A method for adjusting accompaniment music is disclosed. The method transposes the musical key of at least one section of the accompaniment music such that a song will have different musical key transpositions for different sections of the accompaniment music, so that singers whose vocal ranges are narrow can sing songs after the adjustment.

A method for processing information, terminal device and a computer storage medium are disclosed. The method for processing information includes that: a first control instruction is acquired, and a first application is switched to a preset mode according to the first control instruction; a first triggering operation is acquired based on the preset mode, at least two pieces of multimedia data are selected based on the first triggering operation, and a first playing interface is generated; when a second control instruction is acquired, the at least two pieces of multimedia data in the first playing interface are sequentially played; in a process of playing first multimedia data in the at least two pieces of multimedia data, first audio data is acquired; and the first multimedia data and the first audio data are synthesized as second multimedia data.

User interface techniques provide user vocalists with mechanisms for seeding subsequent performances by other users (e.g., joiners). A seed may be a full-length seed spanning much or all of a pre-existing audio (or audiovisual) work and mixing, to seed further contributions of one or more joiners, a user's captured media content for at least some portions of the audio (or audiovisual) work. A short seed may span less than all (and in some cases, much less than all) of the audio (or audiovisual) work. For example, a verse, chorus, refrain, hook or other limited “chunk” of an audio (or audiovisual) work may constitute a seed. A seeding user's call invites other users to join the full-length or short-form seed by singing along, singing a particular vocal part or musical section, singing harmony or other duet part, rapping, talking, clapping, recording video, adding a video clip from camera roll, etc. The resulting group performance, whether full-length or just a chunk, may be posted, livestreamed, or otherwise disseminated in a social network.

A tool is needed for music instrument learners to get feedbacks on the correctness of their performances of a particular piece of music. The invention disclosed here is such a tool that can provide music instrument players instant feedback on note pitch and rhythms accuracy based on sheet music. This is accomplished through audio signal processing, sheet music image processing, and conversion of both analogue images and audio signals into standard digital music representation so a comparison can be done and hence a feedback can be presented to the player. An advanced feature will allow users to save the data to the cloud and retrieve later for comparison of progress. It also will allow user to participate an online competition with other players of the same piece of music.

A music generation device includes: an acquisition unit that acquires first stream data and second stream data different from the first stream data; an accompaniment generation unit that generates accompaniment information, which is music data indicating an accompaniment, based on a change in the first stream data; a melody generation unit that generates melody information, which is music data indicating a melody, based on a change in the second stream data; a melody adjustment unit that adjusts the melody information in accordance with a key of the accompaniment indicated by the generated accompaniment information; a music combining unit that combines the accompaniment information and the adjusted melody information to generate musical piece information; and an output unit that outputs the generated musical piece information.

A method for training one or more AI models for generating audio scores accompanying visual datasets includes obtaining training data comprising a plurality of audiovisual datasets and analyzing each of the plurality of audiovisual datasets to extract multiple visual features, textual features, and audio features. The method also includes correlating the multiple visual features and textual features with the multiple audio features via a machine learning network. Based on the correlations between the visual features, textual features, and audio features, one or more AI models are trained for composing one or more audio scores for accompanying a given dataset.

In an electronic device for an electronic musical instrument, a determination grace period during which a plurality of operations on the electronic musical instrument by a user are determined to be simultaneously performed for the first section is set based on the data included in a first section of the song having a plurality of sections. Automatic accompaniment is advanced from the first section to the next second section when a user operation of the electronic musical instrument is detected outside of the determination grace period for the first section during the playback of the first section of the accompaniment, and automatic accompaniment is not advanced from the first section to the second section when the user operation of the electronic musical instrument is detected within the determination grace period for the first section during the playback of the first section of the accompaniment.

[Problem] To provide an arpeggiator capable of suppressing sound muddiness caused by simultaneous production of sounds in a multi-arpeggiator capable of automatically playing arpeggios in a plurality of performance parts, and a program provided with the function of the arpeggiator. [Solution] A synthesizer 1 decreases velocity in velocity memory 12c in accordance with a duck rate when the time of sound production for a sound production part is the same as the time of sound production for a duck part, and at that time of sound production, a note number of the duck part is the same as a note number of a duck note. This makes it possible to suppress muddiness of output sound, since an increase in output level is suppressed even when a plurality parts produce sound at the same time.

[Problem] To provide an arpeggiator enabling musically natural arpeggio playing to be achieved, and a program comprising a function therefor. [Solution] In the present invention, a synthesizer 1 resets the number of octaves in an octave counter memory 12d to zero at the beginning of each bar when an octave reset function is on. Due to this configuration, sounds generated at the beginning of each bar, that is, when the step count is 0, all have the same note number. Consequently, a sound generation timing-based cycle of an arpeggio pattern of each bar can be synchronized with a pitch variation-based cycle, making it possible to give a listener the impression that a consistent phrase is being played.

A method for synchronizing a pre-recorded music accompaniment to a music playing of a user. The music playing is captured by at least one microphone, which delivers an input acoustic signal feeding a processing unit, which includes a memory for storing data of the music accompaniment and provides an output acoustic signal based on the music accompaniment data to feed at least a loudspeaker playing the music accompaniment. The processing unit analyses the input acoustic signal to detect musical events and music tempo, compares the detected musical events to the music accompaniment data to determine at least a lag between the timings of the detected musical events and the musical events of the music accompaniment, and adapts a timing of the output acoustic signal based on the lag and a synchronization function calculated from a temporal variable, the user's music tempo, and the duration of compensation of the lag.