Abstract: Provided herein are systems and methods for delta models for providing privatized speech-to-text during virtual meetings. In one embodiment, a system may include a non-transitory computer-readable medium; a communications interface; and a processor. The processor may be configured to execute processor-executable instructions to: join a virtual meeting. Each participant in the virtual meeting may exchange audio streams with other participants in the virtual meeting. The instructions may include receiving, from a video conference provider, a local model for speech recognition. The local model may be a copy of a centralized model. The instructions may include performing speech recognition using the local model on the audio streams.

Abstract: Systems and methods for enforcing consent requirements for sharing virtual meeting recordings are provided herein. In an example, a method may include receiving, from a first client device, a recording privacy request associated with a virtual meeting, and receiving, from a second client device, a request to share a recording of the virtual meeting with one or more recipients. The method may also include modifying, by a video conference provider, at least one of a first audio stream or a first video stream associated with the first client device in the recording based on the recording privacy request, and generating, by the video conference provider, a privatized recording based on the modification of at least one of the first audio stream or the first video stream. The method may also include transmitting, by the video conference provider, the privatized recording to the one or more recipients.

Abstract: Techniques for synthesizing multi-accent speech using adaptive weights are provided. A computing system may receive a text input along with first information about a first accent. The computing system may access a first trained machine learning model, the first trained machine learning model trained to synthesize, from inputted text, waveforms representing speech. The computing device may apply one or more adaptive weights to the first trained machine learning model, the one or more adaptive weights characterizing the first accent. The computing device may then synthesize, using the first trained machine learning model with the applied one or more adaptive weights, a first waveform representing the text input, wherein the first waveform is characterized by the first accent.

Abstract: A manipulation of a media stream associated with a manipulated participant of a communication session is identified. A notification of the manipulation is transmitted to a first participant of the communication session. An approval indication of the manipulation is received from the first participant. A determination is made that the approval indication indicates a disapproval of the manipulation. A request to disable the manipulation is transmitted to a second participant of the communication session.

Abstract: A request from a first device of a first communication session participant to connect to a second device of a second communication session participant is received at communications software. The communications software connects the first device to the second device, communications software determines a level of authenticity for the first communication session participant based on a communications history of at least one of the first communication session participant or the second communication session participant. The communications software notifies the second communication session participant of the level of authenticity.

Abstract: A media stream associated with a participant of a communication session is received. A biometric marker is generated for the participant based on the media stream. User profiles associated with the biometric marker are identified in a biometrics reference library. A determination is made as to whether a cardinality of the user profiles exceeds a threshold number. Responsive to determining that the cardinality of the user profiles exceeds the threshold number, another participant is notified of a possible inauthenticity of the participant.

Abstract: Systems and methods for providing automated personal privacy during virtual meetings are provided herein. The method may include establishing, by a video conference provider, a video conference having a plurality of participants. The method may also include receiving, from a first client device associated with one of the plurality of participants, a first audio stream and a first video stream, and recording responsive to an indication from one of the plurality of participants, one or more audio or video streams within a recording. The method may include receiving, from the first client device, a personal privacy request. In response to the personal privacy request, the method may include modifying, by the video conference provider, at least one of the first audio stream or the first video stream in the recording and storing the least one of the first audio stream or the first video stream as modified to the recording.

Abstract: A system for providing off-the-record functionality is provided herein. The system may include a processor configured to execute processor-executable instructions stored in non-transitory computer-readable medium to establish a video conference having a plurality of participants, each participant of the plurality of participants exchanging a plurality of audio or video streams via the video conference. The processor may also be configured to receive, from a first client device associated with one of the plurality of participants, a first audio stream or a first video stream of the plurality of audio or video streams, and record the plurality of audio or video streams within a recording. The processor may also be configured to receive an off-the-record request to begin an off-the-record time period, and in response to the off-the-record request, prevent at least one of the first audio stream or the first video stream from being included in the recording.

Abstract: A speech translation system and methods for cross-lingual communication that enable users to improve and customize content and usage of the system and easily. The methods include, in response to receiving an utterance including a first term associated with a field, translating the utterance into a second language. In response to receiving an indication to add the first term associated with the field to a first recognition lexicon, adding the first term associated with the field and the determined translation to a first machine translation module and to a shared database for a community associated with the field of the first term associated with the field, wherein the first term associated with the field added to the shared database is accessible by the community.

Abstract: One example method includes receiving, during a virtual conference hosted by a virtual conference provider, a first audio stream comprising speech having first speech patterns according to a first accent, the first audio stream received from a first client device associated with a first participant in the virtual conference; generating, by a first trained machine learning (“ML”) model, a second audio stream comprising the speech having second speech patterns according to a second accent; and outputting the second audio stream.

Abstract: Provided herein are systems and methods for delta models for providing privatized speech-to-text during virtual meetings. In one embodiment, a system may include a non-transitory computer-readable medium; a communications interface; and a processor. The processor may be configured to execute processor-executable instructions to: join a virtual meeting. Each participant in the virtual meeting may exchange audio streams with other participants in the virtual meeting. The instructions may include receiving, from a video conference provider, a local model for speech recognition. The local model may be a copy of a centralized model. The instructions may include performing speech recognition using the local model on the audio streams.

Abstract: Systems and methods for providing automated personal privacy during virtual meetings are provided herein. The method may include establishing, by a video conference provider, a video conference having a plurality of participants. The method may also include receiving, from a first client device associated with one of the plurality of participants, a first audio stream and a first video stream, and recording responsive to an indication from one of the plurality of participants, one or more audio or video streams within a recording. The method may include receiving, from the first client device, a personal privacy request. In response to the personal privacy request, the method may include modifying, by the video conference provider, at least one of the first audio stream or the first video stream in the recording and storing the least one of the first audio stream or the first video stream as modified to the recording.

Abstract: A system for providing off-the-record functionality is provided herein. The system may include a processor configured to execute processor-executable instructions stored in non-transitory computer-readable medium to establish a video conference having a plurality of participants, each participant of the plurality of participants exchanging a plurality of audio or video streams via the video conference. The processor may also be configured to receive, from a first client device associated with one of the plurality of participants, a first audio stream or a first video stream of the plurality of audio or video streams, and record the plurality of audio or video streams within a recording. The processor may also be configured to receive an off-the-record request to begin an off-the-record time period, and in response to the off-the-record request, prevent at least one of the first audio stream or the first video stream from being included in the recording.

Abstract: Systems and methods for enforcing consent requirements for sharing virtual meeting recordings are provided herein. In an example, a method may include receiving, from a first client device, a recording privacy request associated with a virtual meeting, and receiving, from a second client device, a request to share a recording of the virtual meeting with one or more recipients. The method may also include modifying, by a video conference provider, at least one of a first audio stream or a first video stream associated with the first client device in the recording based on the recording privacy request, and generating, by the video conference provider, a privatized recording based on the modification of at least one of the first audio stream or the first video stream. The method may also include transmitting, by the video conference provider, the privatized recording to the one or more recipients.

Abstract: Systems and methods for providing instant processing of virtual meeting recordings are provided.

Abstract: Computer systems and computer-implemented methods provide for interactive and incremental post-editing of real-time speech transcription and translation. A first component is automatic identification of potentially problematic regions in the output (e.g., transcription or translation) that are either likely to be technically processed badly or risky in terms of their content or expression. A second component is intelligent, efficient interfaces that permit multiple editors to correct system output concurrently, collaboratively, efficiently, and simultaneously, so that corrections can be seamlessly inserted and become part of a running presentation. A third component is incremental learning and adaptation that allows the system to use the human corrective feedback to deliver instantaneous improvement of system behavior down-stream. A fourth component is transfer learning to transfer short-term learning into long term learning if the modifications warrant long-term retention.

Abstract: Systems and methods for providing a voice agent for sidebars during virtual meetings are provided. In an Example, a system including a non-transitory computer-readable medium, a communications interface, and a processor is provided. The processor configured to execute processor-executable instructions stored in the non-transitory computer-readable medium to: establish a video conference, receive, from a first client device, a request for a sidebar meeting, and transmit to the first client device: a first set of audio and video streams corresponding to a main meeting, and a second set of audio and video streams corresponding to the sidebar meeting. The processor may be configured to identify, by a voice agent, an attention cue in an audio stream from the first set of audio and video streams, and generate, by the voice agent, an alert based on the attention cue identified in the audio stream.

Abstract: A system comprises a machine that is configured to act upon requests from a user and sensing means for sensing an operational-mode dialog stream from the user for the machine. The system also comprises a computing system that is configured to train a neural network through machine learning to output, for each training example in a training dialog stream dataset, a corrected request for the machine. The computing system is also configure to, in an operational mode, using the trained neural network, generate a corrected, operational-mode request for the machine based on the operational-mode dialog stream from the user for the machine, wherein the operational-mode dialog stream is sensed by the sensing means.

Abstract: A speech translation system and methods for cross-lingual communication that enable users to improve and customize content and usage of the system and easily. The methods include, in response to receiving an utterance including a first term associated with a field, translating the utterance into a second language. In response to receiving an indication to add the first term associated with the field to a first recognition lexicon, adding the first term associated with the field and the determined translation to a first machine translation module and to a shared database for a community associated with the field of the first term associated with the field, wherein the first term associated with the field added to the shared database is accessible by the community.

Abstract: Computer-implemented methods and apparatus that use neural modulation codes as an alternative to training many individual recognition models or to loosing performance by training mixed models. Large neural models are modulated by codes that model the different conditions. The codes directly alter (modulate) the behavior of connections in a multiconditional perceptual classifier, so as to permit the most appropriate neuronal units and their features to be applied to each condition. The approach may be applied to multilingual ASR, where the resulting multilingual network arrangement is able to achieve performance that is competitive or better than individually trained mono-lingual network. Moreover, the approach requires no adaptation data or extensive adaptation/training time to operate in a manner tuned to each condition. Beyond multilingual speech processing systems the approach can be applied to many other perceptual processing problems (e.g.