Patents by Inventor Trausti T. Kristjansson
Trausti T. Kristjansson 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: 20210295842Abstract: The subject matter of this specification can be implemented in, among other things, a computer-implemented method for correcting words in transcribed text including receiving speech audio data from a microphone. The method further includes sending the speech audio data to a transcription system. The method further includes receiving a word lattice transcribed from the speech audio data by the transcription system. The method further includes presenting one or more transcribed words from the word lattice. The method further includes receiving a user selection of at least one of the presented transcribed words. The method further includes presenting one or more alternate words from the word lattice for the selected transcribed word. The method further includes receiving a user selection of at least one of the alternate words. The method further includes replacing the selected transcribed word in the presented transcribed words with the selected alternate word.Type: ApplicationFiled: June 7, 2021Publication date: September 23, 2021Applicant: Google LLCInventors: Michael J. LeBeau, William J. Byrne, John Nicholas Jitkoff, Brandon M. Ballinger, Trausti T. Kristjansson
-
Patent number: 11037566Abstract: The subject matter of this specification can be implemented in, among other things, a computer-implemented method for correcting words in transcribed text including receiving speech audio data from a microphone. The method further includes sending the speech audio data to a transcription system. The method further includes receiving a word lattice transcribed from the speech audio data by the transcription system. The method further includes presenting one or more transcribed words from the word lattice. The method further includes receiving a user selection of at least one of the presented transcribed words. The method further includes presenting one or more alternate words from the word lattice for the selected transcribed word. The method further includes receiving a user selection of at least one of the alternate words. The method further includes replacing the selected transcribed word in the presented transcribed words with the selected alternate word.Type: GrantFiled: April 21, 2020Date of Patent: June 15, 2021Assignee: Google LLCInventors: Michael J. Lebeau, William J. Byrne, John Nicholas Jitkoff, Brandon M. Ballinger, Trausti T. Kristjansson
-
Publication number: 20200251113Abstract: The subject matter of this specification can be implemented in, among other things, a computer-implemented method for correcting words in transcribed text including receiving speech audio data from a microphone. The method further includes sending the speech audio data to a transcription system. The method further includes receiving a word lattice transcribed from the speech audio data by the transcription system. The method further includes presenting one or more transcribed words from the word lattice. The method further includes receiving a user selection of at least one of the presented transcribed words. The method further includes presenting one or more alternate words from the word lattice for the selected transcribed word. The method further includes receiving a user selection of at least one of the alternate words. The method further includes replacing the selected transcribed word in the presented transcribed words with the selected alternate word.Type: ApplicationFiled: April 21, 2020Publication date: August 6, 2020Applicant: Google LLCInventors: Michael J. LeBeau, William J. Byrne, John Nicholas Jitkoff, Brandon M. Ballinger, Trausti T. Kristjansson
-
Patent number: 10720176Abstract: A computer-implemented method of multisensory speech detection is disclosed. The method comprises determining an orientation of a mobile device and determining an operating mode of the mobile device based on the orientation of the mobile device. The method further includes identifying speech detection parameters that specify when speech detection begins or ends based on the determined operating mode and detecting speech from a user of the mobile device based on the speech detection parameters.Type: GrantFiled: August 22, 2018Date of Patent: July 21, 2020Assignee: Google LLCInventors: Dave Burke, Michael J. Lebeau, Konrad Gianno, Trausti T. Kristjansson, John Nicholas Jitkoff, Andrew W. Senior
-
Patent number: 10714120Abstract: A computer-implemented method of multisensory speech detection is disclosed. The method comprises determining an orientation of a mobile device and determining an operating mode of the mobile device based on the orientation of the mobile device. The method further includes identifying speech detection parameters that specify when speech detection begins or ends based on the determined operating mode and detecting speech from a user of the mobile device based on the speech detection parameters.Type: GrantFiled: June 25, 2018Date of Patent: July 14, 2020Assignee: Google LLCInventors: Dave Burke, Michael J. Lebeau, Konrad Gianno, Trausti T. Kristjansson, John Nicholas Jitkoff, Andrew W. Senior
-
Patent number: 10672394Abstract: The subject matter of this specification can be implemented in, among other things, a computer-implemented method for correcting words in transcribed text including receiving speech audio data from a microphone. The method further includes sending the speech audio data to a transcription system. The method further includes receiving a word lattice transcribed from the speech audio data by the transcription system. The method further includes presenting one or more transcribed words from the word lattice. The method further includes receiving a user selection of at least one of the presented transcribed words. The method further includes presenting one or more alternate words from the word lattice for the selected transcribed word. The method further includes receiving a user selection of at least one of the alternate words. The method further includes replacing the selected transcribed word in the presented transcribed words with the selected alternate word.Type: GrantFiled: December 21, 2017Date of Patent: June 2, 2020Assignee: Google LLCInventors: Michael J. LeBeau, William J. Byrne, John Nicholas Jitkoff, Brandon M. Ballinger, Trausti T. Kristjansson
-
Publication number: 20180358035Abstract: A computer-implemented method of multisensory speech detection is disclosed. The method comprises determining an orientation of a mobile device and determining an operating mode of the mobile device based on the orientation of the mobile device. The method further includes identifying speech detection parameters that specify when speech detection begins or ends based on the determined operating mode and detecting speech from a user of the mobile device based on the speech detection parameters.Type: ApplicationFiled: August 22, 2018Publication date: December 13, 2018Applicant: Google LLCInventors: Dave Burke, Michael J. Lebeau, Konrad Gianno, Trausti T. Kristjansson, John Nicholas Jitkoff, Andrew W. Senior
-
Publication number: 20180308510Abstract: A computer-implemented method of multisensory speech detection is disclosed. The method comprises determining an orientation of a mobile device and determining an operating mode of the mobile device based on the orientation of the mobile device. The method further includes identifying speech detection parameters that specify when speech detection begins or ends based on the determined operating mode and detecting speech from a user of the mobile device based on the speech detection parameters.Type: ApplicationFiled: June 25, 2018Publication date: October 25, 2018Applicant: Google LLCInventors: Dave Burke, Micheal J. Lebeau, Konrad Gianno, Trausti T. Kristjansson, John Nicholas Jitkoff, Andrew W. Senior
-
Patent number: 10026419Abstract: A computer-implemented method of multisensory speech detection is disclosed. The method comprises determining an orientation of a mobile device and determining an operating mode of the mobile device based on the orientation of the mobile device. The method further includes identifying speech detection parameters that specify when speech detection begins or ends based on the determined operating mode and detecting speech from a user of the mobile device based on the speech detection parameters.Type: GrantFiled: March 12, 2015Date of Patent: July 17, 2018Assignee: Google LLCInventors: Dave Burke, Michael J. LeBeau, Konrad Gianno, Trausti T. Kristjansson, John Nicholas Jitkoff, Andrew W. Senior
-
Patent number: 10020009Abstract: A computer-implemented method of multisensory speech detection is disclosed. The method comprises determining an orientation of a mobile device and determining an operating mode of the mobile device based on the orientation of the mobile device. The method further includes identifying speech detection parameters that specify when speech detection begins or ends based on the determined operating mode and detecting speech from a user of the mobile device based on the speech detection parameters.Type: GrantFiled: December 28, 2016Date of Patent: July 10, 2018Assignee: Google LLCInventors: Dave Burke, Michael J. LeBeau, Konrad Gianno, Trausti T. Kristjansson, John Nicholas Jitkoff, Andrew W. Senior
-
Publication number: 20180114530Abstract: The subject matter of this specification can be implemented in, among other things, a computer-implemented method for correcting words in transcribed text including receiving speech audio data from a microphone. The method further includes sending the speech audio data to a transcription system. The method further includes receiving a word lattice transcribed from the speech audio data by the transcription system. The method further includes presenting one or more transcribed words from the word lattice. The method further includes receiving a user selection of at least one of the presented transcribed words. The method further includes presenting one or more alternate words from the word lattice for the selected transcribed word. The method further includes receiving a user selection of at least one of the alternate words. The method further includes replacing the selected transcribed word in the presented transcribed words with the selected alternate word.Type: ApplicationFiled: December 21, 2017Publication date: April 26, 2018Inventors: Michael J. LeBeau, William J. Byrne, John Nicholas Jitkoff, Brandon M. Ballinger, Trausti T. Kristjansson
-
Patent number: 9881608Abstract: The subject matter of this specification can be implemented in, among other things, a computer-implemented method for correcting words in transcribed text including receiving speech audio data from a microphone. The method further includes sending the speech audio data to a transcription system. The method further includes receiving a word lattice transcribed from the speech audio data by the transcription system. The method further includes presenting one or more transcribed words from the word lattice. The method further includes receiving a user selection of at least one of the presented transcribed words. The method further includes presenting one or more alternate words from the word lattice for the selected transcribed word. The method further includes receiving a user selection of at least one of the alternate words. The method further includes replacing the selected transcribed word in the presented transcribed words with the selected alternate word.Type: GrantFiled: May 30, 2017Date of Patent: January 30, 2018Assignee: Google LLCInventors: Michael J. LeBeau, William J. Byrne, John Nicholas Jitkoff, Brandon M. Ballinger, Trausti T. Kristjansson
-
Publication number: 20170270926Abstract: The subject matter of this specification can be implemented in, among other things, a computer-implemented method for correcting words in transcribed text including receiving speech audio data from a microphone. The method further includes sending the speech audio data to a transcription system. The method further includes receiving a word lattice transcribed from the speech audio data by the transcription system. The method further includes presenting one or more transcribed words from the word lattice. The method further includes receiving a user selection of at least one of the presented transcribed words. The method further includes presenting one or more alternate words from the word lattice for the selected transcribed word. The method further includes receiving a user selection of at least one of the alternate words. The method further includes replacing the selected transcribed word in the presented transcribed words with the selected alternate word.Type: ApplicationFiled: May 30, 2017Publication date: September 21, 2017Inventors: Michael J. LeBeau, William J. Byrne, John Nicholas Jitkoff, Brandon M. Ballinger, Trausti T. Kristjansson
-
Patent number: 9711145Abstract: The subject matter of this specification can be implemented in, among other things, a computer-implemented method for correcting words in transcribed text including receiving speech audio data from a microphone. The method further includes sending the speech audio data to a transcription system. The method further includes receiving a word lattice transcribed from the speech audio data by the transcription system. The method further includes presenting one or more transcribed words from the word lattice. The method further includes receiving a user selection of at least one of the presented transcribed words. The method further includes presenting one or more alternate words from the word lattice for the selected transcribed word. The method further includes receiving a user selection of at least one of the alternate words. The method further includes replacing the selected transcribed word in the presented transcribed words with the selected alternate word.Type: GrantFiled: November 14, 2016Date of Patent: July 18, 2017Assignee: Google Inc.Inventors: Michael J. LeBeau, William J. Byrne, John Nicholas Jitkoff, Brandon M. Ballinger, Trausti T. Kristjansson
-
Publication number: 20170069322Abstract: The subject matter of this specification can be implemented in, among other things, a computer-implemented method for correcting words in transcribed text including receiving speech audio data from a microphone. The method further includes sending the speech audio data to a transcription system. The method further includes receiving a word lattice transcribed from the speech audio data by the transcription system. The method further includes presenting one or more transcribed words from the word lattice. The method further includes receiving a user selection of at least one of the presented transcribed words. The method further includes presenting one or more alternate words from the word lattice for the selected transcribed word. The method further includes receiving a user selection of at least one of the alternate words. The method further includes replacing the selected transcribed word in the presented transcribed words with the selected alternate word.Type: ApplicationFiled: November 14, 2016Publication date: March 9, 2017Inventors: Michael J. LeBeau, William J. Byrne, John Nicholas Jitkoff, Brandon M. Ballinger, Trausti T. Kristjansson
-
Patent number: 9570094Abstract: A computer-implemented method of multisensory speech detection is disclosed. The method comprises determining an orientation of a mobile device and determining an operating mode of the mobile device based on the orientation of the mobile device. The method further includes identifying speech detection parameters that specify when speech detection begins or ends based on the determined operating mode and detecting speech from a user of the mobile device based on the speech detection parameters.Type: GrantFiled: June 29, 2015Date of Patent: February 14, 2017Assignee: Google Inc.Inventors: Dave Burke, Michael J. LeBeau, Konrad Gianno, Trausti T. Kristjansson, John Nicholas Jitkoff, Andrew W. Senior
-
Patent number: 9542932Abstract: The subject matter of this specification can be implemented in, among other things, a computer-implemented method for correcting words in transcribed text including receiving speech audio data from a microphone. The method further includes sending the speech audio data to a transcription system. The method further includes receiving a word lattice transcribed from the speech audio data by the transcription system. The method further includes presenting one or more transcribed words from the word lattice. The method further includes receiving a user selection of at least one of the presented transcribed words. The method further includes presenting one or more alternate words from the word lattice for the selected transcribed word. The method further includes receiving a user selection of at least one of the alternate words. The method further includes replacing the selected transcribed word in the presented transcribed words with the selected alternate word.Type: GrantFiled: February 17, 2016Date of Patent: January 10, 2017Assignee: Google Inc.Inventors: Michael J. LeBeau, William J. Byrne, John Nicholas Jitkoff, Brandon M. Ballinger, Trausti T. Kristjansson
-
Patent number: 9466287Abstract: The subject matter of this specification can be implemented in, among other things, a computer-implemented method for correcting words in transcribed text including receiving speech audio data from a microphone. The method further includes sending the speech audio data to a transcription system. The method further includes receiving a word lattice transcribed from the speech audio data by the transcription system. The method further includes presenting one or more transcribed words from the word lattice. The method further includes receiving a user selection of at least one of the presented transcribed words. The method further includes presenting one or more alternate words from the word lattice for the selected transcribed word. The method further includes receiving a user selection of at least one of the alternate words. The method further includes replacing the selected transcribed word in the presented transcribed words with the selected alternate word.Type: GrantFiled: January 5, 2016Date of Patent: October 11, 2016Assignee: Google Inc.Inventors: Michael J. LeBeau, William J. Byrne, John Nicholas Jitkoff, Brandon M. Ballinger, Trausti T. Kristjansson
-
Publication number: 20160163308Abstract: The subject matter of this specification can be implemented in, among other things, a computer-implemented method for correcting words in transcribed text including receiving speech audio data from a microphone. The method further includes sending the speech audio data to a transcription system. The method further includes receiving a word lattice transcribed from the speech audio data by the transcription system. The method further includes presenting one or more transcribed words from the word lattice. The method further includes receiving a user selection of at least one of the presented transcribed words. The method further includes presenting one or more alternate words from the word lattice for the selected transcribed word. The method further includes receiving a user selection of at least one of the alternate words. The method further includes replacing the selected transcribed word in the presented transcribed words with the selected alternate word.Type: ApplicationFiled: February 17, 2016Publication date: June 9, 2016Inventors: Michael J. LeBeau, William J. Byrne, John Nicholas Jitkoff, Brandon M. Ballinger, Trausti T. Kristjansson
-
Publication number: 20160133258Abstract: The subject matter of this specification can be implemented in, among other things, a computer-implemented method for correcting words in transcribed text including receiving speech audio data from a microphone. The method further includes sending the speech audio data to a transcription system. The method further includes receiving a word lattice transcribed from the speech audio data by the transcription system. The method further includes presenting one or more transcribed words from the word lattice. The method further includes receiving a user selection of at least one of the presented transcribed words. The method further includes presenting one or more alternate words from the word lattice for the selected transcribed word. The method further includes receiving a user selection of at least one of the alternate words. The method further includes replacing the selected transcribed word in the presented transcribed words with the selected alternate word.Type: ApplicationFiled: January 5, 2016Publication date: May 12, 2016Inventors: Michael J. LeBeau, William J. Byrne, John Nicholas Jitkoff, Brandon M. Ballinger, Trausti T. Kristjansson