Methods, systems and non-transitory computer-readable mediums for remote audio project collaboration. The method includes generating a first version of an audio project file including a reference track. The method also includes receiving a first audio track from a first user computing device. The first audio track is synced to the reference track. The method further includes generating a second version of the audio project file by adding the first audio track to the audio project file. The method also includes receiving a second audio track from a second user computing device. The second audio track is synced to the reference track. The second user computing device is remotely located from the first user computing device. The method further includes generating a third version of the audio project file by adding the second audio track to the audio project file.

An apparatus, method, and computer-readable storage medium that generate a harmonized musical piece. The method includes receiving a chord selection including a musical key and a scale selection, generating, within a digital audio work session, a chord progression sequence based on the received chord selection, in response to a detected chord selection change, modifying the chord progression sequence to include a chord progression corresponding to the chord selection change, setting the chord progression sequence as a master sequence, in response to detecting a second progression sequence within the digital audio work session, transmitting an identifier to the second progression sequence setting it as a slave sequence, and establishing a synchronized communication link between the master and the slave sequences such that changes made in the master sequence are automatically effectuated in the slave sequence, and combining the master sequence and the slave sequence to form a composed musical piece.

A method, system, and medium for affective music recommendation and composition. A listener's current affective state and target affective state are identified, and an audio stream, such as a music playlist, is generated with the intent of effecting a controlled trajectory of the listener's affective state from the current state to the target state. The audio stream is generated by a machine learning system trained using data from the listener and/or other users indicating the effectiveness of specific audio segments, or audio segments having specific features, in effecting the desired affective trajectory. The audio stream is presented to the user as an auditory stimulus. The machine learning system may be updated based on the affective state changes induced in the listener after exposure to the auditory stimulus. Over time, the machine learning system gains a robust understanding of the relationship between music and human affect, and thus the machine learning system may also be used to compose, master, and/or adapt music configured to induce specific affective responses in listeners.

The invention generates progressive music in real-time for video games using random, seeded random, and manually input variables to affect melody, phrase length, harmonic chords and complexity, and percussive accompaniment. As the game is played, variables may be passed in that change the music to increase or decrease complexity and tension levels and to interpolate between styles. The generated music then progresses from stable, simple, and consonant to more tense, dissonant, and complex melodies, harmonies and rhythms, and back to the original stage as a musical resolution. Through variables controlling musical parameters, music may progressively change from the atonal region where there is no clear resolution or stability, to tonal, where there is only consonance and stability, and anywhere in between. These variables are assigned through a middleware or a game-engine setup that uses the current device as an audio source plugin, or manually coded into the individual video game.

Audio translation system includes a feature extractor and a style transfer machine learning model. The feature extractor generates for each of a plurality of source voice files one or more source voice parameters encoded as a collection of source feature vectors, and generates for each of a plurality of target voice files one or more target voice parameters encoded as a collection of target feature vectors. The style transfer machine learning model trained on the collection of source feature vectors for the plurality of source voice files and the collection of target feature vectors for the plurality of target voice files to generate a style transformed feature vector.

This information processing device comprises: a control unit which receives an input of information indicating one or more timings in a playback time of a piece of music, and generates a file including information pertaining to a timbre control performed from each of the one or more timings; and a transmission unit which transmits an audio signal of the piece of music and the information pertaining to the timbre control in the file to a device which outputs a synthesized sound of the playback sound of the piece of music and the playing sound of a musical instrument.

Systems and methods for providing audio-file loop-playback functionality are provided. The system includes a processor that performs a method including setting a playback loop start-point based on a first selection of a button; setting a loop end-point, associating a loop with an audio file, and entering into the loop based on a second selection of the button; and exiting the loop based on a third selection of the button. Associating the loop with the audio file includes adding metadata to the audio file. The metadata associates the loop with a button. The method includes reentering the loop based on a fourth selection of the button and exiting the loop based on a fifth selection of the button.

The disclosed technology relates to a process for detecting musical artifacts within a musical composition. The detection of musical artifacts is based on analyzing the energy and frequency of the digital signal of the musical composition. The identification of musical artifacts within a musical composition would be used in connection with audio-video editing.

Presentation of a recommendation to a user for individual processing of audio tracks in a digital audio workstation. Training audio tracks are provided to a human sound mixer and responsive to the training audio tracks individually processed training audio tracks are received from the human sound mixer. The training audio tracks and the individually processed training audio tracks are input to a machine to train the machine. Audio processing operations are output from the trained machine and stored in a record of a database.

Conventionally, significant time and effort are required to construct audio tracks. Disclosed embodiments enable automation of audio tracks using templates that associate sound generator(s) with template section(s). Each template enables a model to automatically generate unique audio tracks in which the sections and/or sounds are probabilistically determined. Certain embodiments introduce additional variability into the automated generation of audio tracks. In addition, the model may generate the audio tracks, note by note, to ensure that no copyrights are infringed.