To generate a melody, one or more machine-readable constraints are accepted from a user through a user interface. The constraints include rhythm constraints and pitch constraints. A sequence of musical elements is generated based on the constraints, each of the musical elements specifying, in machine-readable data, a musical pitch or silence and a duration of the musical pitch or silence. The pitch constraints prescribe pitches in the sequence of musical elements and the rhythm constraints prescribe rhythm of the sequence of musical elements. The sequence of musical elements is rendered in human-perceivable form as a melody.

A computer-implemented method of generating a musical composition containing a plurality of musical texture groups is disclosed. The method includes assembling musical texture groups from musical instrument components and associating therewith a tag expressing emotional textural connotation. The instrument components have musical textural classifiers selected from a set of pre-defined textural classifiers such that different instrument components may have a different subset of pre-defined textural classifiers. The textural classifiers within a texture group possess either no musical feature attribute or a single musical feature attribute and any number of musical accompaniment attributes. The method then generates at least one chord scheme to a narrative brief, to provide an emotional connotation to a series of events, the chord scheme generated by selecting and assembling Form Atoms. The final step includes applying a texture to the chord scheme to generate the musical composition reflecting the narrative brief.

A Form Atom defined by self-contained constructional properties representing a historical corpus of music and contained within metadata of the Form Atom is disclosed. The Form Atom has a generative set of heuristics to support generation of a set of chords in a chord scheme or many different sets of chords. The generated chords are spaced out within a defined window of musical time by chord spacer heuristics. The Form Atom has a tag describing its compositional heuristics. A chord list of the Form Atom is provided in local tonic and defines branching structures that may be used for the generation of different chords from the local tonic. A progression descriptor is combined with a form function such that the Form Atom expresses musically a question, an answer and a statement. A meta-map of a chord scheme for a musical section is created from the metadata.

A processor-based method of producing a generative musical composition is disclosed herein. The method includes the step of receiving a briefing narrative which describes a musical journey by referencing a plurality of emotional descriptions related to a plurality of musical sections. The generative musical composition is assembled with regard to the briefing narrative through the selection and concatenation of Form Atoms with tags that align with the emotional descriptions related to the musical sections. The Form Atoms, which have compositional nature aligned with the emotional descriptions and self-contained constructional properties representative of the historical corpus of music, are then selected and substituted into the generative composition. The method further involves the step of generating the musical composition by mapping musical transition between selectively chosen Form Atoms to reflect pre-established transitions between Form Atoms and groups Form Atoms that have been identified to have similar tags but different constructional properties.

The disclosure provides a method and an apparatus for song generation. A text input may be received. A topic and an emotion may be extracted from the text input. A melody may be determined according to the topic and the emotion. Lyrics may be generated according to the melody and the text input. A song may be generated at least according to the melody and the lyrics.

A generative composition system reduces existing musical artefacts to constituent elements termed “Form Atoms”. These Form Atoms may each be of varying length and have musical properties and associations that link together through Markov chains. To provide myriad new composition, a set of heuristics ensures that musical textures between concatenated musical sections follow a supplied and defined briefing narrative for the new composition whilst contiguous concatenated Form Atoms are also automatically selected to see that similarities in respective and identified attributes of musical textures for those musical sections are maintained to support maintenance of musical form. Independent aspects of the disclosure further ensure that, within the composition work, such as a media product or a real-time audio stream, chord spacing determination and control are practiced to maintain musical sense in the new composition. Further, a structuring of primitive heuristics operates to maintain pitch and permit key transformation. The system and its functionality provides signal analysis and music generation through allowing emotional connotations to be specified and reproduced from cross-referenced Form-Atoms.

A generative composition system reduces existing musical artefacts to constituent elements termed “Form Atoms”. These Form Atoms may each be of varying length and have musical properties and associations that link together through Markov chains. To provide myriad new composition, a set of heuristics ensures that musical textures between concatenated musical sections follow a supplied and defined briefing narrative for the new composition whilst contiguous concatenated Form Atoms are also automatically selected to see that similarities in respective and identified attributes of musical textures for those musical sections are maintained to support maintenance of musical form. Independent aspects of the disclosure further ensure that, within the composition work, such as a media product or a real-time audio stream, chord spacing determination and control are practiced to maintain musical sense in the new composition. Further, a structuring of primitive heuristics operates to maintain pitch and permit key transformation. The system and its functionality provides signal analysis and music generation through allowing emotional connotations to be specified and reproduced from cross-referenced Form-Atoms.

To generate a melody, one or more machine-readable constraints are accepted from a user through a user interface. The constraints include rhythm constraints and pitch constraints. A sequence of musical elements is generated based on the constraints, each of the musical elements specifying, in machine-readable data, a musical pitch or silence and a duration of the musical pitch or silence. The pitch constraints prescribe pitches in the sequence of musical elements and the rhythm constraints prescribe rhythm of the sequence of musical elements. The sequence of musical elements is rendered in human-perceivable form as a melody.

According to an embodiment, there is provided a system and method for automatic AI-based song construction based on ideas of a user. In some embodiments, an embodiment is provided with a database that contains harmony templates which can be used by the user to augment the playback of a given music work. Various embodiments of the instant invention also benefit from a combination of expert knowledge resident in an expert engine which contains rules for musically correct song generation and machine learning in an AI-based audio loop selection engine for the selection of compatible audio loops from a database of audio loops.

An electronic musical instrument includes an operation unit that receives a user performance; and at least one processor. wherein the at least one processor performs the following: in accordance with a user operation specifying a chord on the operation unit, obtaining lyric data of a lyric and obtaining a plurality of pieces of waveform data respectively corresponding to a plurality of pitches indicated by the specified chord; inputting the obtained lyric data to a trained model that has been trained and learned singing voices of a singer so as to cause the trained model to output acoustic feature data in response thereto; synthesizing each of the plurality of pieces of waveform data with the acoustic feature data so as to generate a plurality of pieces of synthesized waveform data; and outputting a polyphonic synthesized singing voice based on the generated plurality of pieces of synthesized waveform data.