Patents by Inventor Bhuvana Ramabhadran

Bhuvana Ramabhadran has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Accuracy improvement of spoken queries transcription using co-occurrence information
    Patent number: 9330661
    Abstract: Techniques disclosed herein include systems and methods for voice-enabled searching. Techniques include a co-occurrence based approach to improve accuracy of the 1-best hypothesis for non-phrase voice queries, as well as for phrased voice queries. A co-occurrence model is used in addition to a statistical natural language model and acoustic model to recognize spoken queries, such as spoken queries for searching a search engine. Given an utterance and an associated list of automated speech recognition n-best hypotheses, the system rescores the different hypotheses using co-occurrence information. For each hypothesis, the system estimates a frequency of co-occurrence within web documents. Combined scores from a speech recognizer and a co-occurrence engine can be combined to select a best hypothesis with a lower word error rate.
    Type: Grant
    Filed: January 16, 2014
    Date of Patent: May 3, 2016
    Assignee: Nuance Communications, Inc.
    Inventors: Jonathan Mamou, Abhinav Sethy, Bhuvana Ramabhadran, Ron Hoory, Paul Joseph Vozila, Nathan Bodenstab
  • Security system based on questions that do not publicly identify the speaker
    Patent number: 9311461
    Abstract: A method and system for authenticating a user seeking access to a secured system in a public area. Access is granted when a user demonstrates sufficient knowledge of the user's personal characteristics stored in the system. The user initiates the access process by tapping into the stored characteristics without overtly stating information that may be overheard. The user statements reflect an awareness about the categories of user uniqueness without divulging details. The system response statements act to elicit further information from the user for response and the response statements are scored. After a cumulative score threshold is met, the user is granted access.
    Type: Grant
    Filed: April 16, 2008
    Date of Patent: April 12, 2016
    Assignee: International Business Machines Corporation
    Inventors: Sara H. Basson, Dimitri Kanevsky, Edward E. Kelley, Bhuvana Ramabhadran
  • Simulation method and system
    Patent number: 9294814
    Abstract: A simulation method and system. A computing system receives a first audio and/or video data stream. The first audio and/or video data stream includes data associated with a first person. The computing system monitors the first audio and/or video data stream. The computing system identifies emotional attributes comprised by the first audio and/or video data stream. The computing system generates a second audio and/or video data stream associated with the first audio and/or video data stream. The second audio and/or video data stream includes the data without the emotional attributes. The computing system stores the second audio and/or video data stream.
    Type: Grant
    Filed: May 24, 2013
    Date of Patent: March 22, 2016
    Assignee: International Business Machines Corporation
    Inventors: Sara H. Basson, Dimitri Kanevsky, Edward Emile Kelley, Bhuvana Ramabhadran
  • USER AUTHENTICATION VIA EVOKED POTENTIAL IN ELECTROENCEPHALOGRAPHIC SIGNALS
    Publication number: 20160021106
    Abstract: Techniques are disclosed for authentication and identification of a user by use of an electroencephalographic (EEG) signal. For example, a method for authenticating a user includes the following steps. At least one electroencephalographic response is obtained from a user in accordance with perceptory stimuli presented to the user. The user is authenticated based on the obtained electroencephalographic response. The authenticating step may be based on detection of an event-related potential in the obtained electroencephalographic response. The event-related potential may be a P300 event-related potential. The method may also include the step of enrolling the user prior to authenticating the user. The enrolling step may include a supervised enrollment procedure or an unsupervised enrollment procedure.
    Type: Application
    Filed: September 28, 2015
    Publication date: January 21, 2016
    Inventors: Jiri Navratil, Bhuvana Ramabhadran
  • User authentication via evoked potential in electroencephalographic signals
    Patent number: 9226698
    Abstract: Techniques are disclosed for authentication and identification of a user by use of an electroencephalographic (EEG) signal. For example, a method for authenticating a user includes the following steps. At least one electroencephalographic response is obtained from a user in accordance with perceptory stimuli presented to the user. The user is authenticated based on the obtained electroencephalographic response. The authenticating step may be based on detection of an event-related potential in the obtained electroencephalographic response. The event-related potential may be a P300 event-related potential. The method may also include the step of enrolling the user prior to authenticating the user. The enrolling step may include a supervised enrollment procedure or an unsupervised enrollment procedure.
    Type: Grant
    Filed: May 12, 2015
    Date of Patent: January 5, 2016
    Assignee: International Business Machines Corporation
    Inventors: Jiri Navratil, Bhuvana Ramabhadran
  • Translating between spoken and written language
    Patent number: 9195650
    Abstract: Techniques for converting spoken speech into written speech are provided. The techniques include transcribing input speech via speech recognition, mapping each spoken utterance from input speech into a corresponding formal utterance, and mapping each formal utterance into a stylistically formatted written utterance.
    Type: Grant
    Filed: September 23, 2014
    Date of Patent: November 24, 2015
    Assignee: Nuance Communications, Inc.
    Inventors: Sara H. Basson, Rick A. Hamilton, II, Dan Ning Jiang, Dimitri Kanevsky, David Nahamoo, Michael A. Picheny, Bhuvana Ramabhadran, Tara N. Sainath
  • DEEP SCATTERING SPECTRUM IN ACOUSTIC MODELING FOR SPEECH RECOGNITION
    Publication number: 20150317990
    Abstract: Deep scattering spectral features are extracted from an acoustic input signal to generate a deep scattering spectral feature representation of the acoustic input signal. The deep scattering spectral feature representation is input to a speech recognition engine. The acoustic input signal is decoded based on at least a portion of the deep scattering spectral feature representation input to a speech recognition engine.
    Type: Application
    Filed: May 2, 2014
    Publication date: November 5, 2015
    Inventors: Petr Fousek, Vaibhava Goel, Brian E.D. Kingsbury, Etienne Marcheret, Shay Maymon, David Nahamoo, Tara N. Sainath, Bhuvana Ramabhadran
  • USER AUTHENTICATION VIA EVOKED POTENTIAL IN ELECTROENCEPHALOGRAPHIC SIGNALS
    Publication number: 20150238122
    Abstract: Techniques are disclosed for authentication and identification of a user by use of an electroencephalographic (EEG) signal. For example, a method for authenticating a user includes the following steps. At least one electroencephalographic response is obtained from a user in accordance with perceptory stimuli presented to the user. The user is authenticated based on the obtained electroencephalographic response. The authenticating step may be based on detection of an event-related potential in the obtained electroencephalographic response. The event-related potential may be a P300 event-related potential. The method may also include the step of enrolling the user prior to authenticating the user. The enrolling step may include a supervised enrollment procedure or an unsupervised enrollment procedure.
    Type: Application
    Filed: May 12, 2015
    Publication date: August 27, 2015
    Inventors: Jiri Navratil, Bhuvana Ramabhadran
  • AUTOMATED TEXT ANNOTATION FOR CONSTRUCTION OF NATURAL LANGUAGE UNDERSTANDING GRAMMARS
    Publication number: 20150242387
    Abstract: Aspects described herein provide various approaches to annotating text samples in order to construct natural language grammars. A text sample may be selected for annotation. A set of annotation candidates may be generated based on the text sample. A classifier may be used to score the set of annotation candidates in order to obtain a set of annotation scores. One of the annotation candidates may be selected as a suggested annotation for the text sample based on the set of annotation scores. A grammar rule may be derived based on the suggested annotation, and a grammar may be configured to include the annotation-derived grammar rule.
    Type: Application
    Filed: February 24, 2014
    Publication date: August 27, 2015
    Applicant: Nuance Communications, Inc.
    Inventors: Leonid Rachevsky, Raimo Bakis, Bhuvana Ramabhadran
  • Methods and apparatus for performing transformation techniques for data clustering and/or classification
    Patent number: 9117444
    Abstract: Some aspects include transforming data, at least a portion of which has been processed to determine at least one representative vector associated with each of a plurality of classifications associated with the data to obtain a plurality of representative vectors. Techniques comprise determining a first transformation based, at least in part, on the plurality of representative vectors, applying at least the first transformation to the data to obtain transformed data, and fitting a plurality of clusters to the transformed data to obtain a plurality of established clusters. Some aspects include classifying input data by transforming the input data using at least the first transformation and comparing the transformed input data to the established clusters.
    Type: Grant
    Filed: August 8, 2012
    Date of Patent: August 25, 2015
    Assignee: Nuance Communications, Inc.
    Inventors: Leonid Rachevsky, Dimitri Kanevsky, Bhuvana Ramabhadran
  • Methods and apparatus for performing transformation techniques for data clustering and/or classification
    Patent number: 9064491
    Abstract: Some aspects include transforming data, at least a portion of which has been processed to determine frequency information associated with features in the data. Techniques include determining a first transformation based, at least in part, on the frequency information, applying at least the first transformation to the data to obtain transformed data, and fitting a plurality of clusters to the transformed data to obtain a plurality of established clusters. Some aspects include classifying input data by transforming the input data using at least the first transformation and comparing the transformed input data to the established clusters.
    Type: Grant
    Filed: August 8, 2012
    Date of Patent: June 23, 2015
    Assignee: Nuance Communications, Inc.
    Inventors: Leonid Rachevsky, Dimitri Kanevsky, Bhuvana Ramabhadran
  • User authentication via evoked potential in electroencephalographic signals
    Patent number: 9058473
    Abstract: Techniques are disclosed for authentication and identification of a user by use of an electroencephalographic (EEG) signal. For example, a method for authenticating a user includes the following steps. At least one electroencephalographic response is obtained from a user in accordance with perceptory stimuli presented to the user. The user is authenticated based on the obtained electroencephalographic response. The authenticating step may be based on detection of an event-related potential in the obtained electroencephalographic response. The event-related potential may be a P300 event-related potential. The method may also include the step of enrolling the user prior to authenticating the user. The enrolling step may include a supervised enrollment procedure or an unsupervised enrollment procedure.
    Type: Grant
    Filed: August 29, 2007
    Date of Patent: June 16, 2015
    Assignee: International Business Machines Corporation
    Inventors: Jiri Navratil, Bhuvana Ramabhadran
  • LEARNING FRONT-END SPEECH RECOGNITION PARAMETERS WITHIN NEURAL NETWORK TRAINING
    Publication number: 20150161995
    Abstract: Techniques for learning front-end speech recognition parameters as part of training a neural network classifier include obtaining an input speech signal, and applying front-end speech recognition parameters to extract features from the input speech signal. The extracted features may be fed through a neural network to obtain an output classification for the input speech signal, and an error measure may be computed for the output classification through comparison of the output classification with a known target classification. Back propagation may be applied to adjust one or more of the front-end parameters as one or more layers of the neural network, based on the error measure.
    Type: Application
    Filed: December 5, 2014
    Publication date: June 11, 2015
    Applicant: Nuance Communications, Inc.
    Inventors: Tara N. Sainath, Brian E.D. Kingsbury, Abdel-rahman Mohamed, Bhuvana Ramabhadran
  • Operation of a noise cancellation device
    Patent number: 9054666
    Abstract: A method for improving the performance of a noise cancellation device, the method includes determining whether one or more noise making objects (NMO) are near an audible range of the noise cancellation device and receiving a signal from the one or more NMOs indicative of a kind of noise the one or more NMOs is generating. The method also includes selecting a specific noise cancellation model to reduce an expected noise in response to the received kind of noise the one or more NMOs is generating.
    Type: Grant
    Filed: April 17, 2012
    Date of Patent: June 9, 2015
    Assignee: International Business Machines Corporation
    Inventors: Andrew Aaron, Dimitri Kanevsky, Edward E. Kelley, Bhuvana Ramabhadran
  • TRANSLATING BETWEEN SPOKEN AND WRITTEN LANGUAGE
    Publication number: 20150120275
    Abstract: Techniques for converting spoken speech into written speech are provided. The techniques include transcribing input speech via speech recognition, mapping each spoken utterance from input speech into a corresponding formal utterance, and mapping each formal utterance into a stylistically formatted written utterance.
    Type: Application
    Filed: September 23, 2014
    Publication date: April 30, 2015
    Applicant: Nuance Communications, Inc.
    Inventors: Sara H. Basson, Rick A. Hamilton, II, Dan Ning Jiang, Dimitri Kanevsky, David Nahamoo, Michael A. Picheny, Bhuvana Ramabhadran, Tara N. Sainath
  • Methods and apparatus for performing transformation techniques for data clustering and/or classification
    Patent number: 8972312
    Abstract: Some aspects include transforming data for which at least one constraint has been specified on a portion of the data, the at least one constraint relating to a similarity and/or dissimilarity of at least some of the portion of the data. Techniques comprise determining a first transformation that approximates the at least one constraint using a cosine similarity as a measure of the similarity and/or dissimilarity of the at least a portion of the data, applying at least the first transformation to the data to obtain transformed data, and fitting a plurality of clusters to the transformed data to obtain a plurality of established clusters. Some aspects include classifying input data by transforming the input data using at least the first transformation and comparing the transformed input data to the established clusters.
    Type: Grant
    Filed: August 8, 2012
    Date of Patent: March 3, 2015
    Assignee: Nuance Communications, Inc.
    Inventors: Leonid Rachevsky, Dimitri Kanevsky, Bhuvana Ramabhadran
  • Method and Apparatus for Using Convolutional Neural Networks in Speech Recognition
    Publication number: 20150032449
    Abstract: Speech recognition techniques are employed in a variety of applications and services serving large numbers of users. As such, there is an increasing demand for speech recognition systems with enhanced performance. Specifically, enhanced performance in large vocabulary continuous speech recognition (LVCSR) systems is a market demand. Herein, convolutional neural networks are explored as an alternative speech recognition approach and different CNN architectures are tested. According to at least one example embodiment, a method and corresponding apparatus for performing speech recognition comprise employing a CNN with at least two convolutional layers and at least two fully-connected layers in speech recognition. Using the CNN a textual representation of input audio data may be provided based on output data by the CNN.
    Type: Application
    Filed: July 26, 2013
    Publication date: January 29, 2015
    Applicant: Nuance Communications, Inc.
    Inventors: Tara N. Sainath, Abdel-Rahman S. Mohamed, Brian E. D. Kingsbury, Bhuvana Ramabhadran
  • Text processing using natural language understanding
    Patent number: 8924210
    Abstract: Techniques for converting spoken speech into written speech are provided. The techniques include transcribing input speech via speech recognition, mapping each spoken utterance from input speech into a corresponding formal utterance, and mapping each formal utterance into a stylistically formatted written utterance.
    Type: Grant
    Filed: May 28, 2014
    Date of Patent: December 30, 2014
    Assignee: Nuance Communications, Inc.
    Inventors: Sara H. Basson, Rick Hamilton, Dan Ning Jiang, Dimitri Kanevsky, David Nahamoo, Michael Picheny, Bhuvana Ramabhadran, Tara N. Sainath
  • Text processing using natural language understanding
    Patent number: 8856004
    Abstract: Techniques for converting spoken speech into written speech are provided. The techniques include transcribing input speech via speech recognition, mapping each spoken utterance from input speech into a corresponding formal utterance, and mapping each formal utterance into a stylistically formatted written utterance.
    Type: Grant
    Filed: May 13, 2011
    Date of Patent: October 7, 2014
    Assignee: Nuance Communications, Inc.
    Inventors: Sara H. Basson, Rick Hamilton, Dan Ning Jiang, Dimitri Kanevsky, David Nahamoo, Michael Picheny, Bhuvana Ramabhadran, Tara N. Sainath
  • TEXT PROCESSING USING NATURAL LANGUAGE UNDERSTANDING
    Publication number: 20140278410
    Abstract: Techniques for converting spoken speech into written speech are provided. The techniques include transcribing input speech via speech recognition, mapping each spoken utterance from input speech into a corresponding formal utterance, and mapping each formal utterance into a stylistically formatted written utterance.
    Type: Application
    Filed: May 28, 2014
    Publication date: September 18, 2014
    Applicant: Nuance Communications, Inc.
    Inventors: Sara H. Basson, Rick Hamilton, Dan Ning Jiang, Dimitri Kanevsky, David Nahamoo, Michael Picheny, Bhuvana Ramabhadran, Tara N. Sainath