Automatic Chord Accompaniment With Probabilistic Jazz Voicing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional automatic music playing techniques struggle to reproduce the nuanced timing and voicing of jazz music, leading to fixed and unnatural sound patterns due to the inability to control tension notes and voicing effectively.
Innovation Solution
An automatic music playing control device that probabilistically selects voicing patterns and sound emission timings based on a combination of sound number and voicing type, allowing for natural and dynamic chord accompaniment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If predetermined chord data including available note scale data is used for automatic music playing, then automatic chord accompaniment can be achieved, but the music playing becomes fixed and cannot reproduce the nuanced timing and voicing of live jazz performance
Solution Approach 1:
The system dynamically selects voicing patterns and determines sound emission timings based on probabilistic calculations rather than using fixed predetermined data. The voicing pattern selection unit probabilistically selects from multiple voicing patterns (first pattern with tension notes, second pattern without tension notes) based on the degree of freedom parameter, enabling dynamic adaptation similar to live performance
Solution Approach 2:
The system changes the degree of freedom parameter to control the probability of selecting different voicing patterns. By adjusting this parameter, the system can vary the tension note inclusion probability, thereby changing the musical expression and adapting to different playing styles and contexts
2Adaptability or versatility
If tension notes are included in chord accompaniment to achieve jazz characteristics, then the stylistic sound is improved, but the number of sounds increases and tension notes may interfere with the melody
Solution Approach 1:
The system uses partial action by probabilistically including tension notes rather than always including them. The degree of freedom parameter controls the probability of tension note inclusion, allowing the system to use tension notes partially (when they enhance the jazz style) while avoiding excessive tension notes that would interfere with the melody or create too much sonic density
3Stability of the object's composition
If the same chords are played repeatedly in automatic music playing, then consistent chord progression is maintained, but subtle changes in playing timing and voicing that characterize live performance are lost
Solution Approach 1:
The system maintains chord progression consistency while introducing playing variation through dynamic probabilistic selection. The voicing pattern selection unit probabilistically selects different voicing patterns for the same chord progression, and the sound emission timing determination unit probabilistically determines timing variations, replicating the natural variations of live performance while maintaining the underlying chord structure
Solution Approach 2:
The system uses the degree of freedom parameter as a controllable feedback mechanism. By adjusting this parameter, users can control the balance between consistency and variation, allowing the system to adapt its behavior based on the desired level of performance naturalness
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Provided is an automatic music playing control device that provides an instruction of playing music, the control device implementing natural music playing capable of expressing the timing and voicing in live music playing of a musical instrument by a player. The automatic music playing control device includes at least one processor, and the at least one processor selects a voicing pattern corresponding to a combination of the probabilistically-selected number of sounds to be emitted and a decided voicing type corresponding to a range from among a plurality of voicing patterns based on a scale decided according to the tune and chords of a music piece and instructs a sound source to emit a chord voiced based on the selected voicing pattern.