Richard F Rose

7209880, Apr 24, 2007

Mar 6, 2002

10/091689

Bojana Gajic - Trondheim, NO
Shrikanth Sambasivan Narayanan - Los Angeles CA, US
Sarangarajan Parthasarathy - New Providence NJ, US
Richard Cameron Rose - Watchung NJ, US
Aaron Edward Rosenberg - Berkeley Heights NJ, US

AT&T Corp. - New York NY

G10L 15/00
G10L 11/00
G06F 15/00

704231, 704270, 704200

Speech recognition models are dynamically re-configurable based on user information, application information, background information such as background noise and transducer information such as transducer response characteristics to provide users with alternate input modes to keyboard text entry. Word recognition lattices are generated for each data field of an application and dynamically concatenated into a single word recognition lattice. A language model is applied to the concatenated word recognition lattice to determine the relationships between the word recognition lattices and repeated until the generated word recognition lattices are acceptable or differ from a predetermined value only by a threshold amount. These techniques of dynamic re-configurable speech recognition provide for deployment of speech recognition on small devices such as mobile phones and personal digital assistants as well environments such as office, home or vehicle while maintaining the accuracy of the speech recognition.

7451081, Nov 11, 2008

Mar 13, 2007

11/685456

Bojana Gajic - Trondheim, NO
Shrikanth Sambasivan Narayanan - Los Angeles CA, US
Sarangarajan Parthasarathy - New Providence NJ, US
Richard Cameron Rose - Watchung NJ, US
Aaron Edward Rosenberg - Berkeley Heights NJ, US

AT&T Corp. - New York NY

G10L 15/00

704231, 704233, 704243, 704244

Speech recognition models are dynamically re-configurable based on user information, application information, background information such as background noise and transducer information such as transducer response characteristics to provide users with alternate input modes to keyboard text entry. Word recognition lattices are generated for each data field of an application and dynamically concatenated into a single word recognition lattice. A language model is applied to the concatenated word recognition lattice to determine the relationships between the word recognition lattices and repeated until the generated word recognition lattices are acceptable or differ from a predetermined value only by a threshold amount. These techniques of dynamic re-configurable speech recognition provide for deployment of speech recognition on small devices such as mobile phones and personal digital assistants as well environments such as office, home or vehicle while maintaining the accuracy of the speech recognition.

8145481, Mar 27, 2012

Sep 9, 2008

12/207175

Bojana Gajic - Trondheim, NO
Shrikanth Sambasivan Narayanan - Los Angeles CA, US
Sarangarajan Parthasarathy - New Providence NJ, US
Richard Cameron Rose - Watchung NJ, US
Aaron Edward Rosenberg - Berkeley Heights NJ, US

AT&T Intellectual Property II, L.P. - Atlanta GA

G10L 21/00

704231

Speech recognition models are dynamically re-configurable based on user information, application information, background information such as background noise and transducer information such as transducer response characteristics to provide users with alternate input modes to keyboard text entry. Word recognition lattices are generated for each data field of an application and dynamically concatenated into a single word recognition lattice. A language model is applied to the concatenated word recognition lattice to determine the relationships between the word recognition lattices and repeated until the generated word recognition lattices are acceptable or differ from a predetermined value only by a threshold amount. These techniques of dynamic re-configurable speech recognition provide for deployment of speech recognition on small devices such as mobile phones and personal digital assistants as well environments such as office, home or vehicle while maintaining the accuracy of the speech recognition.

20120185237, Jul 19, 2012

Mar 26, 2012

13/429946

Bojana GAJIC - Trondheim, NO
Shrikanth Sambasivan Narayanan - Los Angeles CA, US
Sarangarajan Parthasarathy - New Providence NJ, US
Richard Cameron Rose - Watchung NJ, US
Aaron Edward Rosenberg - Berkeley Heights NJ, US

AT&T Intellectual Property II, L.P. - Atlanta GA

G06F 17/20
G10L 17/00

704 8, 704246, 704E15004

Speech recognition models are dynamically re-configurable based on user information, application information, background information such as background noise and transducer information such as transducer response characteristics to provide users with alternate input modes to keyboard text entry. Word recognition lattices are generated for each data field of an application and dynamically concatenated into a single word recognition lattice. A language model is applied to the concatenated word recognition lattice to determine the relationships between the word recognition lattices and repeated until the generated word recognition lattices are acceptable or differ from a predetermined value only by a threshold amount. These techniques of dynamic re-configurable speech recognition provide for deployment of speech recognition on small devices such as mobile phones and personal digital assistants as well environments such as office, home or vehicle while maintaining the accuracy of the speech recognition.

42767520, Jul 7, 1981

Sep 22, 1978

5/944869

Peter R. Modler - Los Angeles CA
Harold E. Dittmer - San Francisco CA
Richard L. Rose - Newark CA
John A. Stafsnes - San Anselmo CA

Pax Equipment Management, Inc. - San Francisco CA

F25D 312

62166

A refrigerated cargo container, comprising no moving parts, for use in transporting temperature sensitive cargoes in aircraft. The container has six insulated walls with an insulated door along part of one of the walls, preferably the container's front wall, to provide for an air-tight container when the door is closed. An insulated bunker, having an insulated wall about a portion of its outer surface and a heat exchange portion along its bottom surface, containing a coolant such as solid carbon dioxide, is located within one of the top corners of the insulated cargo container. An air inlet duct extends along the top wall of the insulated container to one side of the insulated bunker to allow warm air from the interior of the container and the cargo to flow into the inlet duct along the top wall of the container and to pass along the side and bottom of the coolant bunker where the warm air is cooled by the heat exchange portion of the bunker. A small fan driven by a small motor may be installed along the path of the air inlet duct to increase the flow of warm air to the bunker heat exchange portion. Cool air flowing from the heat exchange portion of the bunker is then passed through an output air duct, formed by a curtain, preferably an insulated curtain, passing along one of the insulated side walls of the container to circulate cool air through the interior of the container and among the cargo being transported in the container.