Paul D Cohen

US Patent:

6571209, May 27, 2003

Filed:

Nov 12, 1998

Appl. No.:

09/190974

Inventors:

Paul S. Cohen - Yorktown Heights NY
Srinivasa P. Rao - Jericho NY
Robert T. Ward - Croton-on-Hudson NY

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G10L 1506

US Classification:

704251, 704255

Abstract:

A method for designating a subvocabulary for speech recognition systems includes the steps of providing a vocabulary of words each having a flag with a first value, selecting words to be eliminated from the vocabulary, setting the flags of the selected words to a second value and processing speech based on words having the flag set to the first value. A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for disabling and enabling of subvocabularies in speech recognition systems, the method steps include providing a vocabulary of words each having a flag with a first value, selecting words to be eliminated from the vocabulary, setting the flags of the selected words to a second value and processing speech based on words having the flag set to the first value.

US Patent:

7149686, Dec 12, 2006

Filed:

Jun 23, 2000

Appl. No.:

09/602262

Inventors:

Paul S. Cohen - Yorktown Heights NY, US
John R. Dildine - Lakeville CT, US
Edward J. Gleason - Yorktown Heights NY, US

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G10L 15/12
G10L 21/06

US Classification:

704241, 704278

Abstract:

A system and method for eliminating synchronization errors using speech recognition. Using separate audio and visual speech recognition techniques, the inventive system and method identifies visemes, or visual cues which are indicative of articulatory type, in the video content, and identifies phones and their articulatory types in the audio content. Once the two recognition techniques have been applied, the outputs are compared to determine the relative alignment and, if not aligned, a synchronization algorithm is applied to time-adjust one or both of the audio and the visual streams in order to achieve synchronization.

US Patent:

20030039337, Feb 27, 2003

Filed:

Aug 16, 2001

Appl. No.:

09/682293

Inventors:

Kenneth Davies - Ossining NY, US
Paul Cohen - Yorktown Heights NY, US

International Classification:

H04M001/64
H04M011/00

US Classification:

379/088010, 379/088180, 379/202010

Abstract:

A method and system for participating in and controlling a non-real-time voice conference. By recording a first participant's voice for playback to a second participant that is not connected at the same time as the first participant, a new type of voice conference is created.

US Patent:

58022511, Sep 1, 1998

Filed:

Sep 5, 1995

Appl. No.:

8/523755

Inventors:

Paul S. Cohen - Yorktown Heights NY
John M. Lucassen - New York NY
Elton B. Sherwin - Stamford CT
Jorge L. Vizcaino - Parkland FL

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G10L 300

US Classification:

395 284

Abstract:

A method and system are disclosed for reducing perplexity in a speech recognition system within a telephonic network based upon determined caller identity. In a speech recognition system which processes input frames of speech against stored templates representing speech, a core library of speech templates is created and stored representing a basic vocabulary of speech. Multiple caller-specific libraries of speech templates are also created and stored, each library containing speech templates which represent a specialized vocabulary and pronunciations for a specific geographic location and a particular individual. Additionally, the caller-specific libraries of speech templates are preferably processed to reflect the reduced bandwidth, transmission channel variations and other signal variations introduced into the system via a telephonic network. The identification of a caller is determined upon connection to the network via standard caller identification circuitry and upon detection of a spoken utterance, that utterance is processed against the core library, if the caller's identity cannot be determined, or against a particular caller-specific library, if the caller's identity can be determined, thereby greatly enhancing the efficiency and accuracy of speech recognition by the system.

US Patent:

43807100, Apr 19, 1983

Filed:

Feb 5, 1981

Appl. No.:

6/231671

Inventors:

Paul B. Cohen - New City NY
William R. Young - Indialantic FL
W. Dale Edwards - Indian Harbour Beach FL

Assignee:

Harris Corporation - Melbourne FL

International Classification:

H03K 19092
H03K 19094
H03K 1920
H03K 1704

US Classification:

307475

Abstract:

An interface circuit including a FET inverter with its N channel device being part of the controlled leg of a first current mirror and its P channel device being part of the controlled leg of a second current mirror. The operating point of the inverter is the reference signal applied on the input to the current mirrors. The controlled leg of the first current mirror includes a variable current source responsive to the input signal and the controlled leg of the second current mirror includes a variable current sink for improving the response time of the inverter and compensates the inverter for manufacturing tolerances.

US Patent:

55241697, Jun 4, 1996

Filed:

Dec 30, 1993

Appl. No.:

8/175701

Inventors:

Paul S. Cohen - Yorktown Heights NY
John M. Lucassen - New York NY
Roger M. Miller - Brookfield CT
Elton B. Sherwin - Stamford CT

Assignee:

International Business Machines Incorporated - Armonk NY

International Classification:

G10L 506

US Classification:

395 24

Abstract:

A method and system for reducing perplexity in a speech recognition system based upon determined geographic location. In a mobile speech recognition system which processes input frames of speech against stored templates representing speech, a core library of speech templates is created and stored representing a basic vocabulary of speech. Multiple location-specific libraries of speech templates are also created and stored, each library containing speech templates representing a specialized vocabulary for a specific geographic location. The geographic location of the mobile speech recognition system is then periodically determined utilizing a cellular telephone system, a geopositioning satellite system or other similar systems and a particular one of the location-specific libraries of speech templates is identified for the current location of the system. Input frames of speech are then processed against the combination of the core library and the particular location-specific library to greatly enhance the accuracy and efficiency of speech recognition by the system. Each location-specific library preferably includes speech templates representative of location place names, proper names, and business establishments within a specific geographic location.

US Patent:

49809180, Dec 25, 1990

Filed:

May 9, 1985

Appl. No.:

6/732472

Inventors:

Lalit R. Bahl - Amawalk NY
Paul S. Cohen - Yorktown Heights NY
Robert L. Mercer - Yorktown Heights NY

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G10L 708

US Classification:

381 43

Abstract:

A continuous speech recognition system having a speech processor and a word recognition computer subsystem, characterized by an element for developing a graph for confluent links between confluent nodes; an element for developing a graph of boundary links between adjacent words; an element for storing an inventory of confluent links and boundary links as a coding inventory; an element for converting an unknown utterance into an encoded sequence of confluent links and boundary links corresponding to recognition sequences stored in the word recognition subsystem recognition vocabulary for speech recognition. The invention also includes a method for achieving continouous speech recognition by characterizing speech as a sequence of confluent links which are matched with candidate words. The invention also applies to isolated word speech recognition as with continuous speech recognition, except that in such case there are no boundary links.

US Patent:

52840999, Feb 8, 1994

Filed:

Jun 6, 1991

Appl. No.:

7/711151

Inventors:

Paul J. Cohen - Brooklyn NY

International Classification:

A47B 1308

US Classification:

108 90

Abstract:

A table mat of rectangular construction is provided with at least one pair of parallel lines of perforations, scores or crease to permit end areas of the mat to be folded downwardly to drape over the ends of a table. The mat is of relatively heavy paper while being grease resistant and stain resistant. Two mats may be used to cover a table and to provide drapes to four sides of the table.