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.
Type:
Grant
Filed:
November 21, 1997
Date of Patent:
March 25, 2003
Inventors:
Manish Sharma, Xiaoyu Zhang, Richard J. Mammone
Abstract: The model adaptation system of the present invention is a speaker verification system that embodies the capability to adapt models learned during the enrollment component to track aging of a user's voice. The system has the advantage of only requiring a single enrollment for the user. The model adaptation system and methods can be applied to several types of speaker recognition models including neural tree networks (NTN), Gaussian Mixture Models (GMMs), and dynamic time warping (DTW) or to multiple models (i.e., combinations of NTNs, GMMs and DTW). Moreover, the present invention can be applied to text-dependent or text-independent systems.
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 invention relates to an improved hide-curing additive comprising an effective biocidal amount of an essential oil and a non-ionic surfactant. The improved additive provides an effective cure for the hides, is environmentally safe and economical.
Type:
Grant
Filed:
September 23, 1998
Date of Patent:
September 17, 2002
Assignee:
Birko Corporation
Inventors:
Dana J. Johnson, Terry L. McAninch, Frederick W. Holzhauer
Abstract: An improved method of fragmenting and removing soft tissues of a patient is disclosed. More particularly, the method includes steps for the surgical removal of unwanted fatty tissues using an ultrasonic frequency vibratory probe and a separate multi-lumen suction and irrigation cannula. The ultrasonic frequency vibratory probe and the multi-lumen suction and irrigation cannula are separate instruments that are used to separate the tissue fragmentation and removal processes, thereby decreasing procedure time and reducing trauma to tissues.
Abstract: In general the ultrasonic probe for improved fragmentation is comprised of a longitudinal shank having a proximal end, a distal end, and a shaft. The shaft joins the proximal end and the distal end. The proximal end of the longitudinal shank has a connector for connecting the longitudinal shank to a source of ultrasonic vibrational energy. The distal end of the longitudinal shank may have a blunt or bullet-nosed tip. The shaft has one or more grooves near the tip which circumscribe the shaft of the longitudinal shank.
The walls of the one or more grooves in the shaft of the longitudinal shank provide surface area on the distal end of the ultrasonic probe in planes generally perpendicular to the axis of the ultrasonic probe. The additional surface area increases the tissue fragmenting surface area of the distal end of the ultrasonic probe without increasing the diameter of the distal end of the ultrasonic probe.
Abstract: In general a hand-held ultrasonic surgical apparatus with a focusing lens for fragmenting or emulsifying a predetermined volume of a medium located generally near a focal length from a concave surface of the focusing lens without significant heating of the medium includes a housing to be held and manipulated by a surgeon or physician and an acoustic assembly mounted within the housing. The acoustic assembly has a resonant vibratory frequency that is primarily determined by the length of the acoustic assembly and an axis along which the ultrasonic vibratory energy is directed. The preferred range for the resonant vibratory frequency to achieve sufficient focusing and sufficient ultrasonic power to fragment or emulsify tissue is between 100 kHz and 250 kHz. The acoustic assembly includes an ultrasonic motor, a rear driver, a front driver, a compression fastener, and a focusing lens.
Abstract: A tripe bleaching composition facilitating the economical processing of tripe comprising:
Peracid precursor
7.5-14% by wt.
Hydrogen Peroxide
9.0-46% by wt.
Water
balance.
The peracid precursor may be at least one member selected from the group consisting of tartaric, malic, maleic and acetic acid, with tartaric or malic acid being particularly preferred.
Type:
Grant
Filed:
July 9, 1998
Date of Patent:
February 19, 2002
Inventors:
Terry L. McAninch, Frederick W. Holzhauer