Generating music accompaniment
AssigneeMacdougal Street Technology, Inc.
InventorsIlia Belikov, Aleksandr Alekseev, Vazgen Hakobjanyan, Robert Joseph Pfeifer
Life of this patent
Estimating the term…
Abstract
Techniques are described for generating music data for accompaniment using machine learning (ML) techniques. In an implementation, MIDI-formatted music data is tokenized as a music token sequence. Based on the input music token sequence of a portion of an original music signal, a trained ML model generates an output music token sequence for a portion of a generated music signal. Such a portion of the generated music signal is temporally ahead of the portion of the original music signal, which was used to generate the portion of the generated music signal.
Claims21
A computer-implemented method comprising:
- receiving first input music sequence data that is based, at least in part, on acquiring a first portion of an original audio music signal in real-time at least by sampling the original audio music signal;
- based at least in part on the first input music sequence data, generating, by a machine learning (ML) model, first output music sequence data for an output music signal;
- while receiving third input music sequence data that is based, at least in part, on acquiring a third portion of the original audio music signal in real-time, which is temporally after the first portion and a second portion of the original audio music signal:
- generating, by the ML model, second output music sequence data, for the output music signal, based at least in part on a previously generated particular portion of the first output music sequence data;
- temporally aligning the first output music sequence data of the output music signal with the third portion of the original audio music signal;
- wherein the second output music sequence data is temporally after the first output music sequence data of the output music signal.
One or more non-transitory computer-readable media storing a set of instructions, wherein the set of instructions includes instructions, which when executed by one or more processors, cause:
- receiving first input music sequence data that is based, at least in part, on acquiring a first portion of an original audio music signal in real-time at least by sampling the original audio music signal;
- based at least in part on the first input music sequence data, generating, by a machine learning (ML) model, first output music sequence data for an output music signal;
- while receiving third input music sequence data that is based, at least in part, on acquiring a third portion of the original audio music signal in real-time, which is temporally after the first portion and a second portion of the original audio music signal:
- generating, by the ML model, second output music sequence data, for the output music signal, based at least in part on a previously generated particular portion of the first output music sequence data;
- temporally aligning the first output music sequence data of the output music signal with the third portion of the original audio music signal;
- wherein the second output music sequence data is temporally after the first output music sequence data of the output music signal.
A system comprising one or more processors and one or more storage media storing one or more computer programs for execution by the one or more processors, wherein the one or more computer programs, when executed by the one or more processors, cause:
- receiving first input music sequence data that is based, at least in part, on acquiring a first portion of an original audio music signal in real-time at least by sampling the original audio music signal;
- based at least in part on the first input music sequence data, generating, by a machine learning (ML) model, first output music sequence data for an output music signal;
- while receiving third input music sequence data that is based, at least in part, on acquiring a third portion of the original audio music signal in real-time, which is temporally after the first portion and a second portion of the original audio music signal:
- generating, by the ML model, second output music sequence data, for the output music signal, based at least in part on a previously generated particular portion of the first output music sequence data;
- temporally aligning the first output music sequence data of the output music signal with the third portion of the original audio music signal;
- wherein the second output music sequence data is temporally after the first output music sequence data of the output music signal.
Dependencies are inferred from the claim text.