Patents by Inventor Boris Bekkerman
Boris Bekkerman 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: 10753765Abstract: A method and apparatus for location referencing roadway data. A server determines a roadway event; the roadway event including a roadway description and a roadway location. The server then generates a roadway message. The roadway message includes the roadway description and a roadway path. The roadway path includes a LinkID set, a length of the roadway event, and an offset from a reference node of a starting link. The LinkID set includes at least the starting link. The server then broadcasts the roadway message. A device receives the data. The device decodes and displays the data.Type: GrantFiled: March 19, 2018Date of Patent: August 25, 2020Assignee: HERE Global B.V.Inventors: Boris Bekkerman, Joe Ciprian, Johannes Glossner
-
Patent number: 10510337Abstract: A method on a mobile device for voice recognition training is described. A voice training mode is entered. A voice training sample for a user of the mobile device is recorded. The voice training mode is interrupted to enter a noise indicator mode based on a sample background noise level for the voice training sample and a sample background noise type for the voice training sample. The voice training mode is returned to from the noise indicator mode when the user provides a continuation input that indicates a current background noise level meets an indicator threshold value.Type: GrantFiled: April 10, 2018Date of Patent: December 17, 2019Assignee: Google LLCInventors: Michael E. Gunn, Boris Bekkerman, Mark A. Jasiuk, Pratik M. Kamdar, Jeffrey A. Sierawski
-
Publication number: 20180301142Abstract: A method on a mobile device for voice recognition training is described. A voice training mode is entered. A voice training sample for a user of the mobile device is recorded. The voice training mode is interrupted to enter a noise indicator mode based on a sample background noise level for the voice training sample and a sample background noise type for the voice training sample. The voice training mode is returned to from the noise indicator mode when the user provides a continuation input that indicates a current background noise level meets an indicator threshold value.Type: ApplicationFiled: April 10, 2018Publication date: October 18, 2018Inventors: Michael E. Gunn, Boris Bekkerman, Mark A. Jasiuk, Pratik M. Kamdar, Jeffrey A. Sierawski
-
Publication number: 20180216957Abstract: A method and apparatus for location referencing roadway data. A server determines a roadway event; the roadway event including a roadway description and a roadway location. The server then generates a roadway message. The roadway message includes the roadway description and a roadway path. The roadway path includes a LinkID set, a length of the roadway event, and an offset from a reference node of a starting link. The LinkID set includes at least the starting link. The server then broadcasts the roadway message. A device receives the data. The device decodes and displays the data.Type: ApplicationFiled: March 19, 2018Publication date: August 2, 2018Inventors: Boris Bekkerman, Joe Ciprian, Johannes Glossner
-
Patent number: 9966062Abstract: A method on a mobile device for voice recognition training is described. A voice training mode is entered. A voice training sample for a user of the mobile device is recorded. The voice training mode is interrupted to enter a noise indicator mode based on a sample background noise level for the voice training sample and a sample background noise type for the voice training sample. The voice training mode is returned to from the noise indicator mode when the user provides a continuation input that indicates a current background noise level meets an indicator threshold value.Type: GrantFiled: March 22, 2017Date of Patent: May 8, 2018Assignee: Google Technology Holdings LLCInventors: Michael E. Gunn, Boris Bekkerman, Mark A. Jasiuk, Pratik M. Kamdar, Jeffrey A. Sierawski
-
Patent number: 9945689Abstract: A method and apparatus for location referencing roadway data. A server determines a roadway event; the roadway event including a roadway description and a roadway location. The server then generates a roadway message. The roadway message includes the roadway description and a roadway path. The roadway path includes a LinkID set, a length of the roadway event, and an offset from a reference node of a starting link. The LinkID set includes at least the starting link. The server then broadcasts the roadway message. A device receives the data. The device decodes and displays the data.Type: GrantFiled: August 25, 2015Date of Patent: April 17, 2018Assignee: HERE Global B.V.Inventors: Boris Bekkerman, Joe Ciprian, Johannes Glossner
-
Patent number: 9875744Abstract: A method on a mobile device for voice recognition training is described. A voice training mode is entered. A voice training sample for a user of the mobile device is recorded. The voice training mode is interrupted to enter a noise indicator mode based on a sample background noise level for the voice training sample and a sample background noise type for the voice training sample. The voice training mode is returned to from the noise indicator mode when the user provides a continuation input that indicates a current background noise level meets an indicator threshold value.Type: GrantFiled: March 23, 2017Date of Patent: January 23, 2018Assignee: Google Technology Holdings LLCInventors: Michael E. Gunn, Boris Bekkerman, Mark A. Jasiuk, Pratik M. Kamdar, Jeffrey A. Sierawski
-
Publication number: 20170193985Abstract: A method on a mobile device for voice recognition training is described. A voice training mode is entered. A voice training sample for a user of the mobile device is recorded. The voice training mode is interrupted to enter a noise indicator mode based on a sample background noise level for the voice training sample and a sample background noise type for the voice training sample. The voice training mode is returned to from the noise indicator mode when the user provides a continuation input that indicates a current background noise level meets an indicator threshold value.Type: ApplicationFiled: March 22, 2017Publication date: July 6, 2017Inventors: Michael E. Gunn, Boris Bekkerman, Mark A. Jasiuk, Pratik M. Kamdar, Jeffrey A. Sierawski
-
Publication number: 20170194007Abstract: A method on a mobile device for voice recognition training is described. A voice training mode is entered. A voice training sample for a user of the mobile device is recorded. The voice training mode is interrupted to enter a noise indicator mode based on a sample background noise level for the voice training sample and a sample background noise type for the voice training sample. The voice training mode is returned to from the noise indicator mode when the user provides a continuation input that indicates a current background noise level meets an indicator threshold value.Type: ApplicationFiled: March 23, 2017Publication date: July 6, 2017Inventors: Michael E. Gunn, Boris Bekkerman, Mark A. Jasiuk, Pratik M. Kamdar, Jeffrey A. Sierawski
-
Patent number: 9691377Abstract: A method on a mobile device for voice recognition training is described. A voice training mode is entered. A voice training sample for a user of the mobile device is recorded. The voice training mode is interrupted to enter a noise indicator mode based on a sample background noise level for the voice training sample and a sample background noise type for the voice training sample. The voice training mode is returned to from the noise indicator mode when the user provides a continuation input that indicates a current background noise level meets an indicator threshold value.Type: GrantFiled: December 27, 2013Date of Patent: June 27, 2017Assignee: Google Technology Holdings LLCInventors: Michael E Gunn, Boris Bekkerman, Mark A Jasiuk, Pratik M Kamdar, Jeffrey A Sierawski
-
Publication number: 20170059352Abstract: A method and apparatus for location referencing roadway data. A server determines a roadway event; the roadway event including a roadway description and a roadway location. The server then generates a roadway message. The roadway message includes the roadway description and a roadway path. The roadway path includes a LinkID set, a length of the roadway event, and an offset from a reference node of a starting link. The LinkID set includes at least the starting link. The server then broadcasts the roadway message. A device receives the data. The device decodes and displays the data.Type: ApplicationFiled: August 25, 2015Publication date: March 2, 2017Inventors: Boris Bekkerman, Joe Ciprian, Johannes Glossner
-
Patent number: 9570076Abstract: A method and system for voice recognition are disclosed. In one example embodiment, the method includes receiving voice input information by way of a receiver on a mobile device and performing, by way of at least one processing device on the mobile device, first and second processing operations respectively with respect to first and second voice input portions, respectively, which respectively correspond to and are based at least indirectly upon different respective portions of the voice input information. The first processing operation includes a speech-to-text operation and the second processing operation includes an alternate processing operation. Additionally, the method includes generating recognized voice information based at least indirectly upon results from the first and second processing operations, and performing at least one action based at least in part upon the recognized voice information, where the at least one action includes outputting at least one signal by an output device.Type: GrantFiled: February 22, 2013Date of Patent: February 14, 2017Assignee: Google Technology Holdings LLCInventors: Jeffrey A Sierawski, Boris Bekkerman, Michael P Labowicz, Kazuhiro Ondo
-
Publication number: 20150032451Abstract: A method on a mobile device for voice recognition training is described. A voice training mode is entered. A voice training sample for a user of the mobile device is recorded. The voice training mode is interrupted to enter a noise indicator mode based on a sample background noise level for the voice training sample and a sample background noise type for the voice training sample. The voice training mode is returned to from the noise indicator mode when the user provides a continuation input that indicates a current background noise level meets an indicator threshold value.Type: ApplicationFiled: December 27, 2013Publication date: January 29, 2015Applicant: Motorola Mobility LLCInventors: Michael E. Gunn, Boris Bekkerman, Mark A. Jasiuk, Pratik M. Kamdar, Jeffrey A. Sierawski
-
Publication number: 20140122071Abstract: A method and system for voice recognition are disclosed. In one example embodiment, the method includes receiving voice input information by way of a receiver on a mobile device and performing, by way of at least one processing device on the mobile device, first and second processing operations respectively with respect to first and second voice input portions, respectively, which respectively correspond to and are based at least indirectly upon different respective portions of the voice input information. The first processing operation includes a speech-to-text operation and the second processing operation includes an alternate processing operation. Additionally, the method includes generating recognized voice information based at least indirectly upon results from the first and second processing operations, and performing at least one action based at least in part upon the recognized voice information, where the at least one action includes outputting at least one signal by an output device.Type: ApplicationFiled: February 22, 2013Publication date: May 1, 2014Applicant: Motorola Mobility LLCInventors: Jeffrey A. Sierawski, Boris Bekkerman, Michael P. Labowicz, Kazuhiro Ondo
-
Patent number: 7634577Abstract: A Media Gateway proxy receives a message and parses the message. The message contains an attribute, sub-command, and a destination address. The proxy stores the message and the attributes. Each of the attributes corresponds to a selected one of a plurality of Media Gateways. Each of the gateways has an address. The proxy finds in the memory the address of the selected Media Gateway using the destination address and the attribute. The proxy then forms a message using said sub-command, said address, and said attribute and transmits the message to the destination Media Gateway.Type: GrantFiled: April 19, 2004Date of Patent: December 15, 2009Assignee: 3Com CorporationInventors: David A. Grabelsky, Boris Bekkerman, John Poplett, Sudhakar Ramakrishna
-
Patent number: 7564835Abstract: A system and method for maximizing the use of bandwidth optimization techniques in a voice-over-packet telephony system. In exemplary embodiments, the VOP system includes a plurality of telephones connected to a VOP telephony system. Upon receiving request to initiate a VOP connection, the end office switch connects to an originating softswitch for signaling functions and to an originating media gateway for transporting the media associated with the VOP connection. A connection information system accessible to the softswitch maintains connection information relating to media sessions between the originating media gateway and a plurality of candidate terminating media gateways. The connection information system may be accessed during connection initiation and advantageously used to determine whether there are nearly-simultaneously occurring and distinct media sessions having common endpoints such that bandwidth optimization techniques may be implemented.Type: GrantFiled: November 6, 2002Date of Patent: July 21, 2009Assignee: 3Com CorporationInventors: David Grabelsky, Anoop Tripathi, Boris Bekkerman, Michael Homeier
-
Patent number: 6766377Abstract: A Media Gateway proxy receives a message and parses the message. The message contains an attribute, sub-command, and a destination address. The proxy stores the message and the attributes. Each of the attributes corresponds to a selected one of a plurality of Media Gateways. Each of the gateways has an address. The proxy finds in the memory the address of the selected Media Gateway using the destination address and the attribute. The proxy then forms a message using said sub-command, said address, and said attribute and transmits the message to the destination Media Gateway.Type: GrantFiled: August 24, 2000Date of Patent: July 20, 2004Assignee: 3Com CorporationInventors: David Grabelsky, Boris Bekkerman, John Poplett, Sudhakar Ramakrishna