Abstract: A processor controlled system for correlating an electronic index according to speaker for audio data being recorded in real time. The system includes a source of training data for each of the plurality of individual speakers and audio input system for providing real time audio data including speech for the individual speakers. The audio data is converted into spectral feature data by an audio processor, and is simultaneously recorded on a storage medium by a recording device. A system processor accepts the training data to create individual speaker models, which are combined in parallel to form a speaker network. The system processor then accepts the spectral feature data of the audio data and, using the speaker network, determines segments in the audio data corresponding to each speaker.

Abstract: A user-interactive method for use in a processor-controlled machine provides a user with the capability to establish associations among image segments in a data structure that indicate visually-displayed but otherwise not recognized or interpreted information, for the purpose of retrieving the unrecognized data from the data structure without performing a recognition operation. A user selects and designates a visually recognizable, but computationally unrecognized, displayed image segment as a coherent display object, called a key object, to function as an indexing mechanism. The user then associates the key object with data objects, which may also be computationally unrecognized, that are stored in a target data structure. The key object can be used as an access mechanism to retrieve the target data without recognition of either the key object or the target data.

Abstract: An interactive method and system to support and facilitate note-taking tasks in a variety of settings, primarily, though not exclusively, in real time. In one embodiment, the system user uses a stylus device and display to enter notes in the form of handwritten strokes that are stored and correlated with an address, such as a time provided by a system clock. Notes are collected in a data structure represented by a spatial region on the display called an address, or time, zone that is created when the user enters a gesture requesting an address from the system. All notes entered in a particular time zone region in the display area are stored in a portion of the data structure correlated with the time associated with that time zone region, and, while time zones are created in sequential time order, notes are may be entered in time zones in any sequence and still be correlated with that time zone.

Abstract: A user-interactive method for use in a processor controlled machine provides a user with the capability to retrieve and manipulate associations previously established among image segments in a single or in multiple data structures, where the image segments are stored as image data and not as recognized or interpreted information. The use of certain designated image segments, called key objects, for association with one or more other stored image segments in effect imposes a user-defined categorization structure on the image segments with which key objects are associated, producing groups of image segments associated with respective key object. The categorized information for a particular key object is retrievable and displayable with the key object image, also without performing a recognition operation, providing an indexing mechanism into the image data.

Abstract: An interactive processor-controlled system for entering and storing user information about an event that is being concurrently recorded in real time correlates the user information to user-requested addresses, such as time values stored with the recorded signals. The system includes a recording device for producing signals indicating recorded event data that includes periodic addresses, each of which indicates a portion of the recorded signals. An address source, such as a clock, is connected for providing address values to both the processor and the recording device. Using a pen-based user interface in one embodiment of the system, the system user specifically requests an address value in order to correlate user information to the signals being concurrently recorded. In response to a request for an address, the system establishes a spatial region on the display, called a time zone, into which the system user may enter information, in the form of handwritten strokes, about the event.