Abstract: A device is configured to detect multiple different wakewords. A device may operate a joint encoder that operates on audio data to determine encoded audio data. The device may operate multiple different decoders which process the encoded audio data to determine if a wakeword is detected. Each decoder may correspond to a different wakeword. The decoders may use fewer computing resources than the joint encoder, allowing for the device to more easily perform multiple wakeword processing. Enabling/disabling wakeword(s) may involve the reconfiguring of a wakeword detector to add/remove data for respective decoder(s).

Abstract: A system and method performs wakeword detection using a feedforward neural network model. A first output of the model indicates when the wakeword appears on a right side of a first window of input audio data. A second output of the model indicates when the wakeword appears in the center of a second window of input audio data. A third output of the model indicates when the wakeword appears on a left side of a third window of input audio data. Using these outputs, the system and method determine a beginpoint and endpoint of the wakeword.

Abstract: A neural network model of a user device is trained to map different words represented in audio data to different points in an N-dimensional embedding space. When the user device determines that a mapped point corresponds to a wakeword, it causes further audio processing, such as automatic speech recognition or natural-language understanding, to be performed on the audio data. The user device may first create the wakeword by first processing audio data representing the wakeword to determine the mapped point in the embedding space.

Abstract: Systems and methods are disclosed for actively all-to-all exchanging messages in a large group of individuals, comprising accumulating messages from individuals in at least one hub, processing and reorganizing accumulated messages and their groups into short representations of the messages, and selectively actively delivering short representations according to a distribution pattern found as a maximum of a goodness function. Processing and reorganizing accumulated messages into short representations, that is summarization, is performed by constraining the stream of messages to a hierarchical stream format, having a hierarchy of messages linked by a directional parent-child relationship, and iteratively replacing the parent messages in such hierarchy with a representative message chosen among all children of that message.

Abstract: Systems and methods are disclosed for actively all-to-all exchanging messages in a large group of individuals, comprising accumulating messages from individuals in at least one hub, processing and reorganizing accumulated messages and their groups into short representations of the messages, and selectively actively delivering short representations according to a distribution pattern found as a maximum of a goodness function. Processing and reorganizing accumulated messages into short representations, that is summarization, is performed by constraining the stream of messages to a hierarchical stream format, having a hierarchy of messages linked by a directional parent-child relationship, and iteratively replacing the parent messages in such hierarchy with a representative message chosen among all children of that message.