中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

59 records (took 0.021 seconds)

    Stimmentransformation mit codierten Informationen
    41.
    发明专利
    Stimmentransformation mit codierten Informationen 未知

    公开(公告)号：DE112012000698B4

    公开(公告)日：2019-04-18

    申请号：DE112012000698

    申请日：2012-03-13

    Applicant: IBM

    Inventor： KONS ZVI ,  HOORY RON ,  NAHAMOO DAVID ,  BEN-DAVID SHAY

    IPC: G10L21/00

    Abstract: Verfahren zur Stimmentransformation, wobei das Verfahren aufweist:Transformieren einer Quellsprachaufnahme einer Person unter Verwendung von Transformationsparametern, so dass die Transformation der Quellsprachaufnahme den Eindruck vermittelt, die enthaltene Sprache stamme von einer anderen Person;Codieren von Informationen zu den Transformationsparametern in eine Sprachausgabe unter Verwendung von Steganografie;wobei die Quellsprachaufnahme unter Verwendung der Sprachausgabe und der Informationen zu den Transformationsparametern rekonstruierbar ist.

    Voice print tagging of interactive voice response sessions
    43.
    发明专利
    Voice print tagging of interactive voice response sessions 未知

    公开(公告)号：GB2527980A

    公开(公告)日：2016-01-06

    申请号：GB201517785

    申请日：2014-02-24

    Applicant: IBM

    Inventor： MOORE VICTOR ,  NUSBICKEL WENDI LYNN ,  NAHAMOO DAVID ,  VAVRA CHRISTOPHER JAMES

    IPC: H04M3/493 ,  H04M3/38

    Abstract: Embodiments of the invention provide a method, system and computer program product for voice print tagging for interactive voice response (IVR) session management. In an embodiment of the invention, a method of voiceprint tagging for IVR session management is provided. The method includes establishing an IVR session for a caller from over a network and presenting a portion of the IVR session to the caller over the network. The method also includes storing a voiceprint tag in memory associating a voiceprint of the caller with a portion of the IVR session. Finally, the method includes responding to a premature termination of the IVR session by re-establishing the prematurely terminated IVR session with the caller at the portion of the IVR session indicated by the voiceprint tag of the caller.

    Secure facilities access
    44.
    发明专利
    Secure facilities access 未知

    公开(公告)号：GB2498042B

    公开(公告)日：2014-05-14

    申请号：GB201220270

    申请日：2012-11-12

    Applicant: IBM

    Inventor： HOORY RON ,  NAHAMOO DAVID ,  SICCONI ROBERTO ,  CONNELL JONATHAN HUDSON II ,  BEN-DAVID SHAY

    IPC: G07C9/00 ,  G06F21/32 ,  G06K9/00

    Abstract: Method, system, and computer program product are provided for secure facilities access. The method may include: receiving an access request from a mobile device to a secure facility; authenticating a user using multifactor biometric authentication with data from the mobile device; obtaining data from one or more fixed sensor devices at a location in the physical vicinity of the secure facility; cross-validating data from the mobile device with data from the one or more fixed sensor devices; and granting access to the secure facility if the authentication of the user and the cross-validation are successful. The cross-validating may determine that the access request from the mobile device is made in the vicinity of the secure facility using data from the one or more fixed sensor devices.

    Stimmentransformation mit codierten Informationen
    45.
    发明专利
    Stimmentransformation mit codierten Informationen 未知

    公开(公告)号：DE112012000698T5

    公开(公告)日：2013-11-14

    申请号：DE112012000698

    申请日：2012-03-13

    Applicant: IBM

    Inventor： NAHAMOO DAVID ,  KONS ZVI ,  HOORY RON ,  BEN-DAVID SHAY

    IPC: G10L21/00

    Abstract: Es werden ein Verfahren, ein System und ein Computerprogrammprodukt zur Stimmentransformation bereitgestellt. Das Verfahren weist ein Transformieren einer Quellsprache unter Verwendung von Transformationsparametern und ein Codieren von Informationen zu den Transformationsparametern in eine ausgegebene Sprache unter Verwendung von Steganografie auf, wobei die Quellsprache unter Verwendung der ausgegebenen Sprache und der Informationen zu den Transformationsparametern rekonstruiert werden kann. Außerdem wird ein Verfahren zum Rekonstruieren einer Stimmentransformation bereitgestellt, wobei das Verfahren aufweist: Empfangen einer ausgegebenen Sprache eines Stimmentransformationssystems, wobei es sich bei der ausgegebenen Sprache um transformierte Sprache handelt, die codierte Informationen zu den Transformationsparametern unter Verwendung von Steganografie aufweist; Entnehmen der Informationen zu den Transformationsparametern; und Ausführen einer Umkehrtransformation der ausgegebenen Sprache, um eine Annäherung an eine ursprüngliche Quellsprache zu erhalten.

    47.
    发明专利
    未知

    公开(公告)号：DE69720087T2

    公开(公告)日：2004-02-26

    申请号：DE69720087

    申请日：1997-01-17

    Applicant: IBM

    Inventor： GOPALAKRISHNAN PONANI ,  NAHAMOO DAVID ,  PANMANABHAN MUKUND ,  POLYMENAKOS LAZAROS

    IPC: G10K11/178 ,  G10L21/02

    Abstract: A method and apparatus for removing the effect of background music or noise from speech input to a speech recognizer so as to improve recognition accuracy has been devised. Samples of pure music or noise related to the background music or noise that corrupts the speech input are utilized to reduce the effect of the background in speech recognition. The pure music and noise samples can be obtained in a variety of ways. The music or noise corrupted speech input is segmented in overlapping segments and is then processed in two phases: first, the best matching pure music or noise segment is aligned with each speech segment; then a linear filter is built for each segment to remove the effect of background music or noise from the speech input and the overlapping segments are averaged to improve the signal to noise ratio. The resulting acoustic output can then be fed to a speech recognizer.

    48.
    发明专利
    未知

    公开(公告)号：DE69425412T2

    公开(公告)日：2001-03-08

    申请号：DE69425412

    申请日：1994-10-21

    Applicant: IBM

    Inventor： BELLEGARDA EVELINE JEANNINE ,  BELLEGARDA JEROME RENE ,  NAHAMOO DAVID ,  NATHAN KRISHNA SUNDARAM

    IPC: G06K9/70 ,  G06K9/62 ,  G06K9/68

    Abstract: An automatic handwriting recognition system wherein each written (chirographic) manifestation of each character is represented by a statistical model (called a hidden Markov model). The system implements a method which entails sampling a pool of independent writers and deriving a hidden Markov model for each particular character (allograph) which is independent of a particular writer. The HMMs are used to derive a chirographic label alphabet which is independent of each writer. This is accomplished during what is described as the training phase of the system. The alphabet is constructed using supervised techniques. That is, the alphabet is constructed using information learned in the training phase to adjust the result according to a statistical algorithm (such as a Viterbi alignment) to arrive at a cost efficient recognition tool. Once such an alphabet is constructed a new set of HMMs can be defined which more accurately reflects parameter typing across writers. The system recognizes handwriting by applying an efficient hierarchical decoding strategy which employs a fast match and a detailed match function, thereby making the recognition cost effective.

    49.
    发明专利
    未知

    公开(公告)号：DE69424196T2

    公开(公告)日：2000-12-21

    申请号：DE69424196

    申请日：1994-01-12

    Applicant: IBM

    Inventor： BELLEGARDA JEROME RENE ,  NAHAMOO DAVID ,  NATHAN KRISHNA SUNDARAM

    IPC: G06K9/46 ,  G06K9/03 ,  G06K9/22 ,  G06K9/62 ,  G06K9/68

    Abstract: Methods and apparatus are disclosed for recognizing handwritten characters in response to an input signal from a handwriting transducer. A feature extraction and reduction procedure is disclosed that relies on static or shape information, wherein the temporal order in which points are captured by an electronic tablet may be disregarded. A method of the invention generates and processes the tablet data with three independent sets of feature vectors which encode the shape information of the input character information. These feature vectors include horizontal (x-axis) and vertical (y-axis) slices of a bit-mapped image of the input character data, and an additional feature vector to encode an absolute y-axis displacement from a baseline of the bit-mapped image. It is shown that the recognition errors that result from the spatial or static processing are quite different from those resulting from temporal or dynamic processing. Furthermore, it is shown that these differences complement one another. As a result, a combination of these two sources of feature vector information provides a substantial reduction in an overall recognition error rate. Methods to combine probability scores from dynamic and the static character models are also disclosed.

Patent Agency Ranking