Spotify Ab

Sony France S.a.

Sony Corporation

Soundtrap Ab

Sony Europe Limited

François Pachet

Pierre Roy

Mathieu Ramona

Tristan Jehan

Juan José Bosch Vicente

Jean-Julien Aucouturier

Luc Steels

Gabriele Barbieri

Daniel Cazaly

Olivier Delerue

Stanislaw Gorlow

Aymeric Zils

Benoit Jean Carré

Jonathan Donier

Olumide John Okubadejo

An electronic device receives a source audio file from a user of a digital audio workstation and a target MIDI file, the target MIDI file comprising digital representations for a series of notes. The electronic device generates a series of sounds from the target MIDI file, each respective sound in the series of sounds corresponding to a respective note in the series of notes. The electronic device divides the source audio file into a plurality of segments. For each sound in the series of sounds, the electronic device matches a segment from the plurality of segments to the sound based on a weighted combination of features identified for the corresponding sound. The electronic device generates an audio file in which the series of sounds from the target MIDI file are replaced with the matched segment corresponding to each sound.

Systems and methods for generating a mixed audio file in a digital audio workstation

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.

Audio stem identification systems and methods

A skip behavior analyzer is part of a media delivery system that allows for unbiased A/B testing of a plurality of versions of a song. The media delivery system stores a plurality of versions of a song and randomly selects, for each requesting device, a version of the song to associate with that device. Each time the device requests the song, thereafter, the media delivery system will provide the same version of the song for consistency. The media delivery system then gathers song play and skip information, calculates the differences in distribution of the skip behavior, and provides the skip information to allow a music composer to better determine which version of a song is more popular and why that is so.

Skip behavior analyzer

A system is provided for editing an audio file. The system displays, on an electronic device, a piano roll. The system receives a user input to cut a segment of the piano roll. The segment of the piano roll includes a respective tone that extends across both sides of the segment of the piano roll, such that the respective tone includes: a first portion of the respective tone that precedes the segment of the piano roll; and a second portion of the respective tone that follows the segment of the piano roll. In response to the user input to cut the segment of the piano roll, the system cuts the segment from the piano roll and, without user intervention, concatenate the first portion of the respective tone with the second portion of the respective tone.

Editing of midi files

A computing device comprising a display screen, the computing device being configured to decompose a media recording into a plurality of media recording salient events, apply each of the media recording salient events to a reinforcement model, display on the display screen (i) a mapping of the plurality of media recording salient events and (ii) for at least one of the plurality of media recording salient events, at least one selectable next best action, the computing device further configured to replace at least one of the plurality of media recording salient events with at least one selectable next best action to create a derivative media recording including at least one replacement media recording action.

User consumption behavior analysis and composer interface

The present disclosure relates to a method of automatically preparing a MIDI file based on a target MIDI file comprising respective note information about each of a plurality of target notes and a source MIDI file comprising respective note information about each of a plurality of source notes. Each note information comprises pitch information defining a pitch of the note. The method comprises ranking the plurality of target notes based on the pitch of each target note. The method also comprises, for each of the ranked target notes, removing the pitch information from the note information of the target note. The method also comprises, for each of the ranked target notes, replacing the removed pitch information with pitch information of a corresponding source note, whereby the target note has the same pitch as the corresponding source note, forming a plurality of new notes of a new MIDI file.

Automatic preparation of a new MIDI file

An electronic device segments a first and second MIDI files into pluralities of source segments and target segments. For each of a plurality of consecutive pairs of first and second target segments, the electronic device identifies a first source segment corresponding to the first target segment of the consecutive pair and identifies a second source segment corresponding to the second target segment of the consecutive pair, where the first and second source segments are identified by determining that the first and second source segments are harmonically conformant to the corresponding first and second target segments, and determining that a transition between the first and second source segments is graphically conformant to a transition between a consecutive pair of source segments. The electronic device generates a third MIDI file using the identified first and second source segments for each of the plurality of consecutive pairs of first and second target segments.

Automatic orchestration of a MIDI file

A training set for use during content generation is generated by applying a first machine learning process Pto a first finite sequence s wherein s has a length Ls, to generate a first statistical model M(s). The first statistical model M(s) is sampled using a first sampling process G to generate a second finite sequence t wherein t has a length Lt. A second machine learning process Pis applied to the second finite sequence t to generate a second statistical model M(t), wherein no substring of the second finite sequence t of length d is identical to a substring of the first finite sequence s, wherein d is a predetermined number of elements in a sequence.

Methods, systems and computer program products for generating a training set for use during content generation

A device for automatically generating a real time accompaniment of input music data includes a music input that receives music data. A music analyzer analyzes received music data to obtain a music data description including one or more characteristics of the analyzed music data. A query generator generates a query to a music database including music patterns and associated metadata including one or more characteristics of the music patterns, the query being generated from the music data description and from an accompaniment description describing preferences of the real time accompaniment and/or music rules describing general rules of music. A query interface queries the music database using a generated query and receives a music pattern selected from the music database by use of the query. A music output outputs the received music pattern.

Device, system and method for generating an accompaniment of input music data

Methods, systems and computer program products are provided for testing a lead sheet for plagiarism. A test lead sheet receiving having a plurality of passages is received at receiving a plagiarism detector. A set of annotations describing a level of plagiarism of a plurality of elements (e.g., chord sequence, subsequences, melodic fragments (i.e., notes), rhythm, harmony, etc.) of the test lead sheet in relation to the preexisting lead sheets are generated and output via an output device.

Plagiarism risk detector and interface

Methods, systems and computer program products are provided for identifying an audio stem. Audio stems (t, . . . , t) are stored on a stem database and songs (S, . . . , S) made with at least a subset of the plurality of the audio stems (t, . . . , t) 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 (t, . . . , t) to be complementary to the at least partially composed song (S*).

The present disclosure relates to a method of editing an audio stream (S) having at least one tone (T) extending over time in said stream. The method comprises cutting the stream at a first time point of the stream, producing a first cut (A) having a left cutting end (A) and a right cutting end (A); allocating a respective memory cell to each of the cutting ends; in each of the memory cells, storing information about the tone; and, for one of the cutting ends, concatenating the cutting end with a further stream cutting end which also has an allocated memory cell with information stored therein about any tones extending to said further cutting end. The concatenating comprises using the information stored in the memory cells for adjusting any of the tones extending to the cutting ends.

Growing community of inventors

Paris, France

François Pachet