Abstract: A camera is auto-focused on an in-person attendee in a meeting who is speaking into a microphone at a live location of the meeting. The live location includes a real-time location system (RTLS) having a RTLS tag and a plurality of RTLS anchors for locating a position of the RTLS tag in three-dimensional space. The RTLS tag is fixed to the microphone and transmits a signal that is received by the plurality of RTLS anchors. In operation, it detected when the microphone is active. The position of the RTLS tag in the live location is then identified in three-dimensional space by using the signal transmitted from the RTLS tag and received by the RTLS anchors to calculate the position of the RTLS tag in three-dimensional space. The position of the RTLS tag in three-dimensional space in the live location is presumed to be the same position as the microphone that the RTLS tag is fixed to.

Abstract: An audio-visual sharing system has a first user with a mobile platform executing an application and coupled to an Internet network, a second user with a mobile platform executing the application and coupled to the Internet network, an Internet-connected server having a processor executing coded instructions, and coupled to a data repository, a first profile for the first user stored in the data repository; and a second profile for the second user stored in the data repository. The first user is present at an event capturing audio and video of proximate activity and streaming same to the server. The second user is not present at the event, but both the first and second mobile platforms receive an AR board display comprising avatars for the users. The second user is enabled to interact with the first user's avatar to share the audio and video streamed by the first user.

Abstract: The glasses with display may include a bridge, two temples hingedly coupled to the bridge, and a directional microphone array, the directional microphone array including two or more microphones positioned on the bridge or the temples. The glasses with display may also include a user microphone array, the user microphone array including one or more microphones positioned on the temples and oriented toward the mouth of a user wearing the glasses with display or one or more bone conduction microphones. In addition, the glasses with display include two lenses positioned in the bridge, at least one of the lenses including a display, the display visible by the user, the display including one or more of a directional display, closed caption display, and user volume display. The glasses with display additionally include a processor adapted to receive audio signals from the directional microphone array and the user microphone array, or from a separate mobile device, the processor adapted to control the display.

Abstract: A system and method for automated chatbot testing to provide training and quality assurance of conversational artificial intelligence systems, comprising a chatbot testing administrator interface which allows chatbot makers to define what a chatbot is supposed to do, create test scripts to test the performance of the chatbot, and review the results of the chatbot tests, a chatbot testing server which provides and interface between chatbot testing agents and the administrator interface, instantiates chatbot agents and distributes them across available hardware and runs testing programs which activate, configure, and deactivate chatbot testing agents as needed. A plurality of chatbot agents may be running in parallel to provide automated testing based upon test script configuration.

Abstract: Adapting an audio portion of a video conference includes a presenter providing content for the video conference by delivering live content, prerecorded content, or combining live content with prerecorded content, at least one additional co-presenter provides content for the video conference, and untangling overlapping audio streams of the presenter and the co-presenter by replaying individual audio streams from the presenter and/or the at least one co-presenter or separating the audio streams by diarization. Adapting an audio portion of a video conference may also include recording the presenter to provide a recorded audio stream, using speech-to-text conversion to convert the recorded audio stream to text, correlating the text to the recorded audio stream, retrieving a past portion of the recorded audio stream using a keyword search of the text, and replaying the past portion of the recorded audio stream. The keyword may be entered using a voice recognition system.

Abstract: A system and method for chatbot and search engine integration comprising chatbot crawler engine configured to detect all possible paths through a conversational flow between a chatbot and a user, and also comprising a chatbot search integration manager configured to receive a processed conversation flow from the chatbot crawler engine, parse the conversation flow to identify keywords and features, and build an indexable data structure which can be integrated into search engines in order to expose the information and data contained within the chatbot's knowledge base. This integration may allow search engine users to be redirected to a website hosting the chatbot when an indexed data structure comprises information relevant to a search engine query.

Abstract: Embodiments described herein provide a technique to crowdsource labeling of training data for a machine learning model while maintaining the privacy of the data provided by crowdsourcing participants. Client devices can be used to generate proposed labels for a unit of data to be used in a training dataset. One or more privacy mechanisms are used to protect user data when transmitting the data to a server. The server can aggregate the proposed labels and use the most frequently proposed labels for an element as the label for the element when generating training data for the machine learning model. The machine learning model is then trained using the crowdsourced labels to improve the accuracy of the model.

Abstract: Methods and systems for determining periods of excessive noise for smart speaker voice commands. An electronic timeline of volume levels of currently playing content is made available to a smart speaker. From this timeline, periods of high content volume are determined, and the smart speaker alerts users during periods of high volume, requesting that they wait until the high-volume period has passed before issuing voice commands. In this manner, the smart speaker helps prevent voice commands that may not be detected, or may be detected inaccurately, due to the noise of the content currently being played.

Abstract: Systems, methods, and computer-readable media for providing smart notifications during voice call transitions from hold status to active status are described. An example method can include establishing a call between an endpoint and a remote device; after a determination that the call was placed on hold by the remote device, monitoring, by the endpoint, the call for an indication of a call resume transition, the indication of the call resume transition including at least one of a particular keyword transmitted by the remote device, an active speaker at the remote device, and a dual-tone multi-frequency signaling (DTMF) input from the remote device; detecting, by the endpoint, the indication of the call resume transition; and in response to detecting the indication of the call resume transition, generating, by the endpoint, a notification indicating that the hold has ended and the call has resumed.

Abstract: A method and system for optimizing conference session activities within a conference space, the system comprising at least a first sensor for sensing session characteristics and a processor receiving the sensed session characteristics and identifying a conference paradigm based on the sensed session characteristics, identifying an action sequence to perform as a function of the conference paradigm and performing the action sequence, wherein the action sequence results in automatic presentation of at least some information to at least a subset of conferees within the conference space.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for validating and publishing workflows from remote environments. In some implementations, a link that includes at least one of audio data and video data is established between a wireless device of a remote participant and a computational mixer. A profile for the remote participant is referenced. A venue signal related to the at least one audio data and video data is generated based on the profile for the remote participant and using the computational mixer. The venue signal is transmitted.

Abstract: This disclosure enables various technologies for screensharing to minimize visual distractions, maximize professionalism, or avoid sharing sensitive, confidential, classified, or private information.

Abstract: An agent automation system implements a virtual agent that is capable of learning new words, or new meanings for known words, based on exchanges between the virtual agent and a user in order to customize the vocabulary of the virtual agent to the needs of the user or users. The agent automation framework has access to a corpus of previous exchanges between the virtual agent and the user, such as one or more chat logs. New words and/or new meanings for known words are identified within the corpus and new word vectors are generated for these new words and/or new meanings for known words and added to refine a word vector distribution model. The refined word vector distribution model is then utilized by the agent automation system to interact with the user.

Abstract: Disclosed is a binaural rendering method and apparatus for decoding a multichannel audio signal. The binaural rendering method may include: extracting an early reflection component and a late reverberation component from a binaural filter; generating a stereo audio signal by performing binaural rendering of a multichannel audio signal base on the early reflection component; and applying the late reverberation component to the generated stereo audio signal.

Abstract: Methods, systems, and apparatus for conducting a video conference. A location of one or more sets of eyes in an image may be determined. The relative location of an image capture device and/or a portion of a display device may be adjusted based on the determined location.

Abstract: This application relates to earbuds configured with one or more biometric sensors. At least one of the biometric sensors is configured to be pressed up against a portion of the tragus for making biometric measurements. In some embodiments, the housing of the earbud can be symmetric so that the earbud can be worn interchangeably in either a left or a right ear of a user. In such an embodiment, the earbud can include a sensor and circuitry configured to determine and alter operation of the earbud in accordance to which ear the earbud is determined to be sitting in.

Abstract: The present disclosure provides details of a system and method for customizing an inmate communication notification. Such a system provides an inmate different customized notification messages to be played to different called parties. The system includes a list of different contacts, and each of the contacts can be associated with one or more contact numbers. Each contact number is associated with one or more customized notification messages. The customized notification messages include terms, phrases, and sentences that draw the called party's attention and sound familiar to the called party. The customized notification messages include customized text files, audio files, and video files. An inmate chooses one or more customized notification messages to be played to a called party.

Abstract: Offset cartridge microphones are provided that include multiple unidirectional microphone cartridges mounted in an offset geometry. Various desired polar patterns and/or desired steering angles can be formed by processing the audio signals from the multiple cartridges, including a toroidal polar pattern. The offset geometry of the cartridges may include mounting the cartridges so that they are immediately adjacent to one another and so that their center axes are offset from one another. The microphones may have a more consistent on-axis frequency response and may more uniformly form desired polar patterns and/or desired steering angles by reducing the interference and reflections within and between the cartridges.

Abstract: Techniques for altering default language, in system outputs, with language included in system inputs are described. A system may determine a word(s) in user inputs, associated with a particular user identifier, correspond to but are not identical to a word(s) in system outputs. The system may store an association between the user identifier, the word(s) in the user inputs, and the word(s) in the system outputs. Thereafter, when the system is generates a response to a user input, the system may replace the word(s), traditionally in the system outputs, with the word(s) that was present in previous user inputs. Such processing may further be tailored to a natural language intent.

Abstract: Embodiments of the present invention provide for systems and methods for submitting speech queries to one or more voice assistant devices, and retrieving the responses, in a soundproof environment. The systems and methods provide for sound-dampening voice boxes that are configured to house the respective voice assistant devices, in which the sound-dampening voice boxes submit speech queries to the respective voice assistant devices, and retrieve the responses therefrom.