Abstract: Apparatuses, systems, and techniques to facilitate feature detection of a manufactured object such as a PCB using combined images of said manufactured object. In at least one embodiment, an automated optical inspection system (AOI) comprising one or more neural networks can infer based, at least in part, on combined images of a PCB the existence of defects on said PCB.

Abstract: A system to adaptively control multimedia communication sessions includes a mediator unit in an intermediary communication position between two or more remote clients and a media infrastructure. The mediator unit includes a receiver, a transmitter and a control processor that controls the receiver and the transmitter. The mediator unit communicates remote clients across a communication network, where the first client initiates a communication session and the mediator unit assigns a unique session identifier to the communication message. Additional remote clients send join requests including the unique session identifier, and the mediator unit acts as a back-to-back user agent to pass messages between two remote clients of a two-client communication session.

Abstract: A method for correlating multiple collaborative sessions occurring on multiple single-modality systems includes creating a respective collaborative element containing metadata about each respective collaborative session, associating each collaborative element with a corresponding collaborative conversation, providing an overlaying control plane across the multiple single-modality systems, computing and storing conversational context of user actions within the collaborative sessions. The method further includes performing data aggregation of data within the multiple collaborative sessions, publishing one or more messages providing information regarding changes in the multiple collaborative sessions, switching modalities by entities participating in one or more of the multiple collaborative sessions, wherein the entities can follow session conversations by accessing the published one or more messages, and embedding a link in a single-modality system user interface referring to a previous session.

Abstract: A system to adaptively control multimedia communication sessions includes a mediator unit in an intermediary communication position between two or more remote clients and a media infrastructure. The mediator unit includes a receiver, a transmitter and a control processor that controls the receiver and the transmitter. The mediator unit communicates remote clients across a communication network, where the first client initiates a communication session and the mediator unit assigns a unique session identifier to the communication message. Additional remote clients send join requests including the unique session identifier, and the mediator unit acts as a back-to-back user agent to pass messages between two remote clients of a two-client communication session.

Abstract: A method and apparatus for reducing a set of reference identifiers to a candidate subset of reference identifiers. The reference identifiers are associated in memory with a plurality of index codes. A user provides an input identifier, causing a recognizing device of the present invention to produce a recognized identifier on the basis of the input identifier. The present invention determines an index code based on the recognized identifier and on the basis of a plurality of pre-stored confusion sets of characters that group together in individual confusion sets those characters having a relatively high likelihood of being confused with each other by the recognizing device. After matching the determined index code with one of the reference index codes, the present invention determines which reference index codes are within a predetermined distance of the matched reference index code.

Abstract: A multiple confidence measures subsystem of an automated speech recognition system allows otherwise independent confidence measures to be integrated and used for both training and testing on a consistent basis. Speech to be recognized is input to a speech recognizer and a recognition verifier of the multiple confidence measures subsystem. The speech recognizer generates one or more confidence measures. The speech recognizer preferably generates a misclassification error (MCE) distance as one of the confidence measures. The recognized speech output by the speech recognizer is input to the recognition verifier, which outputs one or more confidence measures. The recognition verifier preferably outputs a misverification error (MVE) distance as one of the confidence measures. The confidence measures output by the speech recognizer and the recognition verifier are normalized and then input to an integrator.

Abstract: A method and apparatus for recognizing an identifier entered by a user. A caller enters a predetermined identifier through a telephone handset. A signal representing the entered identifier is transmitted to a remote recognizer, which responds to the signal by producing a recognized output intended to match the entered identifier. The present invention compares this recognized identifier with a list of valid reference identifiers to determine which one of these reference identifiers most likely matches the entered identifier. In performing this determination, the present invention employs a confusion matrix, which is an arrangement of probabilities that indicate the likelihood that a given character in a particular character position of the reference identifier would be recognized by the recognizer as a character in the corresponding character position of the recognized identifier.