Patents by Inventor Cameron Rose
Cameron Rose 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).
-
Publication number: 20230260507Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speaker diarization are disclosed. In one aspect, a method includes the actions of receiving audio data corresponding to an utterance. The actions further include determining that the audio data includes an utterance of a predefined hotword spoken by a first speaker. The actions further include identifying a first portion of the audio data that includes speech from the first speaker. The actions further include identifying a second portion of the audio data that includes speech from a second, different speaker. The actions further include transmitting the first portion of the audio data that includes speech from the first speaker and suppressing transmission of the second portion of the audio data that includes speech from the second, different speaker.Type: ApplicationFiled: May 1, 2023Publication date: August 17, 2023Applicant: Google LLCInventors: Aleksandar Kracun, Richard Cameron Rose
-
Patent number: 11670287Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speaker diarization are disclosed. In one aspect, a method includes the actions of receiving audio data corresponding to an utterance. The actions further include determining that the audio data includes an utterance of a predefined hotword spoken by a first speaker. The actions further include identifying a first portion of the audio data that includes speech from the first speaker. The actions further include identifying a second portion of the audio data that includes speech from a second, different speaker. The actions further include transmitting the first portion of the audio data that includes speech from the first speaker and suppressing transmission of the second portion of the audio data that includes speech from the second, different speaker.Type: GrantFiled: April 5, 2021Date of Patent: June 6, 2023Assignee: Google LLCInventors: Aleksandar Kracun, Richard Cameron Rose
-
Publication number: 20210295824Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speaker diarization are disclosed. In one aspect a method includes the actions of receiving audio data corresponding to an utterance. The actions further include determining that the audio data includes an utterance of a predefined hotword spoken by a first speaker. The actions further include identifying a first portion of the audio data that includes speech from the first speaker. The actions further include identifying a second portion of the audio data that includes speech from a second, different speaker. The actions further include transmitting the first portion of the audio data that includes speech from the first speaker and suppressing transmission of the second portion of the audio data that includes speech from the second, different speaker.Type: ApplicationFiled: April 5, 2021Publication date: September 23, 2021Applicant: Google LLCInventors: Aleksandar Kracun, Richard Cameron Rose
-
Patent number: 10978070Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speaker diarization are disclosed. In one aspect, a method includes the actions of receiving audio data corresponding to an utterance. The actions further include determining that the audio data includes an utterance of a predefined hotword spoken by a first speaker. The actions further include identifying a first portion of the audio data that includes speech from the first speaker. The actions further include identifying a second portion of the audio data that includes speech from a second, different speaker. The actions further include transmitting the first portion of the audio data that includes speech from the first speaker and suppressing transmission of the second portion of the audio data that includes speech from the second, different speaker.Type: GrantFiled: August 27, 2019Date of Patent: April 13, 2021Inventors: Aleksandar Kracun, Richard Cameron Rose
-
Patent number: 10607600Abstract: A system and method of updating automatic speech recognition parameters on a mobile device are disclosed. The method comprises storing user account-specific adaptation data associated with ASR on a computing device associated with a wireless network, generating new ASR adaptation parameters based on transmitted information from the mobile device when a communication channel between the computing device and the mobile device becomes available and transmitting the new ASR adaptation data to the mobile device when a communication channel between the computing device and the mobile device becomes available. The new ASR adaptation data on the mobile device more accurately recognizes user utterances.Type: GrantFiled: February 12, 2018Date of Patent: March 31, 2020Assignee: NUANCE COMMUNICATIONS, INC.Inventors: Sarangarajan Parthasarathy, Richard Cameron Rose
-
Publication number: 20200098374Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speaker diarization are disclosed. In one aspect, a method includes the actions of receiving audio data corresponding to an utterance. The actions further include determining that the audio data includes an utterance of a predefined hotword spoken by a first speaker. The actions further include identifying a first portion of the audio data that includes speech from the first speaker. The actions further include identifying a second portion of the audio data that includes speech from a second, different speaker. The actions further include transmitting the first portion of the audio data that includes speech from the first speaker and suppressing transmission of the second portion of the audio data that includes speech from the second, different speaker.Type: ApplicationFiled: August 27, 2019Publication date: March 26, 2020Inventors: Aleksandar Kracun, Richard Cameron Rose
-
Patent number: 10403288Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speaker diarization are disclosed. In one aspect, a method includes the actions of receiving audio data corresponding to an utterance. The actions further include determining that the audio data includes an utterance of a predefined hotword spoken by a first speaker. The actions further include identifying a first portion of the audio data that includes speech from the first speaker. The actions further include identifying a second portion of the audio data that includes speech from a second, different speaker. The actions further include transmitting the first portion of the audio data that includes speech from the first speaker and suppressing transmission of the second portion of the audio data that includes speech from the second, different speaker.Type: GrantFiled: October 17, 2017Date of Patent: September 3, 2019Assignee: Google LLCInventors: Aleksandar Kracun, Richard Cameron Rose
-
Publication number: 20190115029Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speaker diarization are disclosed. In one aspect, a method includes the actions of receiving audio data corresponding to an utterance. The actions further include determining that the audio data includes an utterance of a predefined hotword spoken by a first speaker. The actions further include identifying a first portion of the audio data that includes speech from the first speaker. The actions further include identifying a second portion of the audio data that includes speech from a second, different speaker. The actions further include transmitting the first portion of the audio data that includes speech from the first speaker and suppressing transmission of the second portion of the audio data that includes speech from the second, different speaker.Type: ApplicationFiled: October 17, 2017Publication date: April 18, 2019Inventors: Aleksandar Kracun, Richard Cameron Rose
-
Patent number: 10133795Abstract: A system, method and apparatus for providing real-time tracking of user personalized metrics from a database are provided. A request is received from a user device for personalized metrics data from a customer relationship management (CRM) application. A home page user interface is transmitted for display on the user device. The home page user interface provides several icons for user selection, where each of the several icons corresponds to a unique personal metrics category. A selection of one of the several icons is received. A user interface for a personal metrics category corresponding to the selected icon is transmitted for display on the user device. The user interface provides for display on the user device at least one personalized metrics data corresponding to the personal metrics category.Type: GrantFiled: March 23, 2015Date of Patent: November 20, 2018Assignee: salesforce.com, inc.Inventors: Cameron Rose Reed, Lajja Mehta, Kapil Reddy Gowru, Pierre-Marie Dartus, Angela Lee Sy
-
Publication number: 20180166070Abstract: A system and method of updating automatic speech recognition parameters on a mobile device are disclosed. The method comprises storing user account-specific adaptation data associated with ASR on a computing device associated with a wireless network, generating new ASR adaptation parameters based on transmitted information from the mobile device when a communication channel between the computing device and the mobile device becomes available and transmitting the new ASR adaptation data to the mobile device when a communication channel between the computing device and the mobile device becomes available. The new ASR adaptation data on the mobile device more accurately recognizes user utterances.Type: ApplicationFiled: February 12, 2018Publication date: June 14, 2018Inventors: Sarangarajan PARTHASARATHY, Richard Cameron ROSE
-
Patent number: 9892728Abstract: A system and method of updating automatic speech recognition parameters on a mobile device are disclosed. The method comprises storing user account-specific adaptation data associated with ASR on a computing device associated with a wireless network, generating new ASR adaptation parameters based on transmitted information from the mobile device when a communication channel between the computing device and the mobile device becomes available and transmitting the new ASR adaptation data to the mobile device when a communication channel between the computing device and the mobile device becomes available. The new ASR adaptation data on the mobile device more accurately recognizes user utterances.Type: GrantFiled: March 16, 2016Date of Patent: February 13, 2018Assignee: Nuance Communications, Inc.Inventors: Sarangarajan Parthasarathy, Richard Cameron Rose
-
Publication number: 20170129602Abstract: A multipurpose robotic system that includes an unmanned aerial vehicle that is able to fly under its own power to a location of a parked vehicle. A cleaning module is attachable to the unmanned aerial vehicle. The cleaning module is configured to take part in cleaning the parked vehicle.Type: ApplicationFiled: November 8, 2016Publication date: May 11, 2017Inventors: Maan Alduaiji, Abdullah Almasoud, Mostafa Abdulla, Cameron Rose
-
Publication number: 20170129099Abstract: A multipurpose robotic system includes a station that has a robot storage area for storing robots. A module storage area stores modules. Each of the modules is configured to be attached to one of the robots, so that robot/module pairs consisting of one module attached to one robot are configured to deliver and perform services. A preparing area is used for readying robots and extension modules to perform the services. A launching area is used for launching the robot/module pairs.Type: ApplicationFiled: November 8, 2016Publication date: May 11, 2017Inventors: Maan Alduaiji, Abdullah Almasoud, Mostafa Abdulla, Cameron Rose
-
Patent number: 9460709Abstract: A system and method of updating automatic speech recognition parameters on a mobile device are disclosed. The method comprises storing user account-specific adaptation data associated with ASR on a computing device associated with a wireless network, generating new ASR adaptation parameters based on transmitted information from the mobile device when a communication channel between the computing device and the mobile device becomes available and transmitting the new ASR adaptation data to the mobile device when a communication channel between the computing device and the mobile device becomes available. The new ASR adaptation data on the mobile device more accurately recognizes user utterances.Type: GrantFiled: March 26, 2014Date of Patent: October 4, 2016Assignee: AT&T Intellectual Property II, L.P.Inventors: Sarangarajan Parthasarathy, Richard Cameron Rose
-
Publication number: 20160196822Abstract: A system and method of updating automatic speech recognition parameters on a mobile device are disclosed. The method comprises storing user account-specific adaptation data associated with ASR on a computing device associated with a wireless network, generating new ASR adaptation parameters based on transmitted information from the mobile device when a communication channel between the computing device and the mobile device becomes available and transmitting the new ASR adaptation data to the mobile device when a communication channel between the computing device and the mobile device becomes available. The new ASR adaptation data on the mobile device more accurately recognizes user utterances.Type: ApplicationFiled: March 16, 2016Publication date: July 7, 2016Inventors: Sarangarajan PARTHASARATHY, Richard Cameron ROSE
-
Publication number: 20160098467Abstract: A system, method and apparatus for providing real-time tracking of user personalized metrics from a database are provided. A request is received from a user device for personalized metrics data from a customer relationship management (CRM) application. A home page user interface is transmitted for display on the user device. The home page user interface provides several icons for user selection, where each of the several icons corresponds to a unique personal metrics category. A selection of one of the several icons is received. A user interface for a personal metrics category corresponding to the selected icon is transmitted for display on the user device. The user interface provides for display on the user device at least one personalized metrics data corresponding to the personal metrics category.Type: ApplicationFiled: March 23, 2015Publication date: April 7, 2016Inventors: Cameron Rose REED, Lajja MEHTA, Kapil Reddy GOWRU, Pierre-Marie DARTUS, Angela Lee SY
-
Patent number: 9058810Abstract: 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.Type: GrantFiled: March 26, 2012Date of Patent: June 16, 2015Assignee: AT&T Intellectual Property II, L.P.Inventors: Bojana Gajic, Shrikanth Sambasivan Narayanan, Sarangarajan Parthasarathy, Richard Cameron Rose, Aaron Edward Rosenberg
-
Publication number: 20140207459Abstract: A system and method of updating automatic speech recognition parameters on a mobile device are disclosed. The method comprises storing user account-specific adaptation data associated with ASR on a computing device associated with a wireless network, generating new ASR adaptation parameters based on transmitted information from the mobile device when a communication channel between the computing device and the mobile device becomes available and transmitting the new ASR adaptation data to the mobile device when a communication channel between the computing device and the mobile device becomes available. The new ASR adaptation data on the mobile device more accurately recognizes user utterances.Type: ApplicationFiled: March 26, 2014Publication date: July 24, 2014Applicant: AT&T Intellectual Property II, L.P.Inventors: Sarangarajan Parthasarathy, Richard Cameron Rose
-
Patent number: 8688444Abstract: A system and method of updating automatic speech recognition parameters on a mobile device are disclosed. The method comprises storing user account-specific adaptation data associated with ASR on a computing device associated with a wireless network, generating new ASR adaptation parameters based on transmitted information from the mobile device when a communication channel between the computing device and the mobile device becomes available and transmitting the new ASR adaptation data to the mobile device when a communication channel between the computing device and the mobile device becomes available. The new ASR adaptation data on the mobile device more accurately recognizes user utterances.Type: GrantFiled: October 22, 2012Date of Patent: April 1, 2014Assignee: AT&T Intellectual Property II, L.P.Inventors: Sarangarajan Parthasarathy, Richard Cameron Rose
-
Publication number: 20120275553Abstract: The various embodiments include methods, computers and communication systems that enable synchronizing information in a telecommunications system, which may include receiving a first message including communication information to be synchronized from a first domain, receiving a second message including information associated with a communication on a component in a second telecommunication domain, synchronizing information included in the first message with information included in the second message, and sending the synchronized information to a public interface of the first domain. Synchronizing the information included in the first message with information included in the second message may include synchronizing one or more of metering, rating, charging, balance, policy, and contextual information.Type: ApplicationFiled: April 20, 2012Publication date: November 1, 2012Applicant: OPENET TELECOM LTD.Inventors: Bart Lehane, Alan McNamee, Cameron Rose Dunne, Joe Hogan