Sherif Mohamed Yacoub

US Patent:

7756871, Jul 13, 2010

Filed:

Oct 13, 2004

Appl. No.:

10/964094

Inventors:

Sherif Yacoub - Mountain View CA, US
Jean-Manuel Van Thong - Arlington MA, US
John Burns - Barcelona, ES

Assignee:

Hewlett-Packard Development Company, L.P. - Houston TX

International Classification:

G06F 7/00
G06F 17/30

US Classification:

707736, 707758, 707899

Abstract:

An article is extracted from a document using a decision combiner to process a plurality of reading order alternatives. The text flow analysis generates the plurality of reading order alternatives of separate body text regions.

US Patent:

7917364, Mar 29, 2011

Filed:

Sep 23, 2003

Appl. No.:

10/668141

Inventors:

Sherif Yacoub - Mountain View CA, US

Assignee:

Hewlett-Packard Development Company, L.P. - Houston TX

International Classification:

G10L 15/04

US Classification:

704251, 704231, 704246, 704247, 704252

Abstract:

A system comprises a computer system comprising a central processing unit coupled to a memory and resource management application. A plurality of different automatic speech recognition (ASR) engines is coupled to the computer system. The computer system is adapted to select ASR engines to analyze a speech utterance based on resources available on the system.

US Patent:

8098390, Jan 17, 2012

Filed:

Mar 31, 2008

Appl. No.:

12/059824

Inventors:

Sherif M. Yacoub - Seattle WA, US
Hanning Zhou - Seattle WA, US
Jian Liang - Seattle WA, US

Assignee:

Amazon Technologies, Inc. - Reno NV

International Classification:

G06F 3/12

US Classification:

358 115, 358 11

Abstract:

A system and a method of customizing on-demand printed content are disclosed. In response to receiving a request from a consumer for on-demand printed content, content customization is determined. The determined customization is incorporated within the requested content and the on-demand printed content. Thereafter, and further responsive to the request, an on-demand printed copy of the requested content, including the incorporated customizations, is output for on-demand printing.

US Patent:

8189762, May 29, 2012

Filed:

Oct 30, 2003

Appl. No.:

10/696839

Inventors:

Sherif Yacoub - Mountain View CA, US
Francois Vincent - Corenc, FR

Assignee:

Hewlett-Packard Development Company, L.P. - Houston TX

International Classification:

H04M 3/00

US Classification:

37926607, 379 8801, 379 8813, 379 8817, 379 8818

Abstract:

A system and method for managing telephone calls is disclosed. The method discloses: calling a contact; presenting the contact with a predetermined out-calling dialog; translating the contact's vocal responses to the dialog into textual words using selected interactive voice response algorithms; connecting the contact to a human operator after a predetermined portion of the out-calling dialog with the contact is completed; and providing the operator with the textual words. In one embodiment, the system discloses all means for implementing the method. In another embodiment, the system discloses: a contact database for storing information on the contact; a dialog database containing a predetermined out-calling dialog; a call manager for calling the contact and presenting the contact with the dialog; and an interactive voice response module for translating the contact's vocal responses to the dialog into textual words and storing the words in the contact database which are accessible to the operator.

US Patent:

8548267, Oct 1, 2013

Filed:

Sep 28, 2007

Appl. No.:

11/864187

Inventors:

Sherif M. Yacoub - Seattle WA, US
Jian Liang - Seattle WA, US
Hanning Zhou - Seattle WA, US

Assignee:

Amazon Technologies, Inc. - Reno NV

International Classification:

G06K 9/40
G06K 9/34
H04N 1/00

US Classification:

382275, 382112, 382176, 382180, 382260, 382261, 358 21

Abstract:

Systems and methods for removing artifacts from a page of digital image are presented. More particularly, a digital image is obtained, the digital image having at least one page of content to be processed. A content bounding box is determined for the content of the page. Additionally, a set of segments is generating, the set corresponding to particular areas of the content within the content bounding box, each area associated with a type of content. For each segment of the set of segments, the following are performed. Despeckling criteria are selected for identifying artifacts according to the type associated with the segment. Artifacts are identified in the segment according to the despeckling criteria. The identified artifacts are then removed from the page. Thereafter, the updated digital image is stored in a content store.

US Patent:

8589156, Nov 19, 2013

Filed:

Jul 12, 2004

Appl. No.:

10/888593

Inventors:

Paul M. Burke - Bedford NH, US
Sherif Yacoub - Mountain View CA, US

Assignee:

Hewlett-Packard Development Company, L.P. - Houston TX

International Classification:

G10L 15/00

US Classification:

704231, 704244

Abstract:

A system, method, computer-readable medium, and computer-implemented system for optimizing allocation of speech recognition tasks among multiple speech recognizers and combining recognizer results is described. An allocation determination is performed to allocate speech recognition among multiple speech recognizers using at least one of an accuracy-based allocation mechanism, a complexity-based allocation mechanism, and an availability-based allocation mechanism. The speech recognition is allocated among the speech recognizers based on the determined allocation. Recognizer results received from multiple speech recognizers in accordance with the speech recognition task allocation are combined.

US Patent:

20040153319, Aug 5, 2004

Filed:

Jan 30, 2003

Appl. No.:

10/354415

Inventors:

Sherif Yacoub - Mountain View CA, US

International Classification:

G10L015/12
G10L015/08

US Classification:

704/240000

Abstract:

A speech recognition system comprises exactly two automated speech recognition (ASR) engines connected to receive the same inputs. Each engine produces a recognition output, a hypothesis. The system implements one of two (or both) methods for combining the output of the two engines. In one method, a confusion matrix statistically generated for each speech recognition engine is converted into an alternatives matrix in which every column is ordered by highest-to-lowest probability. A program loop is set up in which the recognition outputs of the speech recognition engines are cross-compared with the alternatives matrices. If the output from the first ASR engine matches an alternative, its output is adopted as the final output. If the vectors provided by the alternatives matrices are exhausted without finding a match, the output from the first speech recognition engine is adopted as the final output. In a second method, the confusion matrix for each ASR engine is converted into Bayesian probability matrix.

US Patent:

20050102149, May 12, 2005

Filed:

Nov 12, 2003

Appl. No.:

10/706408

Inventors:

Sherif Yacoub - Mountain View CA, US

International Classification:

G10L011/00

US Classification:

704277000

Abstract:

A system and method for finding a message within a speech recognition application. An assistance manager is activated for forming a selection path and finding a message associated with the selection path.