Abstract: A method and system are provided. The method includes receiving, by a microphone and camera, user utterances indicative of user commands and associated user gestures for the user utterances. The method further includes parsing, by a hardware-based recognizer, sample utterances and the user utterances into verb parts and noun parts. The method also includes recognizing, by a hardware-based recognizer, the user utterances and the associated user gestures based on the sample utterances and descriptions of associated supporting gestures for the sample utterances. The recognizing step includes comparing the verb parts and the noun parts from the user utterances individually and as pairs to the verb parts and the noun parts of the sample utterances. The method additionally includes selectively performing a given one of the user commands responsive to a recognition result.

Abstract: A mistranscription generated by a speech recognition system is identified. A received utterance is matched to a first utterance member within a set of known utterance members. The matching operation matches fewer than the first plural number of words in the received utterance and the received utterance varies in a first particular manner as compared to a first word in a first slot in the first utterance member. The received utterance is sent to a mistranscription analyzer component which increments evidence that the received utterance is evidence of a mistranscription. Once the incremented evidence for the mistranscription exceeds a threshold, future received utterances containing the mistranscription are treated as though the first word was recognized.

Abstract: A physical device may include an embedded microprocessor and memory. The memory is loadable with information associated with a holder of the card device. The microprocessor communicates with another device responsive to detecting said another device is within a threshold proximity. The microprocessor further may negotiate for exchanging of the information with said another device based on current context.

Abstract: A first region of interest is determined by user input to a map interface. A set of locations of items of interest is determined located proximate to the region of interest. A background and a first set of representations are presented against the background on the device display according to a location and an orientation of the device, each representation of a respective item of interest located in the first region of interest.

Abstract: An exercise chatbot control method through augmented reality, system, and computer program product for controlling an exercise machine including a chatbot include determining a context of a user on the exercise machine via a sensor, learning an effectiveness of an activity for the user using the exercise machine, dynamically configuring the activity for the user on the exercise machine and a level of performance of the activity to an ideal activity level based on a user profile, the context of the user, and the effectiveness of the activity for the user, and providing an output including the ideal activity level from the chatbot to the user.

Abstract: An estimate is made of a time since a given presenting cancer would have first been detectable using a known diagnostic technique, and an estimate is also made of initial characteristics of the given presenting cancer at the time when it would have first been detectable using the known diagnostic technique. A first probability of the cancer being present in a first set of one or more clinically significant remote sites is determined based on the estimated initial characteristics. A second probability of the cancer being present in the first set of one or more clinically significant remote sites is determined based on actual current characteristics of the given presenting cancer. The first and second probabilities are used to estimate incremental risk of incurring presence of the cancer at the first set of one or more clinically significant remote sites by delaying therapy for a unit time.

Abstract: A method (and structure) includes forming a wireless ad hoc network with a plurality of sensors at a first location, the ad hoc network being a localized, decentralized network wherein each participating sensor has an equal status on the network for performing network functions and is free to associate with any other ad hoc network device in a link range of a vicinity of the first location. Data is transmitted from the plurality of sensors via the ad hoc network, for consumption by an at-home user located at a second location different from said first location. Each sensor indicates a location and a directivity of sensing in the vicinity of the first location, so that the plurality of sensors thereby can provide data sufficient for the at-home user to be immersed in an experience at the first location.

Abstract: A mistranscription generated by a speech recognition system is identified. A first class of utterance members is provided for use by the speech recognition system, each utterance class member consisting of a respective number of words. The first class is defined by a first common meaning and a first common system response if a class member of the first class is recognized. If the speech recognition system matches a received utterance to a first class member of the first class, the received utterance is sent to a mistranscription analyzer. The received utterance contains a mistranscription as compared to the first class member. Evidence is incremented by the mistranscription analyzer that the received utterance is evidence of the mistranscription of the first class member. If the incremented evidence for the mistranscription of the first class member exceeds a first threshold, a second class member is added to the first class of utterance members based on the mistranscription of the first class member.

Abstract: A parameter-based multi-model blending method and system are described. The method includes selecting a parameter of interest among parameters estimated by each of a set of individual models, running the set of individual models with a range of inputs to obtain a range of estimates of the parameters from each of the set of individual models, and identifying, for each of the set of individual models, critical parameters among the parameters estimated, the critical parameters exhibiting a specified correlation with an error in estimation of the parameter of interest. For each subspace of combinations of the critical parameters, obtaining a parameter-based blended model is based on blending the set of individual models in accordance with the subspace of the critical parameters, the subspace defining a sub-range for each of the critical parameters.

Abstract: A parameter-based multi-model blending method and system are described. The method includes selecting a parameter of interest among parameters estimated by each of a set of individual models, running the set of individual models with a range of inputs to obtain a range of estimates of the parameters from each of the set of individual models, and identifying, for each of the set of individual models, critical parameters among the parameters estimated, the critical parameters exhibiting a specified correlation with an error in estimation of the parameter of interest. For each subspace of combinations of the critical parameters, obtaining a parameter-based blended model is based on blending the set of individual models in accordance with the subspace of the critical parameters, the subspace defining a sub-range for each of the critical parameters.

Abstract: A mistranscription generated by a speech recognition system is identified. A set of known utterance members is provided for use by a speech recognition system. Each utterance member consists of a respective plural number of words. A received utterance is matched to a first utterance member within the set of known utterance members. The first utterance member is a closest matching utterance member and has a first plural number of words. The matching operation matches fewer than the first plural number of words in the received utterance and the received utterance varies in a first particular manner as compared to a first word in a first slot in the first utterance member. The received utterance is sent to a mistranscription analyzer component which increments evidence that the received utterance is evidence of a mistranscription.

Abstract: A system, a computer program product, and method for controlling synthesized speech output on a voice-controlled device. A sensor is used to capture an image of a face of a person. A database of previously stored images of facial features is accessed. In response to i) not recognizing the at least one person the voice-controlled device selects a first set of conversational starters; ii) recognizing the person and recognizing previous communications with the person, the voice-controlled device selects a second set of conversational starters; iii) recognizing the person and not recognizing previous communications with the person, the voice-controlled device selects a third set of conversational starters; or iv) recognizing the at least one person and recognizing previous communications with the person selecting but do not know the person's name selecting a fourth set of conversational starters. The voice controlled device outputs the selected set of conversational starters.

Abstract: A meeting summarization method, system, and computer program product, include capturing notes of a user including a time stamp from the user associated with a meeting, synchronizing an agenda of the meeting and the notes of the user based on a correlation between a time stamp of a topic on the agenda and a time stamp of the notes of the user, and analyzing the synchronized topic and the notes to determine highlights of the meeting based on a co-occurrence of the time stamp of the notes of the user and the time stamp of the topic on the agenda.

Abstract: A parameter-based multi-model blending method and system are described. The method includes selecting a parameter of interest among parameters estimated by each of a set of individual models, running the set of individual models with a range of inputs to obtain a range of estimates of the parameters from each of the set of individual models, and identifying, for each of the set of individual models, critical parameters among the parameters estimated, the critical parameters exhibiting a specified correlation with an error in estimation of the parameter of interest. For each subspace of combinations of the critical parameters, obtaining a parameter-based blended model is based on blending the set of individual models in accordance with the subspace of the critical parameters, the subspace defining a sub-range for each of the critical parameters.

Abstract: A computer-implemented preferred picture-taking method, system, and computer program product that learns from the photos taken in the same camera or other sources to know the pictures the camera owner likes, and generates associated templates, imports/exports the templates among cameras, other devices and media, automatically takes a photo when the target person in the camera view matches with the owner's personal preferences (a selected template), and analyzes images in the template and the current view in the camera, calculates the delta, and generates position and orientation adjustment actions in space.

Abstract: A meeting summarization method, system, and computer program product, include capturing notes of a user including a time stamp from the user associated with a meeting, synchronizing an agenda of the meeting and the notes of the user based on a correlation between a time stamp of a topic on the agenda and a time stamp of the notes of the user, and analyzing the synchronized topic and the notes to determine highlights of the meeting based on a co-occurrence of the time stamp of the notes of the user and the time stamp of the topic on the agenda.

Abstract: A computer-implemented preferred picture-taking method, system, and computer program product that learns from the photos taken in the same camera or other sources to know the pictures the camera owner likes, and generates associated templates, imports/exports the templates among cameras, other devices and media, automatically takes a photo when the target person in the camera view matches with the owner's personal preferences (a selected template), and analyzes images in the template and the current view in the camera, calculates the delta, and generates position and orientation adjustment actions in space.

Abstract: Embodiments for implementing an electronic communication coaching service by a processor are disclosed. An appropriateness of a communication may be interpreted prior to a user sending the communication to another party according a plurality of identified contextual factors. The user may be alerted to a possible negative impact of sending the communication to the another party if the interpreted appropriateness is less than a predetermined threshold. A delay in sending the communication may be suggested for a selected period of time to implement one or more suggestive corrective actions to the communication.

Abstract: A region of interest is determined by a location and an orientation of a device, wherein the region of interest is proximate to the device. A set of locations of items of interest is determined with respect to the region of interest. A background and a first set of representations against the background is presented on the device display according to the location and orientation of the device. Each representation is of a respective item of interest located in the region of interest. The region of interest is adjusted with a pinch gesture on the background, however, the presenting of the background does not change in response to the pinch gesture. Instead, the set of locations of one or more items of interest is determined with respect to the adjusted region of interest, and a second set of representations is presented against the background. Each representation of a respective item of interest is located in the adjusted region of interest.

Abstract: Methods, systems, and computer program products are provided for presenting a user interface on a display of a computer system. A presence of a second person in a proximity of a computer system other than a first person using the computer system is determined. A user interface is automatically selected based on the determined presence of the second person. In an absence of the second person, a voice interface is selected. When the second person is present, a text entry interface is selected. The selected user interface is presented to the first person on a display of the computer system.