Patents by Inventor Gleb Skobeltsyn

Gleb Skobeltsyn 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: 20200243070
    Abstract: 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: Application
    Filed: April 1, 2020
    Publication date: July 30, 2020
    Applicant: Google LLC
    Inventors: Olga Kapralova, Evgeny A. Cherepanov, Dmitry Osmakov, Martin Baeuml, Gleb Skobeltsyn
  • Publication number: 20200227031
    Abstract: The systems and methods of the present disclosure generally relate to a data processing system that can identify and surface alternative requests when presented with ambiguous, unclear, or other requests to which a data processing system may not be able to respond. The data processing system can improve the efficiency of network transmissions to reduce network bandwidth usage and processor utilization by selecting alternative requests that are responsive to the intent of the original request.
    Type: Application
    Filed: March 25, 2020
    Publication date: July 16, 2020
    Inventors: Gleb Skobeltsyn, Mihaly Kozsevnyikov, Vladimir Vuskovic
  • Publication number: 20200168212
    Abstract: 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: Application
    Filed: January 24, 2020
    Publication date: May 28, 2020
    Applicant: Google LLC
    Inventors: Evgeny A Cherepanov, Gleb Skobeltsyn, Jakob Nicolaus Foerster, Petar Aleksic, Assaf Avner Hurwitz Michaely
  • Patent number: 10643603
    Abstract: 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: Grant
    Filed: June 29, 2018
    Date of Patent: May 5, 2020
    Assignee: Google LLC
    Inventors: Olga Kapralova, Evgeny A. Cherepanov, Dmitry Osmakov, Martin Baeuml, Gleb Skobeltsyn
  • Patent number: 10579730
    Abstract: 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: Grant
    Filed: January 25, 2019
    Date of Patent: March 3, 2020
    Assignee: Google LLC
    Inventors: Evgeny A. Cherepanov, Gleb Skobeltsyn, Jakob Foerster, Petar Aleksic, Assaf Hurwitz Michaely
  • Publication number: 20190378511
    Abstract: Methods, apparatus, and computer readable media are described related to automated assistants that proactively incorporate, into human-to-computer dialog sessions, unsolicited content of potential interest to a user. In various implementations, based on content of an existing human-to-computer dialog session between a user and an automated assistant, an entity mentioned by the user or automated assistant may be identified. Fact(s)s related to the entity or to another entity that is related to the entity may be identified based on entity data contained in database(s). For each of the fact(s), a corresponding measure of potential interest to the user may be determined. Unsolicited natural language content may then be generated that includes one or more of the facts selected based on the corresponding measure(s) of potential interest. The automated assistant may then incorporate the unsolicited content into the existing human-to-computer dialog session or a subsequent human-to-computer dialog session.
    Type: Application
    Filed: August 23, 2019
    Publication date: December 12, 2019
    Inventors: Vladimir Vuskovic, Stephan Wenger, Zineb Ait Bahajji, Martin Baeuml, Alexandru Dovlecel, Gleb Skobeltsyn
  • Patent number: 10482882
    Abstract: Methods, apparatus, and computer readable media are described related to automated assistants that proactively incorporate, into human-to-computer dialog sessions, unsolicited content of potential interest to a user. In various implementations, based on content of an existing human-to-computer dialog session between a user and an automated assistant, an entity mentioned by the user or automated assistant may be identified. Fact(s)s related to the entity or to another entity that is related to the entity may be identified based on entity data contained in database(s). For each of the fact(s), a corresponding measure of potential interest to the user may be determined. Unsolicited natural language content may then be generated that includes one or more of the facts selected based on the corresponding measure(s) of potential interest. The automated assistant may then incorporate the unsolicited content into the existing human-to-computer dialog session or a subsequent human-to-computer dialog session.
    Type: Grant
    Filed: November 29, 2017
    Date of Patent: November 19, 2019
    Assignee: Google LLC
    Inventors: Vladimir Vuskovic, Stephan Wenger, Zineb Ait Bahajji, Martin Baeuml, Alexandru Dovlecel, Gleb Skobeltsyn
  • Publication number: 20190348028
    Abstract: The systems and methods of the present disclosure generally relate to a data processing system that can identify and surface alternative requests when presented with ambiguous, unclear, or other requests to which a data processing system may not be able to respond. The data processing system can improve the efficiency of network transmissions to reduce network bandwidth usage and processor utilization by selecting alternative requests that are responsive to the intent of the original request.
    Type: Application
    Filed: May 11, 2018
    Publication date: November 14, 2019
    Inventors: Gleb Skobeltsyn, Mihaly Kozsevnyikov, Vladimir Vuskovic
  • Patent number: 10229109
    Abstract: 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: Grant
    Filed: September 11, 2017
    Date of Patent: March 12, 2019
    Assignee: Google LLC
    Inventors: Evgeny A. Cherepanov, Gleb Skobeltsyn, Jakob Nicolaus Foerster, Petar Aleksic, Assaf Avner Hurwitz Michaely
  • Patent number: 10127909
    Abstract: 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: Grant
    Filed: January 22, 2018
    Date of Patent: November 13, 2018
    Assignee: Google LLC
    Inventors: Gleb Skobeltsyn, Evgeny A. Cherepanov, Behshad Behzadi
  • Publication number: 20180322880
    Abstract: Methods, apparatus, and computer readable media are described related to automated assistants that proactively incorporate, into human-to-computer dialog sessions, unsolicited content of potential interest to a user. In various implementations, based on content of an existing human-to-computer dialog session between a user and an automated assistant, an entity mentioned by the user or automated assistant may be identified. Fact(s)s related to the entity or to another entity that is related to the entity may be identified based on entity data contained in database(s). For each of the fact(s), a corresponding measure of potential interest to the user may be determined. Unsolicited natural language content may then be generated that includes one or more of the facts selected based on the corresponding measure(s) of potential interest. The automated assistant may then incorporate the unsolicited content into the existing human-to-computer dialog session or a subsequent human-to-computer dialog session.
    Type: Application
    Filed: November 29, 2017
    Publication date: November 8, 2018
    Inventors: Vladimir Vuskovic, Stephan Wenger, Zineb Ait Bahajji, Martin Baeuml, Alexandru Dovlecel, Gleb Skobeltsyn
  • Publication number: 20180308471
    Abstract: 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: Application
    Filed: June 29, 2018
    Publication date: October 25, 2018
    Applicant: Google LLC
    Inventors: Olga Kapralova, Evgeny A. Cherepanov, Dmitry Osmakov, Martin Baeuml, Gleb Skobeltsyn
  • Patent number: 10026398
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for predicting follow-up queries to an initial transcription of an utterance. In some implementations, one or more follow-up queries that are pre-associated with a transcription of an initial utterance of a user are identified. A new or modified language model in which a respective probability associated with one or more of the follow-up queries is increased with respect to an initial language model is obtained. Subsequent audio data corresponding to a subsequent utterance of the user is then received. The subsequent audio data is processed using the new or modified language model to generate a transcription of the subsequent utterance. The transcription of the subsequent utterance is then provided for output to the user.
    Type: Grant
    Filed: July 8, 2016
    Date of Patent: July 17, 2018
    Assignee: Google LLC
    Inventors: Behshad Behzadi, Dmitry Osmakov, Martin Baeuml, Gleb Skobeltsyn
  • Patent number: 10019986
    Abstract: 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: Grant
    Filed: July 29, 2016
    Date of Patent: July 10, 2018
    Assignee: Google LLC
    Inventors: Olga Kapralova, Evgeny A. Cherepanov, Dmitry Osmakov, Martin Baeuml, Gleb Skobeltsyn
  • Publication number: 20180166079
    Abstract: 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: Application
    Filed: January 22, 2018
    Publication date: June 14, 2018
    Inventors: Gleb Skobeltsyn, Evgeny A. Cherepanov, Behshad Behzadi
  • Patent number: 9971758
    Abstract: 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: Grant
    Filed: January 6, 2016
    Date of Patent: May 15, 2018
    Assignee: Google LLC
    Inventors: Evgeny A. Cherepanov, Gleb Skobeltsyn, Jakob Nicolaus Foerster, Petar Aleksic, Assaf Avner Hurwitz Michaely
  • Publication number: 20180033426
    Abstract: 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: Application
    Filed: July 29, 2016
    Publication date: February 1, 2018
    Applicant: Google Inc.
    Inventors: Olga Kapralova, Evgeny A. Cherepanov, Dmitry Osmakov, Martin Baeuml, Gleb Skobeltsyn
  • Patent number: 9875738
    Abstract: 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: Grant
    Filed: June 5, 2017
    Date of Patent: January 23, 2018
    Assignee: Google LLC
    Inventors: Gleb Skobeltsyn, Evgeny A. Cherepanov, Behshad Behzadi
  • Publication number: 20180012594
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for predicting follow-up queries to an initial transcription of an utterance. In some implementations, one or more follow-up queries that are pre-associated with a transcription of an initial utterance of a user are identified. A new or modified language model in which a respective probability associated with one or more of the follow-up queries is increased with respect to an initial language model is obtained. Subsequent audio data corresponding to a subsequent utterance of the user is then received. The subsequent audio data is processed using the new or modified language model to generate a transcription of the subsequent utterance. The transcription of the subsequent utterance is then provided for output to the user.
    Type: Application
    Filed: July 8, 2016
    Publication date: January 11, 2018
    Inventors: Behshad Behzadi, Dmitry Osmakov, Martin Baeuml, Gleb Skobeltsyn
  • Patent number: 9865260
    Abstract: Methods, apparatus, and computer readable media are described related to automated assistants that proactively incorporate, into human-to-computer dialog sessions, unsolicited content of potential interest to a user. In various implementations, based on content of an existing human-to-computer dialog session between a user and an automated assistant, an entity mentioned by the user or automated assistant may be identified. Fact(s)s related to the entity or to another entity that is related to the entity may be identified based on entity data contained in database(s). For each of the fact(s), a corresponding measure of potential interest to the user may be determined. Unsolicited natural language content may then be generated that includes one or more of the facts selected based on the corresponding measure(s) of potential interest. The automated assistant may then incorporate the unsolicited content into the existing human-to-computer dialog session or a subsequent human-to-computer dialog session.
    Type: Grant
    Filed: May 3, 2017
    Date of Patent: January 9, 2018
    Assignee: GOOGLE LLC
    Inventors: Vladimir Vuskovic, Stephan Wenger, Zineb Ait Bahajji, Martin Baeuml, Alexandru Dovlecel, Gleb Skobeltsyn