Abstract: Provided are systems, methods, and computer-readable media for providing recommended entities responsive to a search query based on a query-specific subset of contacts from a user's social graph. A search query is received from a user that includes an identifier identifying a subset of the user's social graph. The entities responsive to the search query are identified, and those entities having evaluations by or other associations with contacts from the identified subset are also identified. In response to the search query, those entities having associations with the contacts in the identified subset of the user's social graph are provided as recommended entities in the search results.

Abstract: Example methods and systems use multiple sensors to determine whether a speaker is speaking. Audio data in an audio-channel speech band detected by a microphone can be received. Vibration data in a vibration-channel speech band representative of vibrations detected by a sensor other than the microphone can be received. The microphone and the sensor can be associated with a head-mountable device (HMD). It is determined whether the audio data is causally related to the vibration data. If the audio data and the vibration data are causally related, an indication can be generated that the audio data contains HMD-wearer speech. Causally related audio and vibration data can be used to increase accuracy of text transcription of the HMD-wearer speech. If the audio data and the vibration data are not causally related, an indication can be generated that the audio data does not contain HMD-wearer speech.

Abstract: Methods, apparatus, and computer-readable media are described herein related to recognizing a look up gesture. Level-indication data from at least an accelerometer associated with a wearable computing device (WCD) can be received. The WCD can be worn by a wearer. The WCD can determine whether a head of the wearer is level based on the level-indication data. In response to determining that the head of the wearer is level, the WCD can receive lookup-indication data from at least the accelerometer. The WCD can determine whether the head of the wearer is tilted up based on the lookup-indication data. In response to determining that the head of the wearer is tilted up, the WCD can generate a gesture-recognition trigger, where the gesture-recognition trigger indicates that the head of the wearer has moved up from level.

Abstract: Example methods and systems use multiple sensors to determine whether a speaker is speaking. Audio data in an audio-channel speech band detected by a microphone can be received. Vibration data in a vibration-channel speech band representative of vibrations detected by a sensor other than the microphone can be received. The microphone and the sensor can be associated with a head-mountable device (HMD). It is determined whether the audio data is causally related to the vibration data. If the audio data and the vibration data are causally related, an indication can be generated that the audio data contains HMD-wearer speech. Causally related audio and vibration data can be used to increase accuracy of text transcription of the HMD-wearer speech. If the audio data and the vibration data are not causally related, an indication can be generated that the audio data does not contain HMD-wearer speech.

Abstract: Embodiments include a computer-implemented method that includes receiving a search query associated with a user, identifying a set of search results responsive to the search query, identifying one or more search results of the set of search results that correspond to one or more items previously identified by the user as being of interest to the user, ranking the set of search results to generate a ranked set of search results, the ranking including boosting the rankings of the one or more search results that correspond to one or more items previously identified by the user as being of interest to the user, and providing search result content for display via a graphical user interface, the search result content including the ranked set of search results.

Abstract: Provided are methods and computer-readable media for providing recommended entities based on a user's external social graph, such as asymmetric social graph of a social networking service. In some embodiments, entities responsive to a search query or other request may be obtained. Each entity may be evaluated to determine if the entity is associated with a contact from a user's social graph. The association may include an evaluation (e.g., a rating, review, other evaluation or combination thereof) of the entity by the contact. Additionally, the contacts having associations with an entity may be ranked based on a relationship score with a user. The entities having associations with the contacts from a user's social graph may be provided as recommended entities to the user, and the association may be annotated to the recommended entity for viewing by the user.

Abstract: Methods and systems are provided for assisted speech input. In one example, the method may involve (a) designating a first node of a tree as a current node. Each node in the tree is associated with a speech input data, and the first node includes one or more child nodes. The method may further involve (b) removing all nodes from a first group of nodes, (c) copying each child node of the current node to the first group, (d) removing all nodes from a second group of nodes, (e) moving a selection of nodes from the first group to the second group, and (f) presenting information associated with each node in the second group. The method may include additional elements depending on whether there is a match between a received speech input and a child node of the current node.

Abstract: The present description discloses systems and methods for changing the state of a device. One embodiment may include a device configured to provide a device in a first state, receive a signal indicative of first angular data of the device, and compare the first angular data to a first threshold. The device may then execute instructions to initiate a timer when the first angular data is greater than the first threshold, receive a signal indicative of a second angular data of the device, and compare the second angular data to a second threshold. When the second angular data is less than the second threshold and the time passed is within a pre-determined time period, the device may execute instructions to transition the device to a second state.