Abstract: Example techniques relate to local voice control in a media playback system. A satellite device (e.g., a playback device or microcontroller unit) may be configured to recognize a local set of keywords in voice inputs including context specific keywords (e.g., for controlling an associated smart device) as well as keywords corresponding to a subset of media playback commands for controlling playback devices in the media playback system. The satellite device may fall back to a hub device (e.g., a playback device) configured to recognize a more extensive set of keywords. In some examples, either device may fall back to the cloud for processing of other voice inputs.

Abstract: Systems and methods for managing concurrent voice assistants are disclosed. A network microphone device is associated with a first voice assistant service (VAS). The device receives a request to associate with a second VAS different than the first. The device accesses a concurrency rules engine to determine concurrency restrictions. If the rules engine indicates concurrency is prohibited, concurrency can be restricted by (i) disassociating the network microphone device and the first VAS, and associating the network microphone device with the second VAS; or (ii) precluding associating the network microphone device with the second VAS and maintaining association with the first VAS.

Abstract: In one aspect, an audio playback device having at least one microphone captures a voice input. The playback device detects, within the voice input, at least one keyword from among a plurality of command keywords supported by the playback device. The playback device determines, via a local natural language unit (NLU), an intent based on the keyword. The keyword is then evaluated based at least in part on a volume characteristic of the voice input. Based on the evaluation, the playback device either forgoes further processing of the voice input or performs a command in accordance with the determined intent.

Abstract: Example techniques relate to local voice control in a media playback system. A satellite device (e.g., a playback device or microcontroller unit) may be configured to recognize a local set of keywords in voice inputs including context specific keywords (e.g., for controlling an associated smart device) as well as keywords corresponding to a subset of media playback commands for controlling playback devices in the media playback system. The satellite device may fall back to a hub device (e.g., a playback device) configured to recognize a more extensive set of keywords. In some examples, either device may fall back to the cloud for processing of other voice inputs.

Abstract: Examples described herein relate to triggering voice assistant(s) on a network microphone device (NMD). An NMD is a networked computing device that typically includes an arrangement of microphones, such as a microphone array, that is configured to detect sound present in the NMD's environment. Once the voice assistant is triggered, the NMD may start recording voice input as a potential voice command. Within examples, the NMD may operate in a wakewordless mode if certain conditions are met. These conditions may involve detecting user proximity in one of multiple different ranges. For instance, an example NMD may monitor for user proximity in a first range from the playback device via at least one touch-sensitive sensor and/or user line-of-sight in a second range that is further from the playback device than the first range. When either user proximity or user line-of-sight is detected, the the NMD may enables the wakewordless mode.

Abstract: Provided are methods and devices for determining a stop period of a mobile device in a location, according to geolocation data available on the mobile device. A predicted position of the mobile device and an associated level of uncertainty related to the predicted position is determined according to either the current position of the mobile device if it is available, or, if not, according to an artificial position obtained from a previously known position of the mobile device. The mobile device is considered to be in a stop period if the normalized prediction error between the predicted position and either the current position or the artificial position, depending on the situation, is smaller than a prediction error threshold. Upon detection of a stop period, an action on the mobile device is triggered.

Abstract: A mobile device and a method for determining a place according to geolocation information is disclosed. In one aspect, the method includes triggering an action in obtaining a first set of information related to the user, and, according to the current geographical location, a second set of places. The method may also include, for each place of the second set, determining a combined probability distribution that the user is currently located in said place, according to the first set of information, a first probability distributions based on a set of parameters related to global user habits, a second probability distributions based on a set of parameters related to user habits, and a third probability distributions based on a set of parameters related to local user habits. The method may further include triggering at least one action according to the combined probability distributions of the places of the second set.

Abstract: Methods and systems for determining past activities of a user and triggering an action accordingly are disclosed. In one aspect, the method is performed on a device and involves determining a set of historical information related to past activities of the user, according to at least one sources of historical data available through the device, determining a timeline of past activities of the user, according to the set of historical information, and triggering an action on the device, according to the timeline of past activities of the user.

Abstract: Provided are means for identifying stop periods of a device in a location. A method for identifying the stop periods may be performed by a mobile device and involve during a first step, determining a predicted position of the mobile device, according to a new filtered position obtained using a discrete-time Kalman Filter. The method may also involve during a second step, determining a normalized prediction error according to the difference between the new predicted position and the first position. If the normalized prediction error is smaller than a prediction error threshold, generating a stop message to indicate that the stop period is starting. The method may further involve during a third step, triggering an action on the mobile device, according to the stop message.

Abstract: A mobile device and a method for determining a place according to geolocation information is disclosed. In one aspect, the method includes triggering an action in obtaining a first set of information related to the user, and, according to the current geographical location, a second set of places. The method may also include, for each place of the second set, determining a combined probability distribution that the user is currently located in said place, according to the first set of information, a first probability distributions based on a set of parameters related to global user habits, a second probability distributions based on a set of parameters related to user habits, and a third probability distributions based on a set of parameters related to local user habits. The method may further include triggering at least one action according to the combined probability distributions of the places of the second set.

Abstract: Provided is a method for triggering an action on a mobile device of a user. In one aspect, the method includes determining a current sub-period using the current time and determining at least one sub-region of destination amongst sub-regions of the geographical classification according to probabilities of departure of the user, from the current sub-region, to each sub-region of the geographical classification, for each sub-period of the time classification, and according to the current sub-period. The method may also involve obtaining a list of activities related to the user, determining at least one predicted activity according to probabilities, for each activity of the list of activities, that the user will engage in said activity, in the at least one sub-region of destination, for the sub-period corresponding to a starting time of said activity and triggering at least one action according to the at least one predicted activity.