Abstract: An approach that manages moving surveillance cameras is described. In one embodiment, there is a system for managing images generated from a movable camera. In this embodiment, the system comprises a motion estimation component configured to determine camera motion. A camera motion alert component is configured to generate an alert in response to a determination that the camera has moved or the camera has ceased moving.

Abstract: A computer-implemented method of multisensory speech detection is disclosed. The method comprises determining an orientation of a mobile device and determining an operating mode of the mobile device based on the orientation of the mobile device. The method further includes identifying speech detection parameters that specify when speech detection begins or ends based on the determined operating mode and detecting speech from a user of the mobile device based on the speech detection parameters.

Abstract: A computer-implemented method of multisensory speech detection is disclosed. The method comprises determining an orientation of a mobile device and determining an operating mode of the mobile device based on the orientation of the mobile device. The method further includes identifying speech detection parameters that specify when speech detection begins or ends based on the determined operating mode and detecting speech from a user of the mobile device based on the speech detection parameters.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving data representing acoustic characteristics of a user's voice; selecting a cluster for the data from among a plurality of clusters, where each cluster includes a plurality of vectors, and where each cluster is associated with a speech model trained by a neural network using at least one or more vectors of the plurality of vectors in the respective cluster; and in response to receiving one or more utterances of the user, providing the speech model associated with the cluster for transcribing the one or more utterances

Abstract: Subject matter described in this specification can be embodied in methods, computer program products and systems relating to speech-to-text conversion. A first spoken input is received from a user of an electronic device (an “original utterance”). Based on the original utterance, a first set of character string candidates are determined that each represent the original utterance converted to textual characters and a selection of one or more of the character string candidates are provided in a format for display to the user. A second spoken input is received from the user and a determination is made that the second spoken input is a repeat utterance of the original utterance. Based on this determination and using the original utterance and the repeat utterance, a second set of character string candidates is determined.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for multilingual prosody generation. In some implementations, data indicating a set of linguistic features corresponding to a text is obtained. Data indicating the linguistic features and data indicating the language of the text are provided as input to a neural network that has been trained to provide output indicating prosody information for multiple languages. The neural network can be a neural network having been trained using speech in multiple languages. Output indicating prosody information for the linguistic features is received from the neural network. Audio data representing the text is generated using the output of the neural network.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating representation of acoustic sequences. One of the methods includes: receiving an acoustic sequence, the acoustic sequence comprising a respective acoustic feature representation at each of a plurality of time steps; processing the acoustic feature representation at an initial time step using an acoustic modeling neural network; for each subsequent time step of the plurality of time steps: receiving an output generated by the acoustic modeling neural network for a preceding time step, generating a modified input from the output generated by the acoustic modeling neural network for the preceding time step and the acoustic representation for the time step, and processing the modified input using the acoustic modeling neural network to generate an output for the time step; and generating a phoneme representation for the utterance from the outputs for each of the time steps.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating phoneme representations of acoustic sequences using projection sequences. One of the methods includes receiving an acoustic sequence, the acoustic sequence representing an utterance, and the acoustic sequence comprising a respective acoustic feature representation at each of a plurality of time steps; for each of the plurality of time steps, processing the acoustic feature representation through each of one or more long short-term memory (LSTM) layers; and for each of the plurality of time steps, processing the recurrent projected output generated by the highest LSTM layer for the time step using an output layer to generate a set of scores for the time step.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a first sequence-training speech model, a first batch of training frames that represent speech features of first training utterances; obtaining, by the first sequence-training speech model, one or more first neural network parameters; determining, by the first sequence-training speech model, one or more optimized first neural network parameters based on (i) the first batch of training frames and (ii) the one or more first neural network parameters; obtaining, by a second sequence-training speech model, a second batch of training frames that represent speech features of second training utterances; obtaining one or more second neural network parameters; and determining, by the second sequence-training speech model, one or more optimized second neural network parameters based on (i) the second batch of training frames and (ii) the one or more second neural network parameters.

Abstract: A computer-implemented method of multisensory speech detection is disclosed. The method comprises determining an orientation of a mobile device and determining an operating mode of the mobile device based on the orientation of the mobile device. The method further includes identifying speech detection parameters that specify when speech detection begins or ends based on the determined operating mode and detecting speech from a user of the mobile device based on the speech detection parameters.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for providing a representation based on structured data in resources. The methods, systems, and apparatus include actions of receiving target acoustic features output from a neural network that has been trained to predict acoustic features given linguistic features. Additional actions include determining a distance between the target acoustic features and acoustic features of a stored acoustic sample. Further actions include selecting the acoustic sample to be used in speech synthesis based at least on the determined distance and synthesizing speech based on the selected acoustic sample.

Abstract: The present invention relates to the measurement of human activities through video, particularly in retail environments. A method for measuring retail display effectiveness in accordance with an embodiment of the present invention includes: detecting a moving object in a field of view of an imaging device, the imaging device obtaining image data of a product display; tracking the object in the field of view of the imaging device to obtain a track; and obtaining statistics for the track with regard to the product display.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition using neural networks. A feature vector that models audio characteristics of a portion of an utterance is received. Data indicative of latent variables of multivariate factor analysis is received. The feature vector and the data indicative of the latent variables is provided as input to a neural network. A candidate transcription for the utterance is determined based on at least an output of the neural network.

Abstract: A computer-implemented method of multisensory speech detection is disclosed. The method comprises determining an orientation of a mobile device and determining an operating mode of the mobile device based on the orientation of the mobile device. The method further includes identifying speech detection parameters that specify when speech detection begins or ends based on the determined operating mode and detecting speech from a user of the mobile device based on the speech detection parameters.

Abstract: The system and method obscures descriptive image information about one or more images. The system comprises a selector for selecting the descriptive image information from one or more of the images, a transformer that transforms the descriptive information into a transformed state, and an authorizer that provides authorization criteria with the image. In a preferred embodiment, the transformed state is the respective image encoded with the descriptive information. The descriptive information can be obscured so that the descriptive information in the transformed state can be decoded only if one or more authorization inputs satisfy the authorization criteria.

Abstract: A solution for monitoring an area while accounting for camera motion and/or monitoring tasks is provided. For example, a physical area corresponding to a new field of view can be estimated for a camera for which motion is detected. The physical area can be estimated using a set of reference images previously captured by the camera, each of which comprises a unique field of view previously captured by the camera. Based on the physical area, a status for a monitoring task of the camera (e.g., an alert) can be updated and/or a location of an area for the monitoring task within an image captured by the camera can be updated. Further, based on the update(s), a field of view for a second camera can be automatically adjusted and/or a status for the monitoring task on the second camera can be automatically updated.

Abstract: A solution for monitoring an area includes using a region schema for the area. The region schema can include a set of prototypical tracks, each of which includes a start location, an end location, and a trajectory. The trajectory comprises an expected path an object will travel between the start location and the end location and can include variation information that defines an amount that an object can vary from the trajectory. The region schema can be generated by obtaining training object tracking data for the area for an initialization time period and evaluating the object tracking data to identify the set of prototypical tracks. While monitoring the area, monitored object tracking data is obtained for a monitored object in the area, and abnormal behavior of the monitored object is identified when the monitored object tracking data for the monitored object does not follow at least one of the set of prototypical tracks in the region schema.

Abstract: Multiple event types are monitored for events, and surveillance data is stored for each event. Surveillance data for a primary event of one event type can be presented to a user, and surveillance data for a set of related events corresponding to another event type can be presented based on a set of relatedness criteria and the surveillance data for the primary event. A user can adjust the relatedness criteria to filter/adjust the surveillance data presented for the related event(s). A user interface can enable the user to simultaneously view the surveillance data for both events and adjust the relatedness criteria. In an illustrative application, the invention is utilized to detect fraudulent merchandise returns in a retail store.

Abstract: The present invention provides an item scanning system in which an appearance of an item is received (e.g., at checkout). The appearance is captured with an image capture device (e.g., still frame camera, video camera, etc.) that can be collocated with a barcode scanner. In being collocated, the image capture device can be positioned proximate (e.g., near, attached to, etc.) the bar code scanner, integrated within a common housing/unit with the barcode scanner, etc. In any event, a search engine will then search a database of items based on the appearance to identify a set of items that potentially match the item. When one of the set of items is selected (e.g., by the checkout clerk), the selection will be received and stored for future investigation/auditing.

Abstract: A system, method and program product for providing a video surveillance system that enhances object detection by utilizing feedback from a tracking system to an object detection system. A system is provided that includes: a moving object detection system for detecting moving objects in a video input; an object tracking system for tracking a detected moving object in successive time instants; and a tracker feedback system for feeding tracking information from the object tracking system to the moving object detection system to enhance object detection.