Abstract: Embodiments provided herein generally relate to improved ultrasound visualization. In some embodiments, interoperative ultrasound displays may be enhanced for more accurate identification of cancerous and non-cancerous tissues.

Abstract: Embodiments provided herein generally relate to improved ultrasound visualization. In some embodiments, interoperative ultrasound displays may be enhanced for more accurate identification of cancerous and non-cancerous tissues.

Abstract: A system and method for performing an ultrasound may include generating a set of continuous tone signals for injection into an object. A corresponding set of reflected tone signals in the frequency domain may be received The set of reflected tone signals may be converted from the frequency domain to the time domain to create a set of time domain signals. At least one region of interest may be identified from the set of time domain signals. A window may be defined around the identified region of interest in the set of time domain signals. The windowed time domain signals may be converted from the time domain to the frequency domain to create a set of windowed frequency domain signals. At least one characteristic parameter may be calculated from the set of windowed frequency domain signals. Information may be output based on the calculate at least one characteristic parameter.

Abstract: The voice print system of the present invention is a subword-based, text-dependent automatic speaker verification system that embodies the capability of user-selectable passwords with no constraints on the choice of vocabulary words or the language. An estimate of the enrollement channel and of the test channel is developed for inverse filtering of the enrollment or the test speech, respectively. Automatic blind speech segmentation allows speech to be segmented into subword units without any linguistic knowledge of the password. Subword modeling is performed using a multiple classifiers. The system also takes advantage of such concepts as multiple classifier fusion and data resampling to successfully boost the performance. Key word/key phrase spotting is used to optimally locate the password phrase. Numerous adaptation techniques increase the flexibility of the base system, and include: channel adaptation, fusion adaptation, model adaptation and threshold adaptation.

Abstract: The voice print system of the present invention is a subword-based, text-dependent automatic speaker verification system that embodies the capability of user-selectable passwords with no constraints on the choice of vocabulary words or the language. Automatic blind speech segmentation allows speech to be segmented into subword units without any linguistic knowledge of the password. Subword modeling is performed using a multiple classifiers. The system also takes advantage of such concepts as multiple classifier fusion and data resampling to successfully boost the performance. Key word/key phrase spotting is used to optimally locate the password phrase. Numerous adaptation techniques increase the flexibility of the base system, and include: channel adaptation, fusion adaptation, model adaptation and threshold adaptation.

Abstract: The present invention applies speech recognition technology to remote access, verification, and identification applications. Speech recognition is used to raise the security level of many types of transaction systems which previously had serious safety drawbacks, including: point of sale systems, home authorization systems, systems for establishing a call to a called party (including prison telephone systems), internet access systems, web site access systems, systems for obtaining access to protected computer networks, systems for accessing a restricted hyperlink, desktop computer security systems, and systems for gaining access to a networked server. A general speech recognition system using communication is also presented.

Abstract: The voice print system of the present invention is a subword-based, text-dependent automatic speaker verification system that embodies the capability of user-selectable passwords with no constraints on the choice of vocabulary words or the language. Automatic blind speech segmentation allows speech to be segmented into subword units without any linguistic knowledge of the password. Subword modeling is performed using a multiple classifiers. The system also takes advantage of such concepts as multiple classifier fusion and data resampling to successfully boost the performance. Key word/key phrase spotting is used to optimally locate the password phrase. Numerous adaptation techniques increase the flexibility of the base system, and include: channel adaptation, fusion adaptation, model adaptation and threshold adaptation.

Abstract: The present invention is a reliable system and method for detecting a recorded voice, which can be employed independently or to provide protection from fraudulent use of a recording to defeat an automatic speaker recognition system. Several techniques and systems are employed either independently or in combination to verify that a detected audio sample is live and not recorded. Temporal speech characteristics of an audio sample are analyzed to determine whether a sample under examination is so similar to a previous sample as to indicate a recording. Communications channel characteristics are examined to determine whether an sample was recorded on a different channel from a predetermined communications channel. A pattern classifier is trained to distinguish between live and recorded speech. Finally, an “audio watermark” is used to determine whether a detected audio sample is a recording of a previous communication by an authorized user.

Abstract: The present invention relates to a pattern recognition system which uses data fusion to combine data from a plurality of extracted features and a plurality of classifiers. Speaker patterns can be accurately verified with the combination of discriminant based and distortion based classifiers. A novel approach using a training set of a "leave one out" data can be used for training the system with a reduced data set. Extracted features can be improved with a pole filtered method for reducing channel effects and an affine transformation for improving the correlation between training and testing data.

Abstract: A microscope having a high effective numerical aperture (NA) is achieved in an apparatus in which a real, three-dimensional image is formed of an object placed in an aperture at the apex of one of two facing, axially-aligned concave mirrors. The three-dimensional image is acquired by a video camera positioned in a counterpart aperture at the apex of the other mirror and the acquired image is processed by computer. The processing corrects the acquired image using the point spread function of the mirror system which was previously obtained by positioning a point source of light throughout the object space and measuring the pixel values recorded by the camera's array of sensing element while the camera was positioned at different axial distances in the image space.

Abstract: Processing of the two-dimensional image of a three-dimensional object, such as the human cornea, that has been illuminated with a structured light pattern. A specially filtered Fourier transform and inverse transform are processed to yield the instantaneous spatial frequencies of the illuminated pattern. The instantaneous spatial frequencies are mapped to the instantaneous dioptric powers or depth coordinates of the object's surface.

Abstract: Quantitative measurement of corneal surface topography is obtained by processing a two-dimensional image of the surface which reflects a quasi-periodic illuminated pattern, such as series of concentric rings, from a Placido disk source. The local spatial phases exhibited by the image of the illuminated pattern when reflected from the corneal surface and when reflected from standard specular surfaces are obtained by processing the images which includes use of specially filtered Fourier and inverse transforms. The distances at which predetermined local spatial phases are observed in the image from the cornea are compared with the distances at which these same phases are observed in the images of the standard surfaces. The distances are also compared with certain corresponding distances on the Placido disk source and converted to reveal the dioptric powers of refraction of the corneal surface without the need for parametric interpolation.

Abstract: A method and apparatus for improved mobile radio telecommunications employs the transmission of a pilot reference signal within the coherence band of the modulated carrier wave. The receiver in this system uses instantaneous phase estimation techniques of the pilot and carrier received waveforms to provide immunity from phase distortion introduced by the channel.

Abstract: An apparatus and methods characterized by an electric neural network including a node having multipliers respectively receiving signals representing feature vector elements and signals representing weight vector elements to produce product signals, a summer to add the product signals with a bias signal and output a sum signal to a hard limiter, the hard limiter for outputting a preliminary output signal of polarity. In response to the output signal of polarity, one of at least two logic branches is enabled. In response to such enabling, weight elements are assigned to a next weight vector to be used in subsequent processing by the one of the at least two logic branches until a label is to be produced.

Abstract: The present invention relates to a speaker recognition method and system which applies adaptive component weighting to each frame of speech for attenuating non-vocal tract components and normalizing speech components. A linear predictive all pole model is used to select frames for an adaptively weighted cepstrum. Frames with a predetermined number of resonances are selected for cepstrum analysis. An adaptively weighted cepstrum is determined from a new transfer function. A normalized cepstrum is determined having improved characteristics for speech components. From the improved speech components, improved speaker recognition over a channel is obtained.

Abstract: A toy helmet that permits the wearer to speak as to generate unintelligible noise so far as bystanders are concerned but which can be understood by another child wearing an identical helmet. Each helmet is equipped with internal and external microphones and an external speaker and internal earphones. Scrambler/descrambler circuitry is selectively connectable by means of a push-to-talk switch that delivers speech from the internal microphone to the external loudspeaker of the first helmet. The external microphone and the corresponding scambler/descrambler circuitry and push-to-talk switch of the second helmet delivers unscrambled speech to its internal earphone to permit the two helmet wearers to communicate intelligibly with one another. The scrambler/descrambler circuitry samples the low-pass filtered signals applied to its microphones at a sampling rate equal to the cut-off frequency of the low-pass filter.

Abstract: Apparatus and method for accurately quantifying the instantaneous radius curvature of a large plurality of points on the corneal surface is disclosed. A video image of the corneal surface accurately positioned at a predetermined point on the optic axis of measurement is obtained. The predetermined point is defined by intersecting low power laser beams. The video image is radially scanned from an original position at point defined by the intersection of the visual axis with corneal surface. Accurate measurements of the two-dimensional image radii of a plurality of illuminated mires reflective upon the corneal surface are made and corrected for camera distortions, quantization error and the different magnification occurring for different size corneas. The instrumentation is calibrated by using a plurality of mirror-like spheres of precisely known spherical radii.

Abstract: A device for causing concentric circles of illuminated light to be reflected from the human cornea. The device includes a cylindrical surface which is open at both ends. At one end the eye looks into the cylinder of the device and at the other end a camera or observer can view the illuminated rings on the cornea. The cylinder is advantageously made of transparent plastic or glass having an opaque coating. A lamp box is affixed to an uncoated portion of the device. The coating of the cylindrical surface through is interrupted to define clear rings on the cylindrical surface which light from the lamp box is conducted to be reflected from the cornea.