Harmonic Classification with Enhancing Music Using Deep Learning Techniques

Automatic extraction of features from harmonic information of music audio is considered in this paper. Automatically obtaining of relevant information is necessary not just for analysis but also for the commercial issue such as music program of tutoring and generating of lead sheet. Two aspects of harmony are considered, chord and global key, facing the issue of the extraction problem by the algorithm of machine learning. Contribution here is to recognize chords in the music by the feature extraction method (voiced models) that performd better than manually one. The modelling carried out chord sequence, getting from frame-by-frame basis, which is known in recognition of the chord system. Technique of machine learning such the convolutional neural network (CNN) will systematically extract the chord sequence to achieve the superiority context model. Then, traditional classification is used to create the key classifier which is better than others or manually one. Datasets used to evaluate the proposed model show good achievement results compared with existing one.

Tonal priming is resistant to changes in pitch height

Research on tonal priming has consistently shown that tonally expected events are processed more efficiently and has confirmed that the locus of the effect is cognitive rather than sensory. However, it is also important to investigate the role of pitch height, because models of tonal priming collapse across octaves, yet it is possible that pitch height may modulate the effectiveness of tonal priming. We systematically tested this issue by varying the pitch heights of a related (tonic) or a less-related (subdominant) target chord following a tonal context. Musically untrained participants (N = 30) made speeded consonant/dissonant judgments of the final chord of an eight-chord sequence. The effects of tonal priming emerged in accuracy and reaction time measures for all octaves, except for a ceiling effect on accuracy in the matching (original pitch height) condition. In a second experiment, we increased the shift to two octaves and compressed the chords to eliminate overlap between the target and context chords; again, tonal priming emerged. These findings have implications for the behavioral study of tonal priming and support the assumption of octave equivalence in computational models.

Implicit knowledge and memory for musical stimuli in musicians and non-musicians

The phoneme monitoring task is a musical priming paradigm that demonstrates that both musicians and non-musicians have gained implicit understanding of prevalent harmonic structures. Little research has focused on implicit music learning in musicians and non-musicians. This current study aimed to investigate whether the phoneme monitoring task would identify any implicit memory differences between musicians and non-musicians. It focuses on both implicit knowledge of musical structure and implicit memory for specific musical sequences. Thirty-two musicians and non-musicians (19 female and 13 male) were asked to listen to a seven-chord sequence and decide as quickly as possible whether the final chord ended on the syllable /di/ or /du/. Overall, musicians were faster at the task, though non-musicians made more gains through the blocks of trials. Implicit memory for musical sequence was evident in both musicians and non-musicians. Both groups of participants reacted quicker to sequences that they had heard more than once but showed no explicit knowledge of the familiar sequences.

Creative Chord Sequence Generation for Electronic Dance Music

This paper describes the theory and implementation of a digital audio workstation plug-in for chord sequence generation. The plug-in is intended to encourage and inspire a composer of electronic dance music to explore loops through chord sequence pattern definition, position locking and generation into unlocked positions. A basic cyclic first-order statistical model is extended with latent diatonicity variables which permits sequences to depart from a specified key. Degrees of diatonicity of generated sequences can be explored and parameters for voicing the sequences can be manipulated. Feedback on the concepts, interface, and usability was given by a small focus group of musicians and music producers.