Patents by Inventor Mathieu RAMONA

Mathieu RAMONA 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: 11238839
    Abstract: Methods, systems and computer program products are provided for identifying an audio stem. Audio stems (t1, . . . , tN) are stored on a stem database and songs (S1, . . . , SP) made with at least a subset of the plurality of the audio stems (t1, . . . , tN) are stored on a song database. At least partially composed song (S*) having a predetermined number of pre-selected stems (k) are received. In turn, a probability vector (or relevance value or ranking) is produced for each stem (t1, . . . , tN) to be complementary to the at least partially composed song (S*).
    Type: Grant
    Filed: September 19, 2019
    Date of Patent: February 1, 2022
    Assignee: Spotify AB
    Inventors: François Pachet, Pierre Roy, Mathieu Ramona, Tristan Jehan, Juan José Bosch Vicente
  • Publication number: 20210312941
    Abstract: Methods, systems and computer program products are provided for determining acoustic feature vectors of query and target items in a first vector space, and mapping the acoustic feature vectors to a second vector space having a lower dimension. The distribution of vectors in the second vector space can then be used to identify items from the same songs, and/or items that are complementary. A mapping function is trained using a machine learning algorithm, such that complementary audio items are closer in the second vector space than the first, according to a given distance metric.
    Type: Application
    Filed: March 16, 2021
    Publication date: October 7, 2021
    Applicant: Spotify AB
    Inventors: Juan José Bosch Vicente, François Pachet, Pierre Roy, Mathieu Ramona, Tristan Jehan
  • Patent number: 10997986
    Abstract: Methods, systems and computer program products are provided for determining acoustic feature vectors of query and target items in a first vector space, and mapping the acoustic feature vectors to a second vector space having a lower dimension. The distribution of vectors in the second vector space can then be used to identify items from the same songs, and/or items that are complementary. A mapping function is trained using a machine learning algorithm, such that complementary audio items are closer in the second vector space than the first, according to a given distance metric.
    Type: Grant
    Filed: September 19, 2019
    Date of Patent: May 4, 2021
    Assignee: Spotify AB
    Inventors: Juan José Bosch Vicente, François Pachet, Pierre Roy, Mathieu Ramona, Tristan Jehan
  • Publication number: 20210090590
    Abstract: Methods, systems and computer program products are provided for determining acoustic feature vectors of query and target items in a first vector space, and mapping the acoustic feature vectors to a second vector space having a lower dimension. The distribution of vectors in the second vector space can then be used to identify items from the same songs, and/or items that are complementary. A mapping function is trained using a machine learning algorithm, such that complementary audio items are closer in the second vector space than the first, according to a given distance metric.
    Type: Application
    Filed: September 19, 2019
    Publication date: March 25, 2021
    Applicant: Spotify AB
    Inventors: Juan José Bosch Vicente, François Pachet, Pierre Roy, Mathieu Ramona, Tristan Jehan
  • Publication number: 20210090536
    Abstract: Methods, systems and computer program products are provided for identifying an audio stem. Audio stems (t1, . . . , tN) are stored on a stem database and songs (S1, . . . , SP) made with at least a subset of the plurality of the audio stems (t1, . . . , tN) are stored on a song database. At least partially composed song (S*) having a predetermined number of pre-selected stems (k) are received. In turn, a probability vector (or relevance value or ranking) is produced for each stem (t1, . . . , tN) to be complementary to the at least partially composed song (S*).
    Type: Application
    Filed: September 19, 2019
    Publication date: March 25, 2021
    Applicant: Spotify AB
    Inventors: François Pachet, Pierre Roy, Mathieu Ramona, Tristan Jehan, Juan José Bosch Vicente
  • Patent number: 9936295
    Abstract: An electronic device comprising a processing unit arranged to determine an estimation signal (y(k)) based on an input signal (x(k)) and based on a non-stationary reference signal (s0(k)).
    Type: Grant
    Filed: July 11, 2016
    Date of Patent: April 3, 2018
    Assignee: Sony CORPORATION
    Inventors: Stanislaw Gorlow, Mathieu Ramona, Francois Pachet
  • Publication number: 20170026748
    Abstract: An electronic device comprising a processing unit arranged to determine an estimation signal (y(k)) based on an input signal (x(k)) and based on a non-stationary reference signal (s0(k)).
    Type: Application
    Filed: July 11, 2016
    Publication date: January 26, 2017
    Applicant: Sony Corporation
    Inventors: Stanislaw GORLOW, Mathieu RAMONA, Francois PACHET