Patents by Inventor Evgeny A. Cherepanov
Evgeny A. Cherepanov 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: 20200168212Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing One of the methods includes receiving a first voice input from a user device, generating a first recognition output, receiving a user selection of one or more terms in the first recognition output- receiving a second voice input spelling a correction of the user selection, determining a corrected recognition output for the selected portion; and providing a second recognition output that merges the first recognition output and the corrected recognition output.Type: ApplicationFiled: January 24, 2020Publication date: May 28, 2020Applicant: Google LLCInventors: Evgeny A Cherepanov, Gleb Skobeltsyn, Jakob Nicolaus Foerster, Petar Aleksic, Assaf Avner Hurwitz Michaely
-
Patent number: 10643603Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for speech recognition. One of the methods includes receiving first audio data corresponding to an utterance; obtaining a first transcription of the first audio data; receiving data indicating (i) a selection of one or more terms of the first transcription and (ii) one or more of replacement terms; determining that one or more of the replacement terms are classified as a correction of one or more of the selected terms; in response to determining that the one or more of the replacement terms are classified as a correction of the one or more of the selected terms, obtaining a first portion of the first audio data that corresponds to one or more terms of the first transcription; and using the first portion of the first audio data that is associated with the one or more terms of the first transcription to train an acoustic model for recognizing the one or more of the replacement terms.Type: GrantFiled: June 29, 2018Date of Patent: May 5, 2020Assignee: Google LLCInventors: Olga Kapralova, Evgeny A. Cherepanov, Dmitry Osmakov, Martin Baeuml, Gleb Skobeltsyn
-
Publication number: 20200105247Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the method includes receiving a voice input from a user device; generating a recognition output; receiving a user selection of one or more terms in the recognition output; receiving a user input of one or more letters replacing the user selected one or more terms; determining suggested correction candidates based in part on the user input and the voice input; and providing one or more suggested correction candidates to the user device as suggested corrected recognition outputs.Type: ApplicationFiled: December 3, 2019Publication date: April 2, 2020Applicant: Google LLCInventors: Evgeny A. Cherepanov, Jakob Nicolaus Foerster, Vikram Sridar, Ishai Rabinovitz, Omer Tabach
-
Patent number: 10579730Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the methods includes receiving a first voice input from a user device; generating a first recognition output; receiving a user selection of one or more terms in the first recognition output; receiving a second voice input spelling a correction of the user selection; determining a corrected recognition output for the selected portion; and providing a second recognition output that merges the first recognition output and the corrected recognition output.Type: GrantFiled: January 25, 2019Date of Patent: March 3, 2020Assignee: Google LLCInventors: Evgeny A. Cherepanov, Gleb Skobeltsyn, Jakob Foerster, Petar Aleksic, Assaf Hurwitz Michaely
-
Patent number: 10529316Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the method includes receiving a voice input from a user device; generating a recognition output; receiving a user selection of one or more terms in the recognition output; receiving a user input of one or more letters replacing the user selected one or more terms; determining suggested correction candidates based in part on the user input and the voice input; and providing one or more suggested correction candidates to the user device as suggested corrected recognition outputs.Type: GrantFiled: February 6, 2019Date of Patent: January 7, 2020Assignee: Google LLCInventors: Evgeny A. Cherepanov, Jakob Nicolaus Foerster, Vikram Sridar, Ishai Rabinovitz, Omer Tabach
-
Patent number: 10242662Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the method includes receiving a voice input from a user device; generating a recognition output; receiving a user selection of one or more terms in the recognition output; receiving a user input of one or more letters replacing the user selected one or more terms; determining suggested correction candidates based in part on the user input and the voice input; and providing one or more suggested correction candidates to the user device as suggested corrected recognition outputs.Type: GrantFiled: October 20, 2017Date of Patent: March 26, 2019Assignee: Google LLCInventors: Evgeny A. Cherepanov, Jakob Nicolaus Foerster, Vikram Sridar, Ishai Rabinovitz, Omer Tabach
-
Patent number: 10229109Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the methods includes receiving a first voice input from a user device; generating a first recognition output; receiving a user selection of one or more terms in the first recognition output; receiving a second voice input spelling a correction of the user selection; determining a corrected recognition output for the selected portion; and providing a second recognition output that merges the first recognition output and the corrected recognition output.Type: GrantFiled: September 11, 2017Date of Patent: March 12, 2019Assignee: Google LLCInventors: Evgeny A. Cherepanov, Gleb Skobeltsyn, Jakob Nicolaus Foerster, Petar Aleksic, Assaf Avner Hurwitz Michaely
-
Patent number: 10127909Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the methods includes receiving a first voice query; generating a first recognition output; receiving a second voice query; determining from a recognition of the second voice query that the second voice query triggers a correction request; using the first recognition output and the second recognition to determine a plurality of candidate corrections; scoring each candidate correction; and generating a corrected recognition output for a particular candidate correction having a score that satisfies a threshold value.Type: GrantFiled: January 22, 2018Date of Patent: November 13, 2018Assignee: Google LLCInventors: Gleb Skobeltsyn, Evgeny A. Cherepanov, Behshad Behzadi
-
Publication number: 20180308471Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for speech recognition. One of the methods includes receiving first audio data corresponding to an utterance; obtaining a first transcription of the first audio data; receiving data indicating (i) a selection of one or more terms of the first transcription and (ii) one or more of replacement terms; determining that one or more of the replacement terms are classified as a correction of one or more of the selected terms; in response to determining that the one or more of the replacement terms are classified as a correction of the one or more of the selected terms, obtaining a first portion of the first audio data that corresponds to one or more terms of the first transcription; and using the first portion of the first audio data that is associated with the one or more terms of the first transcription to train an acoustic model for recognizing the one or more of the replacement terms.Type: ApplicationFiled: June 29, 2018Publication date: October 25, 2018Applicant: Google LLCInventors: Olga Kapralova, Evgeny A. Cherepanov, Dmitry Osmakov, Martin Baeuml, Gleb Skobeltsyn
-
Patent number: 10049655Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the method includes receiving a voice input from a user device; generating a recognition output; receiving a user selection of one or more terms in the recognition output; receiving a user input of one or more letters replacing the user selected one or more terms; determining suggested correction candidates based in part on the user input and the voice input; and providing one or more suggested correction candidates to the user device as suggested corrected recognition outputs.Type: GrantFiled: January 5, 2016Date of Patent: August 14, 2018Assignee: Google LLCInventors: Evgeny A. Cherepanov, Jakob Nicolaus Foerster, Vikram Sridar, Ishai Rabinovitz, Omer Tabach
-
Patent number: 10019986Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for speech recognition. One of the methods includes receiving first audio data corresponding to an utterance; obtaining a first transcription of the first audio data; receiving data indicating (i) a selection of one or more terms of the first transcription and (ii) one or more of replacement terms; determining that one or more of the replacement terms are classified as a correction of one or more of the selected terms; in response to determining that the one or more of the replacement terms are classified as a correction of the one or more of the selected terms, obtaining a first portion of the first audio data that corresponds to one or more terms of the first transcription; and using the first portion of the first audio data that is associated with the one or more terms of the first transcription to train an acoustic model for recognizing the one or more of the replacement terms.Type: GrantFiled: July 29, 2016Date of Patent: July 10, 2018Assignee: Google LLCInventors: Olga Kapralova, Evgeny A. Cherepanov, Dmitry Osmakov, Martin Baeuml, Gleb Skobeltsyn
-
Publication number: 20180166079Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the methods includes receiving a first voice query; generating a first recognition output; receiving a second voice query; determining from a recognition of the second voice query that the second voice query triggers a correction request; using the first recognition output and the second recognition to determine a plurality of candidate corrections; scoring each candidate correction; and generating a corrected recognition output for a particular candidate correction having a score that satisfies a threshold value.Type: ApplicationFiled: January 22, 2018Publication date: June 14, 2018Inventors: Gleb Skobeltsyn, Evgeny A. Cherepanov, Behshad Behzadi
-
Patent number: 9971758Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the methods includes receiving a first voice input from a user device; generating a first recognition output; receiving a user selection of one or more terms in the first recognition output; receiving a second voice input spelling a correction of the user selection; determining a corrected recognition output for the selected portion; and providing a second recognition output that merges the first recognition output and the corrected recognition output.Type: GrantFiled: January 6, 2016Date of Patent: May 15, 2018Assignee: Google LLCInventors: Evgeny A. Cherepanov, Gleb Skobeltsyn, Jakob Nicolaus Foerster, Petar Aleksic, Assaf Avner Hurwitz Michaely
-
Publication number: 20180033426Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for speech recognition. One of the methods includes receiving first audio data corresponding to an utterance; obtaining a first transcription of the first audio data; receiving data indicating (i) a selection of one or more terms of the first transcription and (ii) one or more of replacement terms; determining that one or more of the replacement terms are classified as a correction of one or more of the selected terms; in response to determining that the one or more of the replacement terms are classified as a correction of the one or more of the selected terms, obtaining a first portion of the first audio data that corresponds to one or more terms of the first transcription; and using the first portion of the first audio data that is associated with the one or more terms of the first transcription to train an acoustic model for recognizing the one or more of the replacement terms.Type: ApplicationFiled: July 29, 2016Publication date: February 1, 2018Applicant: Google Inc.Inventors: Olga Kapralova, Evgeny A. Cherepanov, Dmitry Osmakov, Martin Baeuml, Gleb Skobeltsyn
-
Patent number: 9875738Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the methods includes receiving a first voice query; generating a first recognition output; receiving a second voice query; determining from a recognition of the second voice query that the second voice query triggers a correction request; using the first recognition output and the second recognition to determine a plurality of candidate corrections; scoring each candidate correction; and generating a corrected recognition output for a particular candidate correction having a score that satisfies a threshold value.Type: GrantFiled: June 5, 2017Date of Patent: January 23, 2018Assignee: Google LLCInventors: Gleb Skobeltsyn, Evgeny A. Cherepanov, Behshad Behzadi
-
Publication number: 20170270928Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the methods includes receiving a first voice query; generating a first recognition output; receiving a second voice query; determining from a recognition of the second voice query that the second voice query triggers a correction request; using the first recognition output and the second recognition to determine a plurality of candidate corrections; scoring each candidate correction; and generating a corrected recognition output for a particular candidate correction having a score that satisfies a threshold value.Type: ApplicationFiled: June 5, 2017Publication date: September 21, 2017Applicant: Google Inc.Inventors: Gleb Skobeltsyn, Evgeny A. Cherepanov, Behshad Behzadi
-
Patent number: 9727603Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining query refinements using search data. In one aspect, a method includes receiving a first query and a second query each comprising one or more n-grams for a user session, determining a first set of query refinements for the first query, determining a second set of query refinements from the first set of query refinements, each query refinement in the second set of query refinements including at least one n-gram that is similar to an n-gram from the first query and at least on n-gram that is similar to an n-gram from the second query, scoring each query refinement in the second set of query refinements, selecting a third query from a group consisting of the second set of query refinements and the second query, and providing the third query as input to a search operation.Type: GrantFiled: July 30, 2015Date of Patent: August 8, 2017Assignee: Google Inc.Inventors: Matthias Heiler, Behshad Behzadi, Evgeny A. Cherepanov, Nils Grimsmo, Aurelien Boffy, Alessandro Agostini, Karoly Csalogany, Fredrik Bergenlid, Marcin M. Nowak-Przygodzki
-
Patent number: 9672824Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the methods includes receiving a first voice query; generating a first recognition output; receiving a second voice query; determining from a recognition of the second voice query that the second voice query triggers a correction request; using the first recognition output and the second recognition to determine a plurality of candidate corrections; scoring each candidate correction; and generating a corrected recognition output for a particular candidate correction having a score that satisfies a threshold value.Type: GrantFiled: November 22, 2016Date of Patent: June 6, 2017Assignee: Google Inc.Inventors: Gleb Skobeltsyn, Evgeny A. Cherepanov, Behshad Behzadi
-
Publication number: 20170076723Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the methods includes receiving a first voice query; generating a first recognition output; receiving a second voice query; determining from a recognition of the second voice query that the second voice query triggers a correction request; using the first recognition output and the second recognition to determine a plurality of candidate corrections; scoring each candidate correction; and generating a corrected recognition output for a particular candidate correction having a score that satisfies a threshold value.Type: ApplicationFiled: November 22, 2016Publication date: March 16, 2017Applicant: Google Inc.Inventors: Gleb Skobeltsyn, Evgeny A. Cherepanov, Behshad Behzadi
-
Patent number: 9514743Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for natural language processing. One of the methods includes receiving a first voice query; generating a first recognition output; receiving a second voice query; determining from a recognition of the second voice query that the second voice query triggers a correction request; using the first recognition output and the second recognition to determine a plurality of candidate corrections; scoring each candidate correction; and generating a corrected recognition output for a particular candidate correction having a score that satisfies a threshold value.Type: GrantFiled: July 29, 2015Date of Patent: December 6, 2016Assignee: Google Inc.Inventors: Gleb Skobeltsyn, Evgeny A. Cherepanov, Behshad Behzadi