Abstract: Provided are a terminal and server of a speaker-adaptation speech-recognition system and a method for operating the system.

Abstract: An input signal analyzer determines a boundary frequency within the limit of a range which does not exceed a first frequency from the mode of an input signal. A spectrum compressor compresses a power spectrum of frequencies in a band higher than the first frequency in a frequency direction. A gain corrector performs a gain correction on the compressed power spectrum. A spectrum synthesizer reflects the power spectrum outputted from the gain corrector in a band determined by both the first frequency and the boundary frequency. A frequency-to-time converter converts both a synthesized power spectrum provided by the spectrum synthesizer and a phase spectrum of the input signal into ones in the time domain, and outputs these spectra.

Abstract: In a case where dither processing is performed as image forming processing, a reference position of a dither matrix to be used is changed in units of predetermined printing execution. Such a change prevents continuous lighting of a light emitting element and fixation of a lighting position, and suppresses speed of deterioration in the light emitting element with time.

Abstract: A conferencing system and method involves conducting a conference between endpoints. The conference can be a videoconference in which audio data and video data are exchanged or can be an audio-only conference. Audio of the conference is obtained from one of the endpoints, and speech is detected in the obtained audio. The detected speech is analyzed to determine that the detected speech constitutes a speech fragment, and an indicia indicative of the determined speech fragment is generated. For a videoconference, the indicia can be a visual cue to be added to video for the given endpoint when displayed at other endpoints. For an audio-only conference, the indicia can be an audio cue to be added to the audio of the conference at the other end points.

Abstract: A color conversion processing apparatus acquires spot color information, which is capable of defining a spot color with device-dependent color values. The color conversion processing apparatus further acquires a reference profile and an updated profile, and using the spot color information, converts an image signal of a spot color plate into a first image signal of a process color plate. Then, by having the reference profile and the updated profile act successively thereon, the color conversion processing apparatus converts the first image signal into a second image signal of a process color plate.

Abstract: A method is disclosed. The method includes analyzing color planes of a compressed sheetside image and generating an overcoat plane based on the color planes.

Abstract: Systems and methods for printing data on a substrate including a color-changeable material are provided. One system includes a processing circuit and a device including an energy source. At least a portion of a printed publication is printed on the substrate using a commercial printing press based on fixed data. The device including the energy source is configured to add variable data to the substrate. The processing circuit is configured to receive the variable data and to control the energy source to change a color of the color-changeable material based on the variable data to provide at least a portion of the printed publication. The processing circuit is configured to control the energy source to change the color of the color-changeable material in-line with a flow of the substrate through one of a printing line, a finishing line, or a packaging line of the commercial printing press.

Abstract: Systems and methods for printing a 3D object on a three-dimensional (3D) printer are described. The methods semi-automatically or automatically delineate an item in an image, receive a 3D model of the item, matches said item to said 3D model, and send the matched 3D model to a 3D printer.

Abstract: Systems and methods of script identification in audio data obtained from audio data. The audio data is segmented into a plurality of utterances. A script model representative of a script text is obtained. The plurality of utterances are decoded with the script model. A determination is made if the script text occurred in the audio data.

Abstract: A system for dynamically generating a digital image comprising a security feature for a document. The system includes a processor 222 configured to receive data indicative of a security feature to be embedded in the document. The processor 222 generates a digital image having content at least partially specified by the received data. The processor 222 transmits a signal indicative of the generated digital image. The generated digital image has a foreground and a background, at least one of which includes a line screen pattern. The foreground and the background of the digital image are configured such that a scanned reproduction of an original printed version of the digital image is reproduced in an altered form relative to the original printed version.

Abstract: In a class of embodiments, an audio encoding system (typically, a perceptual encoding system that is configured to generate a single (“unified”) bitstream that is compatible with (i.e., decodable by) a first decoder configured to decode audio data encoded in accordance with a first encoding protocol (e.g., the multichannel Dolby Digital Plus, or DD+, protocol) and a second decoder configured to decode audio data encoded in accordance with a second encoding protocol (e.g., the stereo AAC, HE AAC v1, or HE AAC v2 protocol). The unified bitstream can include both encoded data (e.g., bursts of data) decodable by the first decoder (and ignored by the second decoder) and encoded data (e.g., other bursts of data) decodable by the second decoder (and ignored by the first decoder).

Abstract: An audio signal with a temporal sequence of blocks or frames is received or accessed. Features are determined as characterizing aggregately the sequential audio blocks/frames that have been processed recently, relative to current time. The feature determination exceeds a specificity criterion and is delayed, relative to the recently processed audio blocks/frames. Voice activity indication is detected in the audio signal. VAD is based on a decision that exceeds a preset sensitivity threshold and is computed over a brief time period, relative to blocks/frames duration, and relates to current block/frame features. The VAD and the recent feature determination are combined with state related information, which is based on a history of previous feature determinations that are compiled from multiple features, determined over a time prior to the recent feature determination time period. Decisions to commence or terminate the audio signal, or related gains, are outputted based on the combination.

Abstract: A method for performing speaker recognition comprises: estimating respective uncertainties of acoustic coverage of respective speech utterance(s) by first and second speakers, the acoustic coverage representing respective sounds used by the speakers when speaking; representing the respective uncertainties of acoustic coverage in a manner that allows for efficient memory usage by discarding dependencies between uncertainties of different sounds for the speakers; representing the respective uncertainties of acoustic coverage in a manner that allows for efficient computation by representing an inverse of the respective uncertainties of acoustic coverage and then discarding the dependencies between the uncertainties of different sounds for the speakers; and computing a score between the speech utterance(s) by the speakers in a manner that leverages the respective uncertainties of the acoustic coverage during the comparison, the score being indicative of a likelihood that the speakers are the same speaker.

Abstract: Systems and methods are provided for correcting a grammatical error in a text sequence. A first text sequence in a first language is received. The first text sequence is translated to a second language to provide a first translated text. The first text sequence is translated to a third language to provide a second translated text. The third language is different from the second language. The first translated text is translated to the first language to provide a first back translation. The second translated text is translated to the first language to provide a second back translation. A plurality of candidate text sequences that include features of the first back translation and the second back translation are determined. The plurality of candidate text sequences include alternative grammatical options for the first text sequence. The plurality of candidate text sequences are scored with the processing system.

Abstract: An approach is provided in which a linguistic analyzer engine generates a leverage value of a language translation supply chain that corresponds to an amount of suggested translations that are accepted by a professional linguist. The linguistic analyzer engine generates a factor value of the language translation supply chain that indicates a productivity of the user to convert the set of accepted translation into a set of final translations. In turn, the linguistic analyzer engine determines a performance efficiency of the language translation supply chain based upon the generated leverage value and the generated factor value, and evaluates the language translation supply chain accordingly. In one embodiment, the linguistic analyzer engine determines a performance efficiency of the language translation supply chain based on “n” distinct metric values associated with final translated segments.

Abstract: A device and method for use with an image recording device. The device having a background target and a first surface including the background target recessed therein. The device further including a substrate stabilizer configured to move a substrate having an image printed therein in closer proximity to the background target and below the first surface when activated.

Abstract: A method of providing a semantic data architecture includes providing a data model layer. The data model layer is formed by a processor, a storage device, a memory, and a communication interface in combination with a data model application program stored in the storage device. The processor, running the data model application program, is configured to use the storage device, memory, and communication interface to selectively receive source data from a source device, process the corresponding source data based on pre-defined data types and filtering terms to form semantic data arranged in a binary tree structure, and store the semantic data in the storage device. The method also includes providing a data filtering layer. The method may also include providing memory model, general purpose parser, backward inference, primitive functions, rewriting engine, and reasoning engine layers in various combinations. An apparatus for providing a semantic data architecture is also provided.

Abstract: There is described a computer implemented method for performing automatic audio production, comprising: receiving an audio signal to be processed; receiving semantic information; determining at least one semantic-based rule using the received semantic information, the semantic-based rule comprising production data that defines how the audio signal to be processed should be produced; processing the audio signal to be processed using the production data, thereby obtaining a produced audio signal; outputting the produced audio signal.

Abstract: A system, method and computer program for performing voice commands on a mobile device and presenting the results on an interactive timeline is disclosed. A user may utter a voice command into the microphone of their mobile device while an application is running. The voice command is processed to derive the intention of the user, specifically by determining the domain, at least one task and at least one parameter for the task from the voice command. A services component performs the task identified and presents the results on the mobile device screen. In various embodiments, the results are presented on a timeline and may be grouped together by domains and sorted by the time that the results were obtained. A search history view may also be viewed that includes search results sorted chronologically each of which is represented graphically by an icon that represents the category of each search.

Abstract: What is disclosed is a novel system and method for banding defect detection and analysis in digital imaging systems. The present method utilizes the gray levels of image regions and a collection of sequence of user images to improve the banding analysis. One embodiment hereof includes: segmenting images into regions; determining banding information for each page over a given sequence of images and detecting problem banding defect frequencies; estimating the banding amplitude(s) and average gray levels for each segmented region for each identified banding frequency(ies); and determining, through a process of interpolation, the banding amplitude for the image or sequence of images based on the banding amplitude and average gray levels of each region. Thereafter, notification can be provided to a key operator when the amplitude(s) are expected to exceed pre-determined levels over the course of a production run. The method demonstrates advantages in banding detection over whole-page methods.