Abstract: Various arrangements for performing radar-based measurement of vital signs. Waveform data may be received then filtered of data indicative of static objects to obtain motion-indicative waveform data. The motion-indicative waveform data may be analyzed to determine one or more frequencies of movement present within the motion-indicative waveform data. A spectral analysis may be performed on the motion-indicative waveform data to determine a spectral-analysis state of a monitored region. The spectral-analysis state of the monitored region may be determined to match a predefined spectral-analysis state during which vital sign monitoring is permitted. One or more vital signs of a monitored user present within the monitored region may be determined and output based on analyzing the motion-indicative waveform data.

Abstract: Audio data is received via a client device, where the audio data captures a first utterance and a second utterance from different users. The audio data can be processed to determine a first transcription of the first utterance and a second transcription of the second utterance. The audio data can be further processed to determine a first account of a first user that provides the first utterance and a second account of a second user that provides the second utterance. A first natural language description including a first user ID of the first account and the first transcription can be generated, and a second natural language description including a second user ID of the second account and the second transcription can be generated. A generative model can be applied to process the first and natural language descriptions, to generate a response responsive to the first and second utterances.

Abstract: Audio data is received via a client device, where the audio data captures a first utterance and a second utterance from different users. The audio data can be processed to determine a first transcription of the first utterance and a second transcription of the second utterance. The audio data can be further processed to determine a first account of a first user that provides the first utterance and a second account of a second user that provides the second utterance. A first natural language description including a first user ID of the first account and the first transcription can be generated, and a second natural language description including a second user ID of the second account and the second transcription can be generated. A generative model can be applied to process the first and natural language descriptions, to generate a response responsive to the first and second utterances.

Abstract: Various arrangements for performing fall detection are presented. A smart-home device may transmit radar waves. Based on reflected radar waves, raw waveform data may be created. The raw waveform data may be processed to determine that a fall by a person has occurred. Speech may then be output announcing that the fall has been detected via the speaker of the smart home device.

Abstract: A disclosed method includes receiving at least an indication of audio data generated based on sound captured by a microphone of a monitoring device. A set of audio event labels are generated by processing the received audio data with a model that includes audio recognition patterns. Each audio event label is generated by matching an audio pattern in the received audio data with an audio pattern of the audio recognition patterns. The method further includes identifying a hazard event type occurring within a time window of the time period by processing the set of audio event labels with a hazard detection model. In response to detecting the hazard event type, a hazard alert is generated and at least an indication of the hazard alert is communicated to an electronic device other than the monitoring device, which is authorized to receive communications from the monitoring device.

Abstract: A user electronic device comprising: one or more microphones configured to capture raw audio data; and one or more processors and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to perform operations comprising: receiving the raw audio data captured by the one or more microphones; processing the raw audio data using a speech transcriber to generate a live transcription of the raw audio data that comprises a plurality of text tokens; processing the raw audio data to generate a speaker identification output that identifies, for each of the text tokens, a respective speaker for each of the text tokens in the live transcription; and processing a first input comprising (i) a first input prompt and (ii) an input text generated from the live transcription using a language model neural network to generate a modified transcription.

Abstract: Audio data is received via a client device, where the audio data captures a first utterance and a second utterance from different users. The audio data can be processed to determine a first transcription of the first utterance and a second transcription of the second utterance. The audio data can be further processed to determine a first account of a first user that provides the first utterance and a second account of a second user that provides the second utterance. A first natural language description including a first user ID of the first account and the first transcription can be generated, and a second natural language description including a second user ID of the second account and the second transcription can be generated. A generative model can be applied to process the first and natural language descriptions, to generate a response responsive to the first and second utterances.

Abstract: Various arrangements for performing radar-based measurement of vital signs. Waveform data may be received then filtered of data indicative of static objects to obtain motion-indicative waveform data. The motion-indicative waveform data may be analyzed to determine one or more frequencies of movement present within the motion-indicative waveform data. A spectral analysis may be performed on the motion-indicative waveform data to determine a spectral-analysis state of a monitored region. The spectral-analysis state of the monitored region may be determined to match a predefined spectral-analysis state during which vital sign monitoring is permitted. One or more vital signs of a monitored user present within the monitored region may be determined and output based on analyzing the motion-indicative waveform data.

Abstract: Various arrangements for performing radar-based measurement of vital signs. Waveform data may be received then filtered of data indicative of static objects to obtain motion-indicative waveform data. The motion-indicative waveform data may be analyzed to determine one or more frequencies of movement present within the motion-indicative waveform data. A spectral analysis may be performed on the motion-indicative waveform data to determine a spectral-analysis state of a monitored region. The spectral-analysis state of the monitored region may be determined to match a predefined spectral-analysis state during which vital sign monitoring is permitted. One or more vital signs of a monitored user present within the monitored region may be determined and output based on analyzing the motion-indicative waveform data.

Abstract: A computer-implemented authentication method comprises broadcasting, by a first device, an ultrawideband (UWB) message. The first device receives one or more UWB responses to the UWB message from one or more UWB equipped devices and determines respective distances to the one or more UWB equipped devices based on timing information associated with the UWB message and the one or more UWB responses. The method further comprises determining one or more of the UWB equipped devices having a respective distance to the first device that is within a threshold radius of the first device to be authenticatable devices, and communicating, by the first device, authentication information to one or more of the authenticatable devices to authenticate a user of the first device on the one or more authenticatable devices.

Abstract: A disclosed method includes receiving at least an indication of audio data generated based on sound captured by a microphone of a monitoring device. A set of audio event labels are generated by processing the received audio data with a model that includes audio recognition patterns. Each audio event label is generated by matching an audio pattern in the received audio data with an audio pattern of the audio recognition patterns. The method further includes identifying a hazard event type occurring within a time window of the time period by processing the set of audio event labels with a hazard detection model. In response to detecting the hazard event type, a hazard alert is generated and at least an indication of the hazard alert is communicated to an electronic device other than the monitoring device, which is authorized to receive communications from the monitoring device.

Abstract: Various arrangements for performing fall detection are presented. A smart-home device may transmit radar waves. Based on reflected radar waves, raw waveform data may be created. The raw waveform data may be processed to determine that a fall by a person has occurred. Speech may then be output announcing that the fall has been detected via the speaker of the smart home device.

Abstract: A handheld system includes a housing, a motion-generating mechanism disposed within the housing, an attachment arm extending from the housing and having a first end coupled to the motion-generating mechanism and a second end configured to receive a user assistive device, a first sensor mounted to measure a first motion of the handheld system and generate a first signal indicative of the first motion, and a control system coupled to the motion-generating mechanism and the first sensor. The control system is configured to use the first signal to stabilize the user-assistive device and compensate for human tremors imparted to the housing.

Abstract: Various arrangements for performing fall detection are presented. A smart-home device (110, 201), comprising a monolithic radar integrated circuit (205), may transmit radar waves. Based on reflected radar waves, raw waveform data may be created. The raw waveform data may be processed to determine that a fall by a person (101) has occurred. Speech may then be output announcing that the fall has been detected via the speaker (217) of the smart home device (110, 201).

Abstract: Various arrangements are presented for training and using a machine learning model. A first training data set may be created that has more samples but fewer dimensions than a second dataset. A second set of training data, created from the second dataset, has at least one additional dimension of data than the first set of training data. An additional dimension of data can then be simulated for the first set of training data. The simulated additional dimension of data can be incorporated with the first set of training data. A first machine learning model can be trained based on the first set of training data that comprises the simulated additional dimension of data to obtain various weights. A second machine learning model can then be trained based on the second set of training data and the obtained plurality of weights from the first trained machine learning model.

Abstract: A disclosed method includes receiving at least an indication of audio data generated based on sound captured by a microphone of a monitoring device. A set of audio event labels are generated by processing the received audio data with a model that includes audio recognition patterns. Each audio event label is generated by matching an audio pattern in the received audio data with an audio pattern of the audio recognition patterns. The method further includes identifying a hazard event type occurring within a time window of the time period by processing the set of audio event labels with a hazard detection model. In response to detecting the hazard event type, a hazard alert is generated and at least an indication of the hazard alert is communicated to an electronic device other than the monitoring device, which is authorized to receive communications from the monitoring device.

Abstract: Various arrangements for performing fall detection are presented. A smart-home device (110, 201), comprising a monolithic radar integrated circuit (205), may transmit radar waves. Based on reflected radar waves, raw waveform data may be created. The raw waveform data may be processed to determine that a fall by a person (101) has occurred. Speech may then be output announcing that the fall has been detected via the speaker (217) of the smart home device (110, 201).

Abstract: Various arrangements for performing radar-based measurement of vital signs. Waveform data may be received then filtered of data indicative of static objects to obtain motion-indicative waveform data. The motion-indicative waveform data may be analyzed to determine one or more frequencies of movement present within the motion-indicative waveform data. A spectral analysis may be performed on the motion-indicative waveform data to determine a spectral-analysis state of a monitored region. The spectral-analysis state of the monitored region may be determined to match a predefined spectral-analysis state during which vital sign monitoring is permitted. One or more vital signs of a monitored user present within the monitored region may be determined and output based on analyzing the motion-indicative waveform data.

Abstract: Various examples are described for using a movement sensor to detecting an activity of an infant. In an example, an activity classification system includes a sensor configured to measure the activity of an infant and an external monitor. The monitor receives, from a sensor, a time series of data comprising an inertial measurement for each a time period. The monitor determines, from the time series and by using a predictive model, an activity from a list of identified activities. Examples of identified activities are deep sleep, light sleep, sitting, awake, nursing, or bottle feeding.

Abstract: Systems and techniques are provided for light source status detection. Ambient light values generated by an ambient light sensor of a device in an environment over a period of time may be received. A first light source model for the device may be generated using a first subset of the ambient light values. A second light source model for the device may be generated using a second subset of the ambient light values. A current ambient light value generated by the ambient light sensor of the device may be received. The first light source model or the second light source model may be selected based on a time at which the current ambient light value was generated. Whether the current ambient light value indicates that a local artificial light source is on may be determined using the current ambient light value and selected light source model.