Jing Y Huang

US Patent:

6421641, Jul 16, 2002

Filed:

Nov 12, 1999

Appl. No.:

09/438932

Inventors:

Jing Huang - Ossining NY
Mukund Padmanabhan - White Plains NY

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G10L 1700

US Classification:

704250, 704230, 704249

Abstract:

A method of performing speaker adaptation of acoustic models in a band-quantized speech recognition system, wherein the system including one or more acoustic models represented by a feature space of multi-dimensional gaussians, whose dimensions are partitioned into bands, and the gaussian means and covariances within each band are quantized into atoms, comprises the following steps. A decoded segment of a speech signal associated with a particular speaker is obtained. Then, at least one adaptation mapping based on the decoded segment is computed. Lastly, the at least one adaptation mapping is applied to the atoms of the acoustic models to generate one or more acoustic models adapted to the particular speaker. Accordingly, a fast speaker adaptation methodology is provided for use in real-time applications.

US Patent:

6430312, Aug 6, 2002

Filed:

Dec 28, 1998

Appl. No.:

09/221473

Inventors:

Jing Huang - Ossining NY
Shanmugasundaram Ravi Kumar - San Jose CA
Mandar Mitra - Calcutta, IN
Wei-Jing Zhu - Ossining NY

Assignee:

Cornell Research Foundation, Inc. - Ithaca NY

International Classification:

G06K 900

US Classification:

382165, 382162

Abstract:

A color correlogram ( ) is a representation expressing the spatial correlation of color and distance between pixels in a stored image. The color correlogram ( ) may be used to distinguish objects in an image as well as between images in a plurality of images. By intersecting a color correlogram of an image object with correlograms of images to be searched, those images which contain the objects are identified by the intersection correlogram.

US Patent:

62467905, Jun 12, 2001

Filed:

Dec 28, 1998

Appl. No.:

9/221472

Inventors:

Jing Huang - Ossining NY
Shanmugasundaram Ravi Kumar - San Jose CA
Mandar Mitra - Calcutta, IN
Wei-Jing Zhu - Ossining NY

Assignee:

Cornell Research Foundation, Inc. - Ithaca NY

International Classification:

G06K 900

US Classification:

382162

Abstract:

A color correlogram is a three-dimensional table indexed by color and distance between pixels which expresses how the spatial correlation of color changes with distance in a stored image. The color correlogram may be used to distinguish an image from other images in a database. To create a color correlogram, the colors in the image are quantized into m color values, c. sub. i. . . c. sub. m. Also, the distance values k. epsilon. [d] to be used in the correlogram are determined where [d] is the set of distances between pixels in the image, and where dmax is the maximum distance measurement between pixels in the image. Each entry (i, j, k) in the table is the probability of finding a pixel of color c. sub. i at a selected distance k from a pixel of color c. sub. i. A color autocorrelogram, which is a restricted version of the color correlogram that considers color pairs of the form (i,i) only, may also be used to identify an image.

US Patent:

20140257809, Sep 11, 2014

Filed:

May 22, 2014

Appl. No.:

14/284738

Inventors:

Vaibhava Goel - Chappaqua NY, US
Peder A. Olsen - Cortlandt Manor NY, US
Steven J. Rennie - Millwood NY, US
Jing Huang - Ossining NY, US

International Classification:

G10L 15/14

US Classification:

704239

Abstract:

Techniques disclosed herein include using a Maximum A Posteriori (MAP) adaptation process that imposes sparseness constraints to generate acoustic parameter adaptation data for specific users based on a relatively small set of training data. The resulting acoustic parameter adaptation data identifies changes for a relatively small fraction of acoustic parameters from a baseline acoustic speech model instead of changes to all acoustic parameters. This results in user-specific acoustic parameter adaptation data that is several orders of magnitude smaller than storage amounts otherwise required for a complete acoustic model. This provides customized acoustic speech models that increase recognition accuracy at a fraction of expected data storage requirements.