An audio analysis method is realized by a computer and includes generating key information which represents a key, by inputting a time series of a feature amount of an audio signal into a learned model that has learned a relationship between keys and time series of feature amounts of audio signals.

Real-time jamming is automatically assisted for musicians. A real-time audio signal is received of played music that is played by at least one person. Beat is tracked of the played music from the real-time audio signal and accordingly a time of a next beat is predicted. At least one of chords; notes; and drum sounds is recognized from the real-time audio signal and repetitions in the played music are accordingly detected. A next development is predicted in the played music, based on the detected repetitions, including at least one of chords; notes; and drum sounds that will be played next, and respective timing based on the predicted time of the next beat. A real-time output is produced based on the predicted next development in the played music.

Systems, including methods and apparatus, for generating audio effects based on accompaniment audio produced by live or pre-recorded accompaniment instruments, in combination with melody audio produced by a singer. Audible broadcast of the accompaniment audio may be delayed by a predetermined time, such as the time required to determine chord information contained in the accompaniment signal. As a result, audio effects that require the chord information may be substantially synchronized with the audible broadcast of the accompaniment audio. The present teachings may be especially suitable for use in karaoke systems, to correct and add sound effects to a singer's voice that sings along with a pre-recorded accompaniment track.

Provided is an electrophonic chordophone system (20) comprising sensor (24) configured to be operatively responsive to respective strings of a guitar (22). The system (20) also includes non-transitory processor-readable storage means (26) which contains first and second user-configurable tonal formats (28) and (30). Also included is processor (32), arranged in signal communication with the sensor (24) and storage means (26), and adapted to associate a melody group of notes producible by the strings with the first tonal format (28) in a one-to-one mapping or direct correlation, and to associate a control group of notes producible by the strings with the second tonal format (30) in a one-to-many mapping or indirect correlation. Also included is a synthesiser (34), arranged in signal communication with the processor (32), and configured to produce both the first and second tonal formats simultaneously in substantial real-time. The first tonal format (28) is actuatable via the melody group of notes and the second tonal format (30) is dynamically selectable via the control group of notes and also actuatable via the melody group of notes. In this manner, a melody is producible via the first tonal format (28) with a dynamic backing track producible via the second tonal format (30), all using one guitar (22).

A method of generating a musical score file for one or more target musical instruments with a score generation component based on input audio data. The score generation component finds candidate musical notes within the input audio data using a frequency analysis to identify segments that share substantially the same audio frequency, and finds a best match for those candidate musical notes in audio data associated with target musical instruments in a sound database. A generated musical score file can be printed as sheet music or audibly played back over speakers.

Performance information of one or more accompaniment parts is extracted from original performance information. Arranged accompaniment performance information is created using, in accordance with a predetermined arranging condition, only any one or more of pitch names included in the extracted accompaniment performance information. The predetermined arranging condition comprises instructing that any of chord component notes be thinned out in an identified chord progression, and arranged accompaniment performance information is created by thinning out an accompaniment note of a pitch name corresponding to the chord component note having been instructed to be thinned out. Another predetermined arranging condition comprises setting a ratio between chords and arpeggios in one or more measures, and a combination of chords and arpeggios in the extracted accompaniment part performance information is changed so that a ratio between chords and arpeggios in one or more measures in the extracted accompaniment performance information assumes the set ratio.

A method of characterising chords in a digital music file comprises: receiving a portion of music in a digital format and for a first time interval in the music, a value of a chord feature from a set of chord features is predicted using a conditional Autoregressive Distribution Estimator (ADE). The ADE is modified using the predicted value for the chord feature and the modified ADE is used to predict a value for a different feature of the chord from the set of chord features. These operations are repeated until a value for each of the features in the set of chord features has been predicted for the first time interval. They are then repeated for subsequent time intervals in the portion of music.

The present disclosure relates to a method for generating a new chord sequence. The method comprises obtaining known chord sequences (S), wherein each known chord sequence has a respective known transition (T) between each pair of consecutive chords (C) in the known chord sequence. The method also comprises, among the chords of the known sequences, determining one or more new allowed transitions (N). The method also comprises, among the chords of the known chord sequences, generating a new chord sequence (L) based on there being a respective known or new allowed transition between each two consecutive chords in the new chord sequence, and the new chord sequence being loopable by there also being a known or new allowed transition between a first chord and a last chord in the new chord.

A method, apparatus, and User Interface, and product for assisting users learning to play the Chords of any selected Song quickly and easily and provide a Means to quickly and easily generate the individual Note sounds for the Chords of the selected Song employing a broad range of Virtual and Physical Instrument.

A visualization method for music-color synesthesia, belonging to the fields of cognitive psychology, color science and computer graphics, and relating to the visualization of the music synesthesia correlation of colors and the generation of a musical color combination scheme. In the method, a musical scale system is presented in the form of a color scale system, and the musical elements are presented through the color correlation to realize the synesthetic conversion between colors and musical elements, and on this basis, a color graphical conversion of the musical structure is performed. The implementations include: a conversion from colors to musical scales, a conversion from colors to chords, a conversion from colors to rhythm and a conversion from colors to texture etc.