Patents by Inventor Michael Seltzer

Michael Seltzer 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: 8474321
    Abstract: An apparatus includes (a) a dial having a front face with indicia thereon and a transparent face plate and a back surface; and (b) a light source attached to the dial and positioned exterior to the transparent face plate and oriented so as to illuminate the face plate. The apparatus is advantageously used to measure blood pressure under adverse lighting conditions.
    Type: Grant
    Filed: May 14, 2010
    Date of Patent: July 2, 2013
    Inventor: Michael Seltzer
  • Publication number: 20110282218
    Abstract: An apparatus includes (a) a dial having a front face with indicia thereon and a transparent face plate and a back surface; and (b) a light source attached to the dial and positioned exterior to the transparent face plate and oriented so as to illuminate the face plate. The apparatus is advantageously used to measure blood pressure under adverse lighting conditions.
    Type: Application
    Filed: May 14, 2010
    Publication date: November 17, 2011
    Inventor: Michael Seltzer
  • Patent number: 8019089
    Abstract: A noisy audio signal, with user input device noise, is received. Particular frames in the audio signal that are corrupted by user input device noise are identified and removed. The removed audio data is then reconstructed to obtain a clean audio signal.
    Type: Grant
    Filed: November 20, 2006
    Date of Patent: September 13, 2011
    Assignee: Microsoft Corporation
    Inventors: Michael Seltzer, Alejandro Acero, Amarnag Subramanya
  • Patent number: 7516067
    Abstract: A system and method are provided that reduce noise in speech signals. The system and method decompose a noisy speech signal into a harmonic component and a residual component. The harmonic component and residual component are then combined as a sum to form a noise-reduced value. In some embodiments, the sum is a weighted sum where the harmonic component is multiplied by a scaling factor. In some embodiments, the noise-reduced value is used in speech recognition.
    Type: Grant
    Filed: August 25, 2003
    Date of Patent: April 7, 2009
    Assignee: Microsoft Corporation
    Inventors: Michael Seltzer, James Droppo, Alejandro Acero
  • Publication number: 20090082037
    Abstract: Framework for receiving, processing, and re-using personal points of interest (PPOI) information of a user in a location-based application. A telephone dialog system provides location-based information related PPOI of a user. For example, the PPOI information can include major intersections that the user may normally travel, gas stations, clubs, etc., based on real-time data obtained via web services. The PPOI information can be acquired using common names and nicknames, which are added into system lexicon and recognition grammars. Each PPOI is also tagged to the user (or “owner”) who defined it. The PPOI information can also be shared to support a community of users. The framework also resolves conflicting PPOI information between multiple users and multiple locations. PPOI information input by one user can be used to extract demographic information and personal preferences and be re-used by other users by automatically popping up common names and attributes other users entered for the same nickname.
    Type: Application
    Filed: September 24, 2007
    Publication date: March 26, 2009
    Applicant: MICROSOFT CORPORATION
    Inventors: Yun-Cheng Ju, Michael Seltzer, Ivan J. Tashev
  • Publication number: 20080118082
    Abstract: A noisy audio signal, with user input device noise, is received. Particular frames in the audio signal that are corrupted by user input device noise are identified and removed. The removed audio data is then reconstructed to obtain a clean audio signal.
    Type: Application
    Filed: November 20, 2006
    Publication date: May 22, 2008
    Applicant: Microsoft Corporation
    Inventors: Michael Seltzer, Alejandro Acero, Amarnag Subramanya
  • Publication number: 20080097688
    Abstract: A route can be optimized according to various constraints, specifically towards non-travel constraints. A number of community activities can take place such that the activities impact traffic. Thus, a route can be produces that lowers an influence the activities have upon a route. Moreover, a route can be produced that improves signal strength, such as strength of a signal used to communicate with a cellular telephone. In addition, a route can be enhanced by taking into account weather conditions, including real-time weather in addition to weather predictions.
    Type: Application
    Filed: December 14, 2007
    Publication date: April 24, 2008
    Applicant: MICROSOFT CORPORATION
    Inventors: Ivan Tashev, Jeffrey Couckuyt, Neil Black, John Krumm, Ruston Panabaker, Michael Seltzer
  • Publication number: 20080091341
    Abstract: A user can be compensated for taking detours from a projected route. Commonly, the reason for the compensation is that the user will be subjected to advertising, the user will pass by an establishment she is likely to visit, or to ease traffic congestion. Analysis of an area takes place and monetization opportunities are determined based upon the results of the analysis. A route between at least about two locations can be altered such that the user is provided a reward, commonly in an optimized manner.
    Type: Application
    Filed: December 14, 2007
    Publication date: April 17, 2008
    Applicant: MICROSOFT CORPORATION
    Inventors: Ruston Panabaker, John Krumm, Jeffrey Couckuyt, Ivan Tashev, Michael Seltzer, Neil Black
  • Publication number: 20070150268
    Abstract: A microphone array having at least three microphones provides a captured signal. Spatial noise suppression estimates a desired signal from a captured signal using spatio-temporal distribution of the speech and the noise. In particular, spatial information indicative of at least two quantities of direction are used. A first quantity is based on a first combination of the signals from the at least three microphones, a second quantity is based on a second combination of the signals of the at least three microphones.
    Type: Application
    Filed: December 22, 2005
    Publication date: June 28, 2007
    Applicant: Microsoft Corporation
    Inventors: Alejandro Acero, Ivan Tashev, Michael Seltzer
  • Publication number: 20070088544
    Abstract: A first set of signals from an array of one or more microphones, and a second signal from a reference microphone are used to calibrate a set of filter parameters such that the filter parameters minimize a difference between the second signal and a beamformer output signal that is based on the first set of signals. Once calibrated, the filter parameters are used to form a beamformer output signal that is filtered using a non-linear adaptive filter that is adapted based on portions of a signal that do not contain speech, as determined by a speech detection sensor.
    Type: Application
    Filed: October 14, 2005
    Publication date: April 19, 2007
    Applicant: Microsoft Corporation
    Inventors: Alejandro Acero, Michael Seltzer, Zhengyou Zhang, Zicheng Liu
  • Publication number: 20070055519
    Abstract: A narrowband power spectrum is converted into a narrowband cepstral vector. A wideband cepstral vector is then estimated from the narrowband cepstral vector, where the wideband cepstral vector represents more frequency components than the narrowband cepstral vector.
    Type: Application
    Filed: September 30, 2005
    Publication date: March 8, 2007
    Applicant: Microsoft Corporation
    Inventors: Michael Seltzer, Alejandro Acero
  • Publication number: 20060178875
    Abstract: A method and apparatus are provided that generate values for a first set of dimensions of a feature vector from a speech signal. The values of the first set of dimensions are used to estimate values for a second set of dimensions of the feature vector to form an extended feature vector. The extended feature vector is then used to train an acoustic model.
    Type: Application
    Filed: February 8, 2005
    Publication date: August 10, 2006
    Applicant: Microsoft Corporation
    Inventors: Michael Seltzer, Alejandro Acero
  • Publication number: 20060178871
    Abstract: A method and apparatus are provided that use narrowband data and wideband data to train a wideband acoustic model.
    Type: Application
    Filed: November 23, 2005
    Publication date: August 10, 2006
    Applicant: Microsoft Corporation
    Inventors: Michael Seltzer, Alejandro Acero
  • Publication number: 20050049857
    Abstract: A system and method are provided that reduce noise in speech signals. The system and method decompose a noisy speech signal into a harmonic component and a residual component. The harmonic component and residual component are then combined as a sum to form a noise-reduced value. In some embodiments, the sum is a weighted sum where the harmonic component is multiplied by a scaling factor. In some embodiments, the noise-reduced value is used in speech recognition.
    Type: Application
    Filed: August 25, 2003
    Publication date: March 3, 2005
    Applicant: Microsoft Corporation
    Inventors: Michael Seltzer, James Droppo, Alejandro Acero