Patents by Inventor Koduvayur Subbalakshmi

Koduvayur Subbalakshmi 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).

  • Patent number: 10593336
    Abstract: A machine learning multi-dimensional acoustic feature vector authentication system, according to an example of the present disclosure, builds and trains multiple multi-dimensional acoustic feature vector machine learning classifiers to determine a probability of spoofing of a voice. The system may extract an acoustic feature from a voice sample of a user. The system may convert the acoustic feature into multi-dimensional acoustic feature vectors and apply the multi-dimensional acoustic feature vectors to the multi-dimensional acoustic feature vector machine learning classifiers to detect spoofing and determine whether to authenticate a user.
    Type: Grant
    Filed: July 26, 2018
    Date of Patent: March 17, 2020
    Assignees: ACCENTURE GLOBAL SOLUTIONS LIMITED, MISRAM LLC
    Inventors: Constantine T. Boyadjiev, Rajarathnam Chandramouli, Koduvayur Subbalakshmi, Zongru Shao
  • Publication number: 20200035247
    Abstract: A machine learning multi-dimensional acoustic feature vector authentication system, according to an example of the present disclosure, builds and trains multiple multi-dimensional acoustic feature vector machine learning classifiers to determine a probability of spoofing of a voice. The system may extract an acoustic feature from a voice sample of a user. The system may convert the acoustic feature into multi-dimensional acoustic feature vectors and apply the multi-dimensional acoustic feature vectors to the multi-dimensional acoustic feature vector machine learning classifiers to detect spoofing and determine whether to authenticate a user.
    Type: Application
    Filed: July 26, 2018
    Publication date: January 30, 2020
    Applicants: MISRAM LLC
    Inventors: Constantine Boyadjiev, Rajarathnam Chandramouli, Koduvayur Subbalakshmi, Zongru Shao
  • Patent number: 10516701
    Abstract: According to an embodiment, a natural language processing artificial intelligence network and data security system determines an emotions model for one or more users from electronic natural language interactions of the users. The system includes a natural language processing decoder to determine textual features from the electronic natural language interactions that may be indicative of emotional states of the users. They system includes an emotions model encoder that generates an emotions model based on the emotional states of the users in the electronic natural language interactions retrieved from the data storage. The system also includes an artificial intelligence network and data security subsystem.
    Type: Grant
    Filed: October 5, 2017
    Date of Patent: December 24, 2019
    Assignees: ACCENTURE GLOBAL SOLUTIONS LIMITED, MISRAM LLC
    Inventors: Constantine Boyadjiev, Rajarathnam Chandramouli, Zongru Shao, Koduvayur Subbalakshmi
  • Publication number: 20190109878
    Abstract: According to an embodiment, a natural language processing artificial intelligence network and data security system determines an emotions model for one or more users from electronic natural language interactions of the users. The system includes a natural language processing decoder to determine textual features from the electronic natural language interactions that may be indicative of emotional states of the users. They system includes an emotions model encoder that generates an emotions model based on the emotional states of the users in the electronic natural language interactions retrieved from the data storage. The system also includes an artificial intelligence network and data security subsystem.
    Type: Application
    Filed: October 5, 2017
    Publication date: April 11, 2019
    Applicants: MISRAM LLC
    Inventors: Constantine Boyadjiev, Rajarathnam CHANDRAMOULI, Zongru SHAO, Koduvayur SUBBALAKSHMI
  • Publication number: 20060176299
    Abstract: A product and process for extracting hidden data from a stego-image that has been subjected to scaling attacks are disclosed. The hidden data extraction method of the present invention retains the one-to-one mapping of the stego-image blocks to the corresponding blocks in the scaled image. When the stego-image is scaled down, the block size for extracting the hidden data is reduced proportionally. When the stego-image is scaled up, the block size for extracting the hidden data is increased proportionally. The total overall number of blocks of pixels to be examined is kept constant between the scaled image and the stego-image. The hidden data extraction method can be combined with any existing block-DCT based data hiding method to provide an overall method for dealing with scaling attacks. Both the extraction method and the combined method can be implemented in software and stored within a machine-readable medium.
    Type: Application
    Filed: August 10, 2005
    Publication date: August 10, 2006
    Inventors: Koduvayur Subbalakshmi, Palak Amin