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).

  • Publication number: 20190318732
    Abstract: A whole sentence recurrent neural network (RNN) language model (LM) is provided for for estimating a probability of likelihood of each whole sentence processed by natural language processing being correct. A noise contrastive estimation sampler is applied against at least one entire sentence from a corpus of multiple sentences to generate at least one incorrect sentence. The whole sentence RNN LN is trained, using the at least one entire sentence from the corpus and the at least one incorrect sentence, to distinguish the at least one entire sentence as correct. The whole sentence recurrent neural network language model is applied to estimate the probability of likelihood of each whole sentence processed by natural language processing being correct.
    Type: Application
    Filed: April 16, 2018
    Publication date: October 17, 2019
    Inventors: Yinghui Huang, Abhinav Sethy, Kartik Audhkhasi, Bhuvana Ramabhadran
  • Patent number: 10431210
    Abstract: A whole sentence recurrent neural network (RNN) language model (LM) is provided for for estimating a probability of likelihood of each whole sentence processed by natural language processing being correct. A noise contrastive estimation sampler is applied against at least one entire sentence from a corpus of multiple sentences to generate at least one incorrect sentence. The whole sentence RNN LN is trained, using the at least one entire sentence from the corpus and the at least one incorrect sentence, to distinguish the at least one entire sentence as correct. The whole sentence recurrent neural network language model is applied to estimate the probability of likelihood of each whole sentence processed by natural language processing being correct.
    Type: Grant
    Filed: April 16, 2018
    Date of Patent: October 1, 2019
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Yinghui Huang, Abhinav Sethy, Kartik Audhkhasi, Bhuvana Ramabhadran
  • Patent number: 10360901
    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: Grant
    Filed: December 5, 2014
    Date of Patent: July 23, 2019
    Assignee: Nuance Communications, Inc.
    Inventors: Tara N. Sainath, Brian E. D. Kingsbury, Abdel-rahman Mohamed, Bhuvana Ramabhadran
  • Publication number: 20190205748
    Abstract: A technique for generating soft labels for training is disclosed. In the method, a teacher model having a teacher side class set is prepared. A collection of class pairs for respective data units is obtained. Each class pair includes classes labelled to a corresponding data unit from among the teacher side class set and from among a student side class set that is different from the teacher side class set. A training input is fed into the teacher model to obtain a set of outputs for the teacher side class set. A set of soft labels for the student side class set is calculated from the set of the outputs by using, for each member of the student side class set, at least an output obtained for a class within a subset of the teacher side class set having relevance to the member of the student side class set, based at least in part on observations in the collection of the class pairs.
    Type: Application
    Filed: January 2, 2018
    Publication date: July 4, 2019
    Inventors: Takashi Fukuda, Samuel Thomas, Bhuvana Ramabhadran
  • Publication number: 20190149769
    Abstract: A method of combining data streams from fixed audio-visual sensors with data streams from personal mobile devices including, forming a communication link with at least one of one or more personal mobile devices; receiving at least one of an audio data stream and/or a video data stream from the at least one of the one or more personal mobile devices; determining the quality of the at least one of the audio data stream and/or the video data stream, wherein the audio data stream and/or the video data stream having a quality above a threshold quality is retained; and combining the retained audio data stream and/or the video data stream with the data streams from the fixed audio-visual sensors.
    Type: Application
    Filed: January 9, 2019
    Publication date: May 16, 2019
    Inventors: STANLEY CHEN, KENNETH W. CHURCH, VAIBHAVA GOEL, LIDIA L. MANGU, ETIENNE MARCHERET, BHUVANA RAMABHADRAN, LAURENCE P. SANSONE, ABHINAV SETHY, SAMUEL THOMAS
  • Publication number: 20190139550
    Abstract: Symbol sequences are estimated using a computer-implemented method including detecting one or more candidates of a target symbol sequence from a speech-to-text data, extracting a related portion of each candidate from the speech-to-text data, detecting repetition of at least a partial sequence of each candidate within the related portion of the corresponding candidate, labeling the detected repetition with a repetition indication, and estimating whether each candidate is the target symbol sequence, using the corresponding related portion including the repetition indication of each of the candidates.
    Type: Application
    Filed: January 7, 2019
    Publication date: May 9, 2019
    Inventors: Kenneth W. Church, Gakuto Kurata, Bhuvana Ramabhadran, Abhinav Sethy, Masayuki Suzuki, Ryuki Tachibana
  • Publication number: 20190080684
    Abstract: A computer-implemented method for processing a speech signal, includes: identifying speech segments in an input speech signal; calculating an upper variance and a lower variance, the upper variance being a variance of upper spectra larger than a criteria among speech spectra corresponding to frames in the speech segments, the lower variance being a variance of lower spectra smaller than a criteria among the speech spectra corresponding to the frames in the speech segments; determining whether the input speech signal is a special input speech signal using a difference between the upper variance and the lower variance; and performing speech recognition of the input speech signal which has been determined to be the special input speech signal, using a special acoustic model for the special input speech signal.
    Type: Application
    Filed: September 14, 2017
    Publication date: March 14, 2019
    Inventors: Osamu Ichikawa, Takashi Fukuda, Gakuto Kurata, Bhuvana Ramabhadran
  • Patent number: 10230922
    Abstract: A method of combining data streams from fixed audio-visual sensors with data streams from personal mobile devices including, forming a communication link with at least one of one or more personal mobile devices; receiving at least one of an audio data stream and/or a video data stream from the at least one of the one or more personal mobile devices; determining the quality of the at least one of the audio data stream and/or the video data stream, wherein the audio data stream and/or the video data stream having a quality above a threshold quality is retained; and combining the retained audio data stream and/or the video data stream with the data streams from the fixed audio-visual sensors.
    Type: Grant
    Filed: October 2, 2017
    Date of Patent: March 12, 2019
    Assignee: International Business Machines Corporation
    Inventors: Stanley Chen, Kenneth W. Church, Vaibhava Goel, Lidia L. Mangu, Etienne Marcheret, Bhuvana Ramabhadran, Laurence P. Sansone, Abhinav Sethy, Samuel Thomas
  • Patent number: 10229685
    Abstract: Symbol sequences are estimated using a computer-implemented method including detecting one or more candidates of a target symbol sequence from a speech-to-text data, extracting a related portion of each candidate from the speech-to-text data, detecting repetition of at least a partial sequence of each candidate within the related portion of the corresponding candidate, labeling the detected repetition with a repetition indication, and estimating whether each candidate is the target symbol sequence, using the corresponding related portion including the repetition indication of each of the candidates.
    Type: Grant
    Filed: January 18, 2017
    Date of Patent: March 12, 2019
    Assignee: International Business Machines Corporation
    Inventors: Kenneth W. Church, Gakuto Kurata, Bhuvana Ramabhadran, Abhinav Sethy, Masayuki Suzuki, Ryuki Tachibana
  • Publication number: 20190066662
    Abstract: An apparatus, method, and computer program product for adapting an acoustic model to a specific environment are defined. An adapted model obtained by adapting an original model to the specific environment using adaptation data, the original model being trained using training data and being used to calculate probabilities of context-dependent phones given an acoustic feature. Adapted probabilities obtained by adapting original probabilities using the training data and the adaptation data, the original probabilities being trained using the training data and being prior probabilities of context-dependent phones. An adapted acoustic model obtained from the adapted model and the adapted probabilities.
    Type: Application
    Filed: November 6, 2017
    Publication date: February 28, 2019
    Inventors: Gakuto Kurata, Bhuvana Ramabhadran, Masayuki Suzuki
  • Publication number: 20190066661
    Abstract: An apparatus, method, and computer program product for adapting an acoustic model to a specific environment are defined. An adapted model obtained by adapting an original model to the specific environment using adaptation data, the original model being trained using training data and being used to calculate probabilities of context-dependent phones given an acoustic feature. Adapted probabilities obtained by adapting original probabilities using the training data and the adaptation data, the original probabilities being trained using the training data and being prior probabilities of context-dependent phones. An adapted acoustic model obtained from the adapted model and the adapted probabilities.
    Type: Application
    Filed: August 25, 2017
    Publication date: February 28, 2019
    Inventors: Gakuto Kurata, Bhuvana Ramabhadran, Masayuki Suzuki
  • Publication number: 20180341851
    Abstract: Optimizing the performance of a machine learning system includes: defining an n-dimensional approximate computing configuration space, the n-dimensional approximate computing configuration space defining tuning parameters for tuning the machine learning system; setting a performance objective for the machine learning system that identifies one or more machine learning system performance criteria; collecting and monitoring performance data; comparing the performance data to the machine learning system performance objective; and dynamically updating the n-dimensional approximate computing configuration space by adjusting the at least one tuning parameter, in response to the comparison.
    Type: Application
    Filed: May 24, 2017
    Publication date: November 29, 2018
    Inventors: I-Hsin CHUNG, John A. GUNNELS, Changhoan KIM, Michael P. PERRONE, Bhuvana RAMABHADRAN
  • Publication number: 20180277104
    Abstract: A computer-implemented method is provided. The computer-implemented method is performed by a speech recognition system having at least a processor. The method includes estimating sound identification information from a neural network having periodic indications and components of a frequency spectrum of an audio signal data inputted thereto. The method further includes performing a speech recognition operation on the audio signal data to decode the audio signal data into a textual representation based on the estimated sound identification information. The neural network includes a plurality of fully-connected network layers having a first layer that includes a plurality of first nodes and a plurality of second nodes. The method further comprises training the neural network by initially isolating the periodic indications from the components of the frequency spectrum in the first layer by setting weights between the first nodes and a plurality of input nodes corresponding to the periodic indications to 0.
    Type: Application
    Filed: May 30, 2018
    Publication date: September 27, 2018
    Inventors: Takashi Fukuda, Osamu Ichikawa, Bhuvana Ramabhadran
  • Publication number: 20180247641
    Abstract: A computer-implemented method and an apparatus are provided. The method includes obtaining, by a processor, a frequency spectrum of an audio signal data. The method further includes extracting, by the processor, periodic indications from the frequency spectrum. The method also includes inputting, by the processor, the periodic indications and components of the frequency spectrum into a neural network. The method additionally includes estimating, by the processor, sound identification information from the neural network.
    Type: Application
    Filed: February 24, 2017
    Publication date: August 30, 2018
    Inventors: Takashi Fukuda, Osamu Ichikawa, Bhuvana Ramabhadran
  • Patent number: 10062378
    Abstract: A computer-implemented method and an apparatus are provided. The method includes obtaining, by a processor, a frequency spectrum of an audio signal data. The method further includes extracting, by the processor, periodic indications from the frequency spectrum. The method also includes inputting, by the processor, the periodic indications and components of the frequency spectrum into a neural network. The method additionally includes estimating, by the processor, sound identification information from the neural network.
    Type: Grant
    Filed: February 24, 2017
    Date of Patent: August 28, 2018
    Assignee: International Business Machines Corporation
    Inventors: Takashi Fukuda, Osamu Ichikawa, Bhuvana Ramabhadran
  • Publication number: 20180204567
    Abstract: Symbol sequences are estimated using a computer-implemented method including detecting one or more candidates of a target symbol sequence from a speech-to-text data, extracting a related portion of each candidate from the speech-to-text data, detecting repetition of at least a partial sequence of each candidate within the related portion of the corresponding candidate, labeling the detected repetition with a repetition indication, and estimating whether each candidate is the target symbol sequence, using the corresponding related portion including the repetition indication of each of the candidates.
    Type: Application
    Filed: January 18, 2017
    Publication date: July 19, 2018
    Inventors: Kenneth W. Church, Gakuto Kurata, Bhuvana Ramabhadran, Abhinav Sethy, Masayuki Suzuki, Ryuki Tachibana
  • Patent number: 10019438
    Abstract: A mechanism is provided in a data processing system for external word embedding neural network language models. The mechanism configures the data processing system with an external word embedding neural network language model that accepts as input a sequence of words and predicts a current word based on the sequence of words. The external word embedding neural network language model combines an external embedding matrix to a history word embedding matrix and a prediction word embedding matrix of the external word embedding neural network language model. The mechanism receives a sequence of input words by the data processing system. The mechanism applies a plurality of previous words in the sequence of input words as inputs to the external word embedding neural network language model. The external word embedding neural network language model generates a predicted current word based on the plurality of previous words.
    Type: Grant
    Filed: March 18, 2016
    Date of Patent: July 10, 2018
    Assignee: International Business Machines Corporation
    Inventors: Kartik Audhkhasi, Bhuvana Ramabhadran, Abhinav Sethy
  • Publication number: 20180113742
    Abstract: A method and an apparatus of allocating available resources in a cluster system with learning models and tuning methods are provided. The learning model may be trained from historic performance data of previously executed jobs and used to project a suggested amount of resources for execution of a job. The tuning process may suggest a configuration for the projected amount of resources in the cluster system for an optimal operating point. An optimization may be performed with respect to a set of objective functions to improve resource utilization and system performance while suggesting the configuration. Through many executions and job characterization, the learning/tuning process for suggesting the configuration for the projected amount of resources may be improved by understanding correlations of historic data and the objective functions.
    Type: Application
    Filed: October 25, 2016
    Publication date: April 26, 2018
    Inventors: I-Hsin Chung, Paul G. Crumley, Bhuvana Ramabhadran, WeiChung Wang, Huifang Wen
  • Patent number: 9942225
    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: September 28, 2015
    Date of Patent: April 10, 2018
    Assignee: International Business Machines Corporation
    Inventors: Jiri Navratil, Bhuvana Ramabhadran
  • Patent number: 9934778
    Abstract: Techniques for conversion of non-back-off language models for use in speech decoders. For example, an apparatus for conversion of non-back-off language models for use in speech decoders. For example, an apparatus is configured convert a non-back-off language model to a back-off language model. The converted back-off language model is pruned. The converted back-off language model is usable for decoding speech.
    Type: Grant
    Filed: August 1, 2016
    Date of Patent: April 3, 2018
    Assignee: International Business Machines Corporation
    Inventors: Ebru Arisoy, Bhuvana Ramabhadran, Abhinav Sethy, Stanley Chen