41 results about "Teleconference" patented technology

Techniques for transcribing and / or summarizing multimedia collaboration sessions are discussed herein. For example, users can communicate within a teleconferencing meeting associated with a channel. In some examples, a first machine learning model may be configured to receive audio-visual data and user interaction data (e.g., selected emojis, detected gestures, messages or text input by a user, a thread of messages, etc.) and output a teleconferencing meeting summary. In some examples, the teleconferencing meeting summary can include one or more highlights, action items, and / or artificial intelligence (AI) notes generated using a machine learning model(s).

A method of setting up a teleconferencing system using mobile devices is disclosed. Participants with mobile devices in multiple rooms may communicate based on the disclosed teleconferencing application executed on the mobile devices. Each room has one of the mobile devices designated as a leader device for that room. The leader devices may communicate using VoIP over the Internet. Other mobile devices in a room are designated as client devices associated with the leader devices. Participants operating the client devices can talk to other participants in that room and the other rooms through the client device communicating through the leader device of the room. The leader device synchronizes the playing of received audio between all of the client devices in the room. The leader device includes a selection algorithm that selects one of the devices to act as the microphone for audio signals generated in the room.

The invention relates to the technical field of intelligent contracts, and discloses an intelligent contract safety generation and risk insight method fusing a large language model and a digital signature, and the method comprises the steps: firstly obtaining a telephone conference voice, carrying out the telephone band processing, and carrying out the system sound interference suppression, and obtaining a purified signal; positioning a short near-end fragment based on the purification signal, extracting an energy peak moment, and setting an early window and a late window; estimating a fundamental frequency in the early window and constructing a harmonic set, calculating a normalized double-coherence intensity set average value of the early window and the late window, constructing a characteristic index and forming a time-varying gating weight field through monotone mapping; obtaining a word-level timestamp through automatic speech recognition, and calculating word availability in combination with a gating weight field; extracting an offer of the speaker A, collecting response words of the speaker B in a preset time window, and calculating response reliability according to word availability and time closeness; and generating a clause draft, judging whether the clause draft is included in the first draft of the contract, and outputting risk clauses of the contract draft.

Described herein are methods, systems, devices, and processor readable storage devices for use during a teleconference among a plurality of users that each uses a respective device, of a plurality of devices, to participate in the teleconference. Certain such embodiments use positional information to cause displaying, by a device that is provided with the positional information, of a respective graphical indicator that indicates where a region of interest is within or relative to the viewport that is being displayed on the device.

Systems and methods are provided for identifying polling questions from a conference call discussion. One or more text strings are identified, the one or more text strings comprising a textual form of one or more spoken phrases provided by one or more participants of a conference call. The one or more text strings are provided as input to a trained machine learning model. One or more outputs are obtained from the trained machine learning model. A spoken phrase of the one or more spoken phrases provided by the one or more participants is extracted from the one or more outputs that comprises a confidence level that a question associated with a poll during the conference call. In response to a determination that the confidence level satisfies a confidence criterion, the spoken phrase is designated as a polling question presented during the conference call.

A telephone conferencing system capable of conducting telephone conferences smoothly is provided. According to the invention, a speech determination unit (2) determines whether the speech of each participant in a telephone conference is a statement or an interruption. A speech output control unit (4) performs control such that the speeches of the multiple participants are output to the communication terminals of the multiple participants respectively. When another participant speaks while one of the multiple participants is speaking, the speech output control unit (4) performs control to suppress the output of the other participant's speech. A counting unit (6) counts the number of speech conflicts for each participant. A count display control unit (8) performs control such that a display related to the count is displayed on the communication terminals of the multiple participants.

The utility model relates to the technical field of teleconferences, and provides a teleconference system, which comprises a rotating support, an acquisition support is fixedly mounted in the rotating support, an acquisition camera for face recognition and information acquisition is fixedly mounted in the acquisition support, and a camera is fixedly mounted in the acquisition camera. A laser distance measuring sensor for detecting the position of the acquisition camera is arranged on one side of the acquisition camera; the utility model has the advantages that the rotary support and the acquisition support which can be rotationally adjusted are arranged to support and adjust the camera for face recognition and image acquisition, so that the working direction of the camera can be conveniently adjusted according to requirements, and the main body display content of a conference can be switched; according to the remote conference system, the cameras are arranged, the laser distance measuring sensor is arranged on one side of each camera to detect the distance between the cameras, the collecting support is controlled according to detected data to conduct local fine adjustment on the positions of the cameras, the cameras can work more clearly, and then the use convenience of the remote conference system is effectively improved.

The application relates to the technical field of intelligent contract, and discloses an intelligent contract security generation and risk insight method fusing a large language model and a digital signature, which comprises the following steps: first, acquiring a telephone conference voice and performing telephone voice band processing and system sound interference suppression to obtain a purified signal; positioning a short near-end segment based on the purified signal, extracting an energy peak time and setting an early window and a late window; estimating a fundamental frequency in the early window and constructing a harmonic set, calculating a normalized bicoherence intensity set average value of the early window and the late window, constructing a characteristic index and forming a time-varying gating weight field through a monotone mapping; then, acquiring a word-level timestamp through automatic speech recognition, and calculating word availability in combination with the gating weight field; extracting an offer of a speaker A, collecting response words of a speaker B in a preset time window, and calculating response reliability according to the word availability and time closeness; generating a clause draft according to the response reliability, judging whether the clause draft is included in a contract preliminary draft, and outputting a risk clause of the contract draft.

This invention discloses a method and system for speech separation and segment attribution in remote conferencing scenarios, relating to the field of speech recognition technology. The method includes: triggering speech recording in a target meeting window via a conferencing platform to generate meeting audio; performing two-way speech separation processing on the meeting audio using a first engine to construct a speech logic graph; matching a target meeting template using a second engine and performing speech segment attribution based on automated meeting record layout according to the speech logic graph to generate a target meeting record; and storing the target meeting record in a platform database for retrieval and management using access settings. This invention solves the technical problem in existing multi-party conferencing systems where speech interleaving makes it difficult to effectively distinguish speakers and the logical structure of their statements, leading to unclear meeting record attribution and low editing efficiency. It achieves two-way semantic logic separation and structured attribution of remote meeting speech content, improving the accuracy of meeting records and the efficiency of automatic layout.

Solutions are disclosed that provide automated audience response estimation (sentiment analysis) and presenter feedback. Examples capture a plurality of multi-modal signals from a first multi-participant interaction session, such as capturing an audio feed, a video feed, a chat, and actions (e.g., hand-raising) from a video teleconference. Timing information is correlated, enabling accurate sentiment analysis across the multi-modal signals, such as nodding in agreement, detected in the video feed, is correlated with spoken words, captured in the audio clip and identified in an automated transcript. This enables reporting audience sentiment to the presenter, in near-real-time (i.e., during the teleconference) in some examples. Some examples combine multi-modal sentiment analysis results from multiple teleconferences in order to create or train a presentation coach that is able to suggest improvements to planned presentations. Some examples are able to identify a particular audience member (e.g., a VIP), and perform individualized sentiment analysis for that person.

Using a camera pointing downward, a working area below eye level can be displayed by a headwear for users, so that the user can maintain healthy sitting or standing posture while working on patients or objects located below eye level. Using two or more cameras pointing downward, three-dimensional views with accurate and natural depth perception of a working area can be displayed by a headwear for users. Additional functions including eye protection, zoom-in, zoom-out, on-off, lighting control, overlapping, and teleconference capabilities are also supported using electronic, video and audio devices associated with the headwear. The headwear can also comprise a face shield designed to protect the user from hazardous droplets, aerosols, harmful wavelengths of light, heat, sparks, flash burn, debris and / or flying objects. Contactless control devices can be used to control the functions of the headwear.

This document relates to adaptive presentation of content during a teleconference. For instance, the disclosed techniques can employ one or more attention signals to infer that a user's attention is directed to certain content presented during a particular time period during a teleconference. Then, other content that the user may have missed can be summarized using a generative machine learning model. A summary of the potentially-missed content can be output to the user during the teleconference. In this manner, users who may miss presentation of certain content can remain informed during the course of the teleconference.

A method of compensating for ambient noise during a teleconference may involve estimating, by a control system, a current speech spectrum corresponding to a speech of a remote teleconference participant; estimating, by the control system, a current noise spectrum corresponding to ambient noise in a local environment in which a local teleconference participant is located; calculating, by the control system, a current speech intelligibility index (SII) based at least in part on the current speech spectrum and the current noise spectrum; determining, by the control system and based at least in part on the current SII, whether to adjust a local audio system used by the local teleconference participant, where the determining involves evaluating the current SII according to one or more target SII parameters; and updating at least one of the one or more target SII parameters in response to a user input corresponding to the playback volume change.

A session join request to join an active teleconference session is provided to a teleconference computing system that hosts the active teleconference session. The session join request can include information that identifies a first participant associated with the first computing device. Responsive to providing the session join request to join the active teleconference session, interface display information is received from the teleconference computing system. The interface display information can include information indicating that a second computing device associated with the first participant is already connected to the active teleconference session. The interface display information can include instructions to display a first candidate content item of a plurality of candidate content items. Display of either the first video stream or the second video stream within an interface associated with the active teleconference session is caused.

The invention discloses an intelligent communication analysis and performance evaluation system for a whole sales process. The system comprises a data acquisition module, a preprocessing and feature extraction module, a communication stage identification module, a performance evaluation module, a prediction and decision support module and a feedback and visualization module. According to the invention, unified collection and fusion analysis of multi-channel communication data such as telephones, conferences and mails can be realized, information splitting is avoided, and the integrity and consistency of the data are improved; manual subjective scoring is replaced by a preset quantitative index and an intelligent model, so that objectiveness and standardization of performance evaluation are realized; stage identification results and improvement suggestions can be output in real time in the sales communication process, salesmen are helped to adjust communication strategies in real time, and the improvement period is shortened; meanwhile, the customer transformation probability and the transaction trend are predicted based on the historical data and the current features, and the perspectiveness and the accuracy of the sales process are improved.

This document relates to providing adaptive teleconferencing experiences using generative image models. For example, the disclosed implementations can employ inpainting and / or image-to-image restyling modes of a generative image model to generate images for a teleconference. The images can be generated based on prompts relating to the teleconference. Users can be superimposed on the generated images, thus giving the appearance that the users are present in an environment generated by the generative image model.

Embodiments may relate to a user equipment (UE) that is configured to determine a real-time transport protocol (RTP) media flow that includes visual data related to a plurality of images concurrently taken of a location and a supplemental information enhancement (SEI) message that is to be used to display at least a portion of the visual data. The UE is further configured to visually display, based on the visual data and the SEI message, the portion of the visual data to a user of the user device. Other embodiments may be described or claimed.

Systems, devices, manufactured articles, and methods for saving energy in teleconferences are disclosed. An exemplary first client device includes an interface circuit; machine-readable instructions; and at least one processor circuit to instantiate or execute the machine-readable instructions to: determine whether a first participant in a teleconference is absent from the first client device; and cause the transmission of a notification to at least one server for the teleconference or to a second client device connected to the teleconference and different from the first client device, the notification causing the second client device to change an operational state associated with the teleconference.

A video recording system and a method for tagging network meetings and video / audio clips from a main video / audio stream are described and claimed. The video recording system allows a system user to view and selectively tag a main video stream or video clips. A rewind control plays back the main video stream and then tags the selected video clip from a start indicator to an end indicator. The video recording system also allows network members to conduct teleconferences while a main video stream is being recorded. Any network member can tag selected sections of the teleconference in real time. In addition, a recording alert control automatically displays a reminder message to the operator of a digital device after a period of inactivity, such as 5 to 10 seconds, following the opening of the software application.This feature is useful when the camera operator forgets to record. A voice control function allows you to activate the controls using voice commands.

This document relates to adaptive presentation of content during a teleconference. For instance, the disclosed techniques can employ one or more attention signals to infer that a user's attention is directed to certain content presented during a particular time period during a teleconference. Then, other content that the user may have missed can be summarized using a generative machine learning model. A summary of the potentially-missed content can be output to the user during the teleconference. In this manner, users who may miss presentation of certain content can remain informed during the course of the teleconference.

A teleconference system (1) capable of smoothly progressing a teleconference is provided. A speech determination unit (2) determines whether a voice of each of a plurality of participants in a teleconference indicates speech or back-channel. A voice output control unit (4) performs control so that the voice of each of a plurality of the participants is output by a communication terminal of each of a plurality of the participants. The voice output control unit (4) performs control, when, while one of a plurality of the participants makes speech, another participant makes speech, so as to suppress an output of the speech of the another participant. A count unit (6) counts the number of collision speeches, for each participant. A number display control unit (8) performs control so that a display related to the number of times is made at the communication terminals of a plurality of the participants.

The invention relates to the technical field of communication, and discloses a data sharing method, electronic equipment and a system. The method comprises the following steps: receiving first streaming media data from a sending end; decoding the first streaming media data to obtain second streaming media data in a preset format; transmitting the second streaming media data to a virtual drive program in a core layer of the native system; the virtual drive program is identified as a virtual audio and video node by the conference application; and after directly reading the second streaming media data of the virtual audio and video node through the conference application, displaying the second streaming media data and sharing the second streaming media data to the remote equipment. According to the invention, instant sharing of the screen transmission picture from the sending end is realized, private interface development does not need to be carried out for each conference application, compatibility and maintainability are good, and when desktop sharing is carried out on the remote conference, once streaming media data sent by the sending end are received, the remote conference can be shared in real time. And the streaming media data can be directly shared to the remote equipment of the teleconference.

A sound communication device improves the sense of presence in a teleconference. The sound communication device includes: a sound image position decision unit that decides a sound image positioning position in a virtual space having a first wall and a second wall for each of N sound signals; N sound image positioning units that perform sound image positioning processing in a manner that a sound image is positioned at the sound image positioning position, and output sound image positioning sound signals; and an addition unit that adds the N sound image positioning sound signals, and outputs an added sound image positioning sound signal. The sound image positioning unit performs the sound image positioning processing using a first head transfer function that simulates a direct arrival at a listener's binaural ears of a sound wave emitted from the sound image positioning position and a second head transfer function that simulates an arrival at the listener's binaural ears of a sound wave emitted from the sound image positioning position and reflected from a wall closer to the sound image positioning position than the other wall among the first wall and the second wall.

Techniques for transcribing and / or summarizing a multimedia collaboration session are discussed herein. For example, users may communicate within a teleconference conference associated with a channel. In some examples, a first machine learning model may be configured to receive audiovisual data and user interaction data (e.g., selected emojis, detected gestures, messages or text entered by users, message threads, etc.) and output a teleconference conference summary. In some examples, the teleconference conference summary may include one or more highlights, action items, and / or artificial intelligence (AI) notes generated using the machine learning model(s).

Examples herein provide a method for enhancing audio mixing of teleconference applications by switching between noise suppression modes using a single model. Specifically, a machine learning (ML) model may be configured to, in response to receiving an audio mix representation as input, suppress background noise of the audio mix or suppress all noise of the audio mix other than the user's speech. In some examples, an ML model may be trained using speech and background noise training data during a training phase. In addition, the ML model may be trained with the user's speech during the registration phase. In addition, during the inference phase, the ML model may enhance the audio mixing by suppressing portions of the audio mixing.

A system includes circuitry and a memory that stores an information recording application. When executed at a terminal apparatus, the information recording application creates recording information according to screen information displayed by a teleconference application selected by the information recording application and image information representing a surrounding space around a device acquired by the device.

The present disclosure relates to audio modification using interconnected electronic devices. Provided herein are systems and methods for reducing undesirable noise in electronic audio signals, where a computing device with a microphone is configured to receive a signal from a sensor on an external device, such as a camera, a second microphone, or a motion sensor. The signal from the sensor is used to identify sound information or characteristics of sound produced by a noise source, and the audio signal of the microphone is modified based on that sound information or based on the sound identified from a second audio signal obtained by the second microphone to reduce undesirable sound, thereby improving teleconference and videoconference audio quality and removing distracting noise from transmitted audio output.