, dynamic motions and subtle changes of lips are captured, text semantics corresponding to detail features of lip motions of standard pronunciation are accurately recognized, the number of channels is increased on the basis of dimension reduction, deeper and finer lip visual information is captured, and the lip motion feature extraction efficiency is improved. More accurate lip action guidance is provided for pronunciation correction; according to the method, understanding and recognition of lip actions are guided through semantic features, a multi-head self-attention mechanism is introduced to optimize the semantic features, the incidence relation between the lip actions and voice texts is captured, and corresponding position codes are added, so that the model understands the pronunciation sequence of the oral text in the lip actions, and the lip actions can be recognized. And more accurate lip action guidance is realized.

The utility model discloses a convenient spoon based on baby dining, and relates to the technical field of spoons, the convenient spoon comprises a handle, the inner wall of the handle is slidably connected with a push rod, the left side of the push rod is fixedly connected with a push plate, the right side of the handle is fixedly connected with a spoon body, and the inner wall of the spoon body is provided with a cavity. An air bag skin is fixedly connected to the inner surface of the spoon body, the main material of the air bag skin is nylon, the expansion mechanism comprises an air pipe fixedly connected to the bottom end of the inner wall of the handle, and a second piston plate is slidably connected to the inner wall of the air pipe. Meanwhile, air on the inner wall of the air pipe is pushed out from the arc-shaped opening and enters the inner cavity of the spoon body communicated with the handle, the air pressure of the spoon body is large, the air bag skin is pushed upwards, and when the cavity is filled with the air, the spoon body is changed into a round shape, so that the situation that the upper lip of the baby is injured by friction due to bad introduction of the spoon is prevented.

A mouth or lip guard for placement over the lid or rim of a can or container prior to consumption to establish a sanitary barrier between a drinker's contact points of mouth, and more specifically lips, and the lid, rim, and / or sidewalls of the beverage can or other container and with a straw capture and alignment port having a slit dividing the planar tab into a first tab section and second tab section, the first tab section having a first straw contact finger configured therein and the second tab section having a second straw contact finger configured therein, each straw contact finger separated by said slit, the straw contact fingers are hingeably configured to removably secure the straw against a straw contact rim formed in the planar tab by a cutout of said first straw contact finger and said second straw contact finger.

The invention discloses a target positioning method and device, video conference equipment and a storage medium, and relates to the technical field of target positioning, and the method comprises the steps: obtaining the position information of human voice; adjusting an image acquired by a lens according to the position information; acquiring a plurality of lip key points of at least one face image of the image, and processing the plurality of lip key points based on a pre-trained lip movement recognition model to determine a lip state of the face image; wherein the lip state comprises a moving state and a static state; when it is determined that the lip state of the at least one face image is a motion state, determining that at least one spokesman exists in the image, and controlling a lens to obtain a close-up picture of the spokesman; the objective of the invention is to solve the technical problem that the existing tracking camera is low in spokesman recognition precision.

The present invention relates to a cup lid comprising: a main lid body for attachment to a cup body, the main lid body having a first opening formed thereon, the first opening providing a first path for attachment to the inside of the cup body when the main lid body is attached to the cup body; the sucking part is installed on the main cover body, the sucking part extends upwards and is in a C shape facing the first opening, a second opening is formed in the sucking part, and when the main cover body is attached to the cup body, the second opening provides a second path attached to the interior of the cup body; wherein a horizontal interval is formed between the first opening and the sucking part, the first opening is located at a low position, and the second opening is located at a high position, so that when the cup body is inclined for direct drinking, the horizontal interval is converted into a high-low fall surface capable of reducing water flow impact, and the lip cannot cover the whole sucking part and the first opening at the same time, so that gas circulation in the direct drinking process is met. Through the cooperative design of the first opening, the second opening and the sucking part, different drinking requirements of sucking, small-amount direct drinking, large-amount direct drinking and the like can be met.