Patents by Inventor Michael H. Cohen
Michael H. Cohen 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: 11914925Abstract: A computer-implemented input-method editor process includes receiving a request from a user for an application-independent input method editor having written and spoken input capabilities, identifying that the user is about to provide spoken input to the application-independent input method editor, and receiving a spoken input from the user. The spoken input corresponds to input to an application and is converted to text that represents the spoken input. The text is provided as input to the application.Type: GrantFiled: July 13, 2022Date of Patent: February 27, 2024Assignee: Google LLCInventors: Brandon M. Ballinger, Johan Schalkwyk, Michael H. Cohen, William J. Byrne, Gudmundur Hafsteinsson, Michael J. Lebeau
-
Publication number: 20220405046Abstract: A computer-implemented input-method editor process includes receiving a request from a user for an application-independent input method editor having written and spoken input capabilities, identifying that the user is about to provide spoken input to the application-independent input method editor, and receiving a spoken input from the user. The spoken input corresponds to input to an application and is converted to text that represents the spoken input. The text is provided as input to the application.Type: ApplicationFiled: July 13, 2022Publication date: December 22, 2022Applicant: Google LLCInventors: Brandon M. Ballinger, Johan Schalkwyk, Michael H. Cohen, William J. Byrne, Gudmundur Hafsteinsson, Michael J. Lebeau
-
Patent number: 11416214Abstract: A computer-implemented input-method editor process includes receiving a request from a user for an application-independent input method editor having written and spoken input capabilities, identifying that the user is about to provide spoken input to the application-independent input method editor, and receiving a spoken input from the user. The spoken input corresponds to input to an application and is converted to text that represents the spoken input. The text is provided as input to the application.Type: GrantFiled: June 4, 2020Date of Patent: August 16, 2022Assignee: Google LLCInventors: Brandon M. Ballinger, Johan Schalkwyk, Michael H. Cohen, William J. Byrne, Gudmundur Hafsteinsson, Michael J. Lebeau
-
Publication number: 20200293276Abstract: A computer-implemented input-method editor process includes receiving a request from a user for an application-independent input method editor having written and spoken input capabilities, identifying that the user is about to provide spoken input to the application-independent input method editor, and receiving a spoken input from the user. The spoken input corresponds to input to an application and is converted to text that represents the spoken input. The text is provided as input to the application.Type: ApplicationFiled: June 4, 2020Publication date: September 17, 2020Applicant: Google LLCInventors: Brandon M. Ballinger, Johan Schalkwyk, Michael H. Cohen, William J. Byrne, Gudmundur Hafsteinsson, Michael J. Lebeau
-
Patent number: 10713010Abstract: A computer-implemented input-method editor process includes receiving a request from a user for an application-independent input method editor having written and spoken input capabilities, identifying that the user is about to provide spoken input to the application-independent input method editor, and receiving a spoken input from the user. The spoken input corresponds to input to an application and is converted to text that represents the spoken input. The text is provided as input to the application.Type: GrantFiled: October 24, 2018Date of Patent: July 14, 2020Assignee: Google LLCInventors: Brandon M. Ballinger, Johan Schalkwyk, Michael H. Cohen, William J. Byrne, Gudmundur Hafsteinsson, Michael J. Lebeau
-
Patent number: 10410627Abstract: A method for generating a speech recognition model includes accessing a baseline speech recognition model, obtaining information related to recent language usage from search queries, and modifying the speech recognition model to revise probabilities of a portion of a sound occurrence based on the information. The portion of a sound may include a word. Also, a method for generating a speech recognition model, includes receiving at a search engine from a remote device an audio recording and a transcript that substantially represents at least a portion of the audio recording, synchronizing the transcript with the audio recording, extracting one or more letters from the transcript and extracting the associated pronunciation of the one or more letters from the audio recording, and generating a dictionary entry in a pronunciation dictionary.Type: GrantFiled: March 15, 2018Date of Patent: September 10, 2019Assignee: Google LLCInventors: Michael H. Cohen, Shumeet Baluja, Pedro J. Moreno Mengibar
-
Patent number: 10380160Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for speech recognition. One of the methods includes receiving a base language model for speech recognition including a first word sequence having a base probability value; receiving a voice search query associated with a query context; determining that a customized language model is to be used when the query context satisfies one or more criteria associated with the customized language model; obtaining the customized language model, the customized language model including the first word sequence having an adjusted probability value being the base probability value adjusted according to the query context; and converting the voice search query to a text search query based on one or more probabilities, each of the probabilities corresponding to a word sequence in a group of one or more word sequences, the group including the first word sequence having the adjusted probability value.Type: GrantFiled: November 26, 2018Date of Patent: August 13, 2019Assignee: Google LLCInventors: Pedro J. Moreno Mengibar, Michael H. Cohen
-
Patent number: 10322349Abstract: A system and method implemented as computer-based, computer-executable instructions employing a computation engine with digital storage provide a virtual environment with personalized user profiles specifically adapted to cognitive abilities of the user to train the user for specified tasks, herein called microtasks. The set of microtasks include achievement criteria. The virtual environment is controlled through an engine that automatically adapts the set of user-profile-specific microtasks to achieve a set of learning goals. The engine may calculate and/or measure a set of qualities associated with one or more sub-profiles associated with a given user based on game-type performance by that user either in isolation or among a group of users. Sub-profiles may include, but are not limited to, one or more of the following: a personality profile, a neural link profile, and/or a motivation profile.Type: GrantFiled: November 15, 2017Date of Patent: June 18, 2019Assignee: Cignition, Inc.Inventors: Michael H. Cohen, Jennifer Balogh-Ghosh, Niloufar Valorie Salimpoor
-
Publication number: 20190138539Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for speech recognition. One of the methods includes receiving a base language model for speech recognition including a first word sequence having a base probability value; receiving a voice search query associated with a query context; determining that a customized language model is to be used when the query context satisfies one or more criteria associated with the customized language model; obtaining the customized language model, the customized language model including the first word sequence having an adjusted probability value being the base probability value adjusted according to the query context; and converting the voice search query to a text search query based on one or more probabilities, each of the probabilities corresponding to a word sequence in a group of one or more word sequences, the group including the first word sequence having the adjusted probability value.Type: ApplicationFiled: November 26, 2018Publication date: May 9, 2019Applicant: Google, LLCInventors: Pedro J. Moreno Mengibar, Michael H. Cohen
-
Publication number: 20190056909Abstract: A computer-implemented input-method editor process includes receiving a request from a user for an application-independent input method editor having written and spoken input capabilities, identifying that the user is about to provide spoken input to the application-independent input method editor, and receiving a spoken input from the user. The spoken input corresponds to input to an application and is converted to text that represents the spoken input. The text is provided as input to the application.Type: ApplicationFiled: October 24, 2018Publication date: February 21, 2019Applicant: Google LLCInventors: Brandon M Ballinger, Johan Schalkwyk, Michael H. Cohen, William J. Byrne, Gudmundur Hafsteinsson, Michael J. Lebeau
-
Patent number: 10157040Abstract: A computer-implemented input-method editor process includes receiving a request from a user for an application-independent input method editor having written and spoken input capabilities, identifying that the user is about to provide spoken input to the application-independent input method editor, and receiving a spoken input from the user. The spoken input corresponds to input to an application and is converted to text that represents the spoken input. The text is provided as input to the application.Type: GrantFiled: January 5, 2016Date of Patent: December 18, 2018Assignee: Google LLCInventors: Brandon M. Ballinger, Johan Schalkwyk, Michael H. Cohen, William J. Byrne, Gudmundur Hafsteinsson, Michael J. LeBeau
-
Patent number: 10140362Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for speech recognition. One of the methods includes receiving a base language model for speech recognition including a first word sequence having a base probability value; receiving a voice search query associated with a query context; determining that a customized language model is to be used when the query context satisfies one or more criteria associated with the customized language model; obtaining the customized language model, the customized language model including the first word sequence having an adjusted probability value being the base probability value adjusted according to the query context; and converting the voice search query to a text search query based on one or more probabilities, each of the probabilities corresponding to a word sequence in a group of one or more word sequences, the group including the first word sequence having the adjusted probability value.Type: GrantFiled: August 8, 2016Date of Patent: November 27, 2018Assignee: Google LLCInventors: Pedro J. Moreno Mengibar, Michael H. Cohen
-
Publication number: 20180204565Abstract: A method for generating a speech recognition model includes accessing a baseline speech recognition model, obtaining information related to recent language usage from search queries, and modifying the speech recognition model to revise probabilities of a portion of a sound occurrence based on the information. The portion of a sound may include a word. Also, a method for generating a speech recognition model, includes receiving at a search engine from a remote device an audio recording and a transcript that substantially represents at least a portion of the audio recording, synchronizing the transcript with the audio recording, extracting one or more letters from the transcript and extracting the associated pronunciation of the one or more letters from the audio recording, and generating a dictionary entry in a pronunciation dictionary.Type: ApplicationFiled: March 15, 2018Publication date: July 19, 2018Inventors: Michael H. Cohen, Shumeet Baluja, Pedro J. Moreno Mengibar
-
Publication number: 20180147493Abstract: A system and method implemented as computer-based, computer-executable instructions employing a computation engine with digital storage provide a virtual environment with personalized user profiles specifically adapted to cognitive abilities of the user to train the user for specified tasks, herein called microtasks. The set of microtasks include achievement criteria. The virtual environment is controlled through an engine that automatically adapts the set of user-profile-specific microtasks to achieve a set of learning goals. The engine may calculate and/or measure a set of qualities associated with one or more sub-profiles associated with a given user based on game-type performance by that user either in isolation or among a group of users. Sub-profiles may include, but are not limited to, one or more of the following: a personality profile, a neural link profile, and/or a motivation profile.Type: ApplicationFiled: November 15, 2017Publication date: May 31, 2018Inventors: Michael H. Cohen, Jennifer Balogh-Ghosh, Niloufar Valorie Salimpoor
-
Patent number: 9953636Abstract: A method for generating a speech recognition model includes accessing a baseline speech recognition model, obtaining information related to recent language usage from search queries, and modifying the speech recognition model to revise probabilities of a portion of a sound occurrence based on the information. The portion of a sound may include a word. Also, a method for generating a speech recognition model, includes receiving at a search engine from a remote device an audio recording and a transcript that substantially represents at least a portion of the audio recording, synchronizing the transcript with the audio recording, extracting one or more letters from the transcript and extracting the associated pronunciation of the one or more letters from the audio recording, and generating a dictionary entry in a pronunciation dictionary.Type: GrantFiled: October 9, 2015Date of Patent: April 24, 2018Inventors: Michael H. Cohen, Shumeet Baluja, Pedro J. Moreno Mengibar
-
Patent number: 9849388Abstract: A system and method implemented as computer-based, computer-executable instructions employing a computation engine with digital storage provide a virtual environment with personalized user profiles specifically adapted to cognitive abilities of the user to train the user for specified tasks, herein called microtasks. The set of microtasks include achievement criteria. The virtual environment is controlled through an engine that automatically adapts the set of user-profile-specific microtasks to achieve a set of learning goals. The engine may calculate and/or measure a set of qualities associated with one or more sub-profiles associated with a given user based on game-type performance by that user either in isolation or among a group of users. Sub-profiles may include, but are not limited to, one or more of the following: a personality profile, a neural link profile, and/or a motivation profile.Type: GrantFiled: October 24, 2016Date of Patent: December 26, 2017Assignee: Cignition, Inc.Inventors: Michael H. Cohen, Jennifer Balogh-Ghosh, Niloufar Valorie Salimpoor
-
Publication number: 20170036116Abstract: A system and method implemented as computer-based, computer-executable instructions employing a computation engine with digital storage provide a virtual environment with personalized user profiles specifically adapted to cognitive abilities of the user to train the user for specified tasks, herein called microtasks. The set of microtasks include achievement criteria. The virtual environment is controlled through an engine that automatically adapts the set of user-profile-specific microtasks to achieve a set of learning goals. The engine may calculate and/or measure a set of qualities associated with one or more sub-profiles associated with a given user based on game-type performance by that user either in isolation or among a group of users. Sub-profiles may include, but are not limited to, one or more of the following: a personality profile, a neural link profile, and/or a motivation profile.Type: ApplicationFiled: October 24, 2016Publication date: February 9, 2017Inventors: Michael H. Cohen, Jennifer Balogh-Ghosh, Niloufar Valorie Salimpoor
-
Publication number: 20160342682Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for speech recognition. One of the methods includes receiving a base language model for speech recognition including a first word sequence having a base probability value; receiving a voice search query associated with a query context; determining that a customized language model is to be used when the query context satisfies one or more criteria associated with the customized language model; obtaining the customized language model, the customized language model including the first word sequence having an adjusted probability value being the base probability value adjusted according to the query context; and converting the voice search query to a text search query based on one or more probabilities, each of the probabilities corresponding to a word sequence in a group of one or more word sequences, the group including the first word sequence having the adjusted probability value.Type: ApplicationFiled: August 8, 2016Publication date: November 24, 2016Applicant: Google Inc.Inventors: Pedro J. Moreno Mengibar, Michael H. Cohen
-
Patent number: 9498704Abstract: A system and method implemented as computer-based, computer-executable instructions employing a computation engine with digital storage provide a virtual environment with personalized user profiles specifically adapted to cognitive abilities of the user to train the user for specified tasks, herein called microtasks. The set of microtasks include achievement criteria. The virtual environment is controlled through an engine that automatically adapts the set of user-profile-specific microtasks to achieve a set of learning goals. The engine may calculate and/or measure a set of qualities associated with one or more sub-profiles associated with a given user based on game-type performance by that user either in isolation or among a group of users. Sub-profiles may include, but are not limited to, one or more of the following: a personality profile, a neural link profile, and/or a motivation profile.Type: GrantFiled: September 22, 2014Date of Patent: November 22, 2016Assignee: Cignition, Inc.Inventors: Michael H. Cohen, Jennifer Balogh-Ghosh, Niloufar Valorie Salimpoor
-
Patent number: 9495127Abstract: Methods, computer program products and systems are described for converting speech to text. Sound information is received at a computer server system from an electronic device, where the sound information is from a user of the electronic device. A context identifier indicates a context within which the user provided the sound information. The context identifier is used to select, from among multiple language models, a language model appropriate for the context. Speech in the sound information is converted to text using the selected language model. The text is provided for use by the electronic device.Type: GrantFiled: December 22, 2010Date of Patent: November 15, 2016Assignee: Google Inc.Inventors: Brandon M. Ballinger, Johan Schalkwyk, Michael H. Cohen, Cyril Georges Luc Allauzen