Patents by Inventor Thomas Chadwick Walters
Thomas Chadwick Walters 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: 11756561Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating discrete latent representations of input audio data. Only the discrete latent representation needs to be transmitted from an encoder system to a decoder system in order for the decoder system to be able to effectively to decode, i.e., reconstruct, the input audio data.Type: GrantFiled: February 17, 2022Date of Patent: September 12, 2023Assignee: DeepMind Technologies LimitedInventors: Cristina Garbacea, Aaron Gerard Antonius van den Oord, Yazhe Li, Sze Chie Lim, Alejandro Luebs, Oriol Vinyals, Thomas Chadwick Walters
-
Publication number: 20220319527Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating discrete latent representations of input audio data. Only the discrete latent representation needs to be transmitted from an encoder system to a decoder system in order for the decoder system to be able to effectively to decode, i.e., reconstruct, the input audio data.Type: ApplicationFiled: February 17, 2022Publication date: October 6, 2022Inventors: Cristina Garbacea, Aaron Gerard Antonius van den Oord, Yazhe Li, Sze Chie Lim, Alejandro Luebs, Oriol Vinyals, Thomas Chadwick Walters
-
Publication number: 20220223162Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for bandwidth extension. One of the methods includes obtaining a low-resolution version of an input, the low-resolution version of the input comprising a first number of samples at a first sample rate over a first time period; and generating, from the low-resolution version of the input, a high-resolution version of the input comprising a second, larger number of samples at a second, higher sample rate over the first time period. Generating the high-resolution version includes generating a representation of the low-resolution version of the input; processing the representation of the low-resolution version of the input through a conditioning neural network to generate a conditioning input; and processing the conditioning input using a generative neural network to generate the high/resolution version of the input.Type: ApplicationFiled: April 30, 2020Publication date: July 14, 2022Inventors: Ioannis Alexandros Assael, Thomas Chadwick Walters, Archit Gupta, Brendan Shillingford
-
Patent number: 11257507Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating discrete latent representations of input audio data. Only the discrete latent representation needs to be transmitted from an encoder system to a decoder system in order for the decoder system to be able to effectively to decode, i.e., reconstruct, the input audio data.Type: GrantFiled: January 17, 2020Date of Patent: February 22, 2022Assignee: DeepMind Technologies LimitedInventors: Cristina Garbacea, Aaron Gerard Antonius van den Oord, Yazhe Li, Sze Chie Lim, Alejandro Luebs, Oriol Vinyals, Thomas Chadwick Walters
-
Patent number: 11003413Abstract: Systems and techniques for removing a sound recording from an audio recording (e.g., an audio recording embedded in a media file) are presented. The system can include an identification component, a first subtraction component and a second subtraction component. The identification component identifies a sound recording in a mixed audio recording. The first subtraction component determines a local linear transformation of the sound recording and subtracts the local linear transformation of the sound recording from the mixed audio recording to generate a new mixed audio recording. The second subtraction component compares one or more segments of the sound recording with one or more corresponding segments of the new mixed audio recording and reduces a power level of the new mixed audio recording based at least in part on correlation of the one or more corresponding segments with the one or more segments.Type: GrantFiled: October 22, 2015Date of Patent: May 11, 2021Assignee: Google LLCInventors: Christopher Russell LaRosa, Sam Kvaalen, Thomas Chadwick Walters, Richard Francis Lyon, Robert Steven Glickstein, Rushabh Ashok Doshi, Molly Castle Nix, Jason Matthew Toff
-
Publication number: 20210073638Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using a machine learning model that has been trained through reinforcement learning to select a content item. One of the methods includes receiving first data characterizing a first context in which a first content item may be presented to a first user in a presentation environment; and providing the first data as input to a long-term engagement machine learning model, the model having been trained through reinforcement learning to: receive a plurality of inputs, and process each of the plurality of inputs to generate a respective engagement score for each input that represents a predicted, time-adjusted total number of selections by the respective user of future content items presented to the respective user in the presentation environment if the respective content item is presented in the respective context.Type: ApplicationFiled: November 16, 2020Publication date: March 11, 2021Inventors: Benjamin Kenneth Coppin, Mustafa Suleyman, Thomas Chadwick Walters, Timothy Mann, Chia-Yueh Carlton Chu, Martin Szummer, Luis Carlos Cobo Rus, Jean-Francois Crespo
-
Patent number: 10839310Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using a machine learning model that has been trained through reinforcement learning to select a content item. One of the methods includes receiving first data characterizing a first context in which a first content item may be presented to a first user in a presentation environment; and providing the first data as input to a long-term engagement machine learning model, the model having been trained through reinforcement learning to: receive a plurality of inputs, and process each of the plurality of inputs to generate a respective engagement score for each input that represents a predicted, time-adjusted total number of selections by the respective user of future content items presented to the respective user in the presentation environment if the respective content item is presented in the respective context.Type: GrantFiled: July 15, 2016Date of Patent: November 17, 2020Assignee: Google LLCInventors: Benjamin Kenneth Coppin, Mustafa Suleyman, Thomas Chadwick Walters, Timothy Mann, Chia-Yueh Carlton Chu, Martin Szummer, Luis Carlos Cobo Rus, Jean-Francois Crespo
-
Publication number: 20200234725Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating discrete latent representations of input audio data. Only the discrete latent representation needs to be transmitted from an encoder system to a decoder system in order for the decoder system to be able to effectively to decode, i.e., reconstruct, the input audio data.Type: ApplicationFiled: January 17, 2020Publication date: July 23, 2020Inventors: Cristina Garbacea, Aaron Gerard Antonius van den Oord, Yazhe Li, Sze Chie Lim, Alejandro Luebs, Oriol Vinyals, Thomas Chadwick Walters
-
Patent number: 10210884Abstract: Systems and methods facilitating removal of content from audio files are described. A method includes identifying a sound recording in a first audio file, identifying a reference file having at least a defined level of similarity to the sound recording, and processing the first audio file to remove the sound recording and generate a second audio file. In some embodiments, winner-take-all coding and Hough transforms are employed for determining alignment and rate adjustment of the reference file in the first audio file. After alignment, the reference file is filtered in the frequency domain to increase similarity between the reference file and the sound recording. The frequency domain representation (FR) of the filtered version is subtracted from the FR first audio and the result converted to a time representation of the second audio file. In some embodiments, spectral subtraction is also performed to generate a further improved second audio file.Type: GrantFiled: May 19, 2017Date of Patent: February 19, 2019Assignee: Google LLCInventors: Richard Francis Lyon, Ron Weiss, Thomas Chadwick Walters
-
Patent number: 9971940Abstract: Provided content is determined to contain an asset represented by reference content by comparing digital fingerprints of the provided content and the reference content. The fingerprints of the reference content and the provided content are generated using a convolutional neural network (CNN). The CNN is trained using a plurality of frame triplets including an anchor frame representing the reference content, a positive frame which is a transformation of the anchor frame, and a negative frame representing content that is not the reference content. The provided content is determined to contain the asset represented by the reference content based on a similarity measure between the generated fingerprints. If the provided content is determined to contain the asset represented by the reference content, a policy associated with the asset is enforced on the provided content.Type: GrantFiled: August 8, 2016Date of Patent: May 15, 2018Assignee: GOOGLE LLCInventors: Luciano Sbaiz, Jay Yagnik, King Hong Thomas Leung, Hanna Pasula, Thomas Chadwick Walters, Thomas Bugnon, Matthias Rochus Konrad
-
Publication number: 20180018580Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using a machine learning model that has been trained through reinforcement learning to select a content item. One of the methods includes receiving first data characterizing a first context in which a first content item may be presented to a first user in a presentation environment; and providing the first data as input to a long-term engagement machine learning model, the model having been trained through reinforcement learning to: receive a plurality of inputs, and process each of the plurality of inputs to generate a respective engagement score for each input that represents a predicted, time-adjusted total number of selections by the respective user of future content items presented to the respective user in the presentation environment if the respective content item is presented in the respective context.Type: ApplicationFiled: July 15, 2016Publication date: January 18, 2018Inventors: Benjamin Kenneth Coppin, Mustafa Suleyman, Thomas Chadwick Walters, Timothy Mann, Chia-Yueh Carlton Chu, Martin Szummer, Luis Carlos Cobo Rus, Jean-Francois Crespo
-
Publication number: 20170256271Abstract: Systems and methods facilitating removal of content from audio files are described. A method includes identifying a sound recording in a first audio file, identifying a reference file having at least a defined level of similarity to the sound recording, and processing the first audio file to remove the sound recording and generate a second audio file. In some embodiments, winner-take-all coding and Hough transforms are employed for determining alignment and rate adjustment of the reference file in the first audio file. After alignment, the reference file is filtered in the frequency domain to increase similarity between the reference file and the sound recording. The frequency domain representation (FR) of the filtered version is subtracted from the FR first audio and the result converted to a time representation of the second audio file. In some embodiments, spectral subtraction is also performed to generate a further improved second audio file.Type: ApplicationFiled: May 19, 2017Publication date: September 7, 2017Inventors: Richard Francis Lyon, Ron Weiss, Thomas Chadwick Walters
-
Patent number: 9679579Abstract: Systems and methods facilitating removal of content from audio files are described. A method includes identifying a sound recording in a first audio file, identifying a reference file having at least a defined level of similarity to the sound recording, and processing the first audio file to remove the sound recording and generate a second audio file. In some embodiments, winner-take-all coding and Hough transforms are employed for determining alignment and rate adjustment of the reference file in the first audio file. After alignment, the reference file is filtered in the frequency domain to increase similarity between the reference file and the sound recording. The frequency domain representation (FR) of the filtered version is subtracted from the FR first audio and the result converted to a time representation of the second audio file. In some embodiments, spectral subtraction is also performed to generate a further improved second audio file.Type: GrantFiled: June 20, 2016Date of Patent: June 13, 2017Assignee: Google Inc.Inventors: Richard Francis Lyon, Ron Weiss, Thomas Chadwick Walters
-
Patent number: 9659014Abstract: Aspects relate to determining whether a probe media content matches one or more reference media content. The reference media content is classified into a content class. The probe media content could also be classified into a content class. Similarities between the probe media content and the reference media content are identified. A matching score given to the probe media content is weighted based on statistics regarding matches and false-positive rates for the content class of the reference media content. Further, classifiers can be trained on computed audio features and video features and/or video metadata and audio metadata of various media content.Type: GrantFiled: September 11, 2013Date of Patent: May 23, 2017Assignee: Google Inc.Inventors: Thomas Chadwick Walters, Gertjan Pieter Halkes, Matthias Rochus Konrad, Gheorghe Postelnicu
-
Patent number: 9373320Abstract: Systems and methods facilitating removal of content from audio files are described. A method includes identifying a sound recording in a first audio file, identifying a reference file having at least a defined level of similarity to the sound recording, and processing the first audio file to remove the sound recording and generate a second audio file. In some embodiments, winner-take-all coding and Hough transforms are employed for determining alignment and rate adjustment of the reference file in the first audio file. After alignment, the reference file is filtered in the frequency domain to increase similarity between the reference file and the sound recording. The frequency domain representation (FR) of the filtered version is subtracted from the FR first audio and the result converted to a time representation of the second audio file. In some embodiments, spectral subtraction is also performed to generate a further improved second audio file.Type: GrantFiled: August 21, 2013Date of Patent: June 21, 2016Assignee: Google Inc.Inventors: Richard Francis Lyon, Ron Weiss, Thomas Chadwick Walters
-
Publication number: 20160041807Abstract: Systems and techniques for removing a sound recording from an audio recording (e.g., an audio recording embedded in a media file) are presented. The system can include an identification component, a first subtraction component and a second subtraction component. The identification component identifies a sound recording in a mixed audio recording. The first subtraction component determines a local linear transformation of the sound recording and subtracts the local linear transformation of the sound recording from the mixed audio recording to generate a new mixed audio recording. The second subtraction component compares one or more segments of the sound recording with one or more corresponding segments of the new mixed audio recording and reduces a power level of the new mixed audio recording based at least in part on correlation of the one or more corresponding segments with the one or more segments.Type: ApplicationFiled: October 22, 2015Publication date: February 11, 2016Inventors: Christopher Russell LaRosa, Sam Kvaalen, Thomas Chadwick Walters, Richard Francis Lyon, Robert Steven Glickstein, Rushabh Ashok Doshi, Molly Castle Nix, Jason Matthew Toff
-
Patent number: 9195431Abstract: Systems and techniques for removing a sound recording from an audio recording (e.g., an audio recording embedded in a media file) are presented. The system can include an identification component, a first subtraction component and a second subtraction component. The identification component identifies a sound recording in a mixed audio recording. The first subtraction component determines a local linear transformation of the sound recording and subtracts the local linear transformation of the sound recording from the mixed audio recording to generate a new mixed audio recording. The second subtraction component compares one or more segments of the sound recording with one or more corresponding segments of the new mixed audio recording and reduces a power level of the new mixed audio recording based at least in part on correlation of the one or more corresponding segments with the one or more segments.Type: GrantFiled: December 28, 2012Date of Patent: November 24, 2015Assignee: Google Inc.Inventors: Christopher Russell LaRosa, Sam Kvaalen, Thomas Chadwick Walters, Richard Francis Lyon, Robert Steven Glickstein, Rushabh Ashok Doshi, Molly Castle Nix, Jason Matthew Toff
-
Patent number: 9158842Abstract: Sound representations and winner-take-all codes of auditory spectra are used in the identification of audio content. A transformation component converts a set of sound frames from audio content into a set of spectral slices. A spectral encoder component encodes the spectral slices of auditory spectra into winner-take-all codes with a winner-take-all hash function. An identification component identifies which spectral dimension of a subset of spectral dimensions within a spectral slice has highest spectral value according to the winner-take-all codes. Reference audio content is determined to be similar or matching to the audio content based on the winner-take-all codes.Type: GrantFiled: September 14, 2012Date of Patent: October 13, 2015Assignee: GOOGLE INC.Inventors: Jay Yagnik, Richard Francis Lyon, Thomas Chadwick Walters, Douglas Eck
-
Publication number: 20130338806Abstract: Systems and techniques for removing a sound recording from an audio recording (e.g., an audio recording embedded in a media file) are presented. The system can include an identification component, a first subtraction component and a second subtraction component. The identification component identifies a sound recording in a mixed audio recording. The first subtraction component determines a local linear transformation of the sound recording and subtracts the local linear transformation of the sound recording from the mixed audio recording to generate a new mixed audio recording. The second subtraction component compares one or more segments of the sound recording with one or more corresponding segments of the new mixed audio recording and reduces a power level of the new mixed audio recording based at least in part on correlation of the one or more corresponding segments with the one or more segments.Type: ApplicationFiled: December 28, 2012Publication date: December 19, 2013Applicant: GOOGLE INC.Inventors: Christopher Russell LaRosa, Sam Kvaalen, Thomas Chadwick Walters, Richard Francis Lyon, Robert Steven Glickstein, Rushabh Ashok Doshi, Molly Castle Nix, Jason Matthew Toff