Abstract: A system that handles delivery of a service through a client device or a secondary device paired with the client device, includes an interactive service provider and the client device. The interactive service provider inserts at least one of digital watermarks, fingerprints, and trigger identifiers at event opportunities in media content. The client device detects at least one of the inserted digital watermarks, the digital fingerprints, and the inserted trigger identifiers in the media content. The client device further renders overlay graphics on the media content and activates at least one of input devices in vicinity of the client device or the rendered overlay graphics. The client device receives trigger responses over an activated overlay graphic, via the activated input devices. The client device further displays an interactive view on the client device, to enable delivery of services in response to the received trigger responses.

Abstract: A method, system and apparatus are shown for identifying non-language speech sounds in a speech or audio signal. An audio signal is segmented and feature vectors are extracted from the segments of the audio signal. The segment is classified using a hidden Markov model (HMM) that has been trained on sequences of these feature vectors. Post-processing components can be utilized to enhance classification. An embodiment is described in which the hidden Markov model is used to classify a segment as a language speech sound or one of a variety of non-language speech sounds. Another embodiment is described in which the hidden Markov model is trained using discriminative learning.

Abstract: A method, system and apparatus are shown for identifying non-language speech sounds in a speech or audio signal. An audio signal is segmented and feature vectors are extracted from the segments of the audio signal. The segment is classified using a hidden Markov model (HMM) that has been trained on sequences of these feature vectors. Post-processing components can be utilized to enhance classification. An embodiment is described in which the hidden Markov model is used to classify a segment as a language speech sound or one of a variety of non-language speech sounds. Another embodiment is described in which the hidden Markov model is trained using discriminative learning.

Abstract: A system and method for the management of one or more wide area or local area network connected devices by a collocated managing device. The managing device includes communications connectivity to each of the managed devices via a console connection and optionally via shared local area network connections. Additionally, the managing device includes a control system and a database. The device is designed to operate securely and operate autonomously or coupled with an external device, for example a management system, or a user.