• Corpus ID: 46172545

DeepGTTM-II : Automatic Generation of Metrical Structure based on Deep Learning Technique

@inproceedings{Hamanaka2016DeepGTTMIIA,
  title={DeepGTTM-II : Automatic Generation of Metrical Structure based on Deep Learning Technique},
  author={Masatoshi Hamanaka},
  year={2016}
}
This paper describes an analyzer that automatically generates the metrical structure of a generative theory of tonal music (GTTM). Although a fully automatic time-span tree analyzer has been developed, musicologists have to correct the errors in the metrical structure. In light of this, we use a deep learning technique for generating the metrical structure of a GTTM. Because we only have 300 pieces of music with the metrical structure analyzed by musicologist, directly learning the relationship… 

Figures and Tables from this paper

deepGTTM-III: Multi-task Learning with Grouping and Metrical Structures
TLDR
An analyzer that simultaneously learns grouping and metrical structures on the basis of the generative theory of tonal music (GTTM) by using a deep learning technique and is presented, which is a new analyzezer that includes the concept of feedback that enables simultaneous learning of grouping and meetingrical structures by integrating both deepG TTM-I and deepGttM-II networks.
deepGTTM-III : Automatic Acquisition of Grouping and Metrical Structures
TLDR
An analyzer that simultaneously learns the grouping and metrical structures on the basis of the generative theory of tonal music (GTTM) by using a deep learning technique and is presented, which includes the concept of feedback.
deepGTTM-III: Simultaneous Learning of Grouping and Metrical Structures
TLDR
An analyzer that simultaneously learns the grouping and metrical structures on the basis of the generative theory of tonal music (GTTM) by using a deep learning technique and is presented, which includes the concept of feedback.
Polyphonic Music Analysis Database Based on GTTM
This paper presents a method for manually analyzing polyphonic music on the basis of the generative theory of tonal music and the analysis database obtained with the tool. A time-span tree of the
Time-span Tree Leveled by Duration of Time-span
TLDR
It is confirmed that melodic morphing and deep learning of timespan tree analysis can be carried out automatically using the proposed method for defining the priority order in total order in accordance with the length of the time span of each branch in a time-span tree.
Applying Melody-Morphing Method to Composition
TLDR
An experiment with a musicologist who understood the melody morphing method and attempted to use it for composition showed that 78.5% of the notes in the composed pieces were generated with the melody morph method, while the remaining 21.

References

SHOWING 1-10 OF 31 REFERENCES
deepGTTM-I&II: Local Boundary and Metrical Structure Analyzer Based on Deep Learning Technique
TLDR
A multi-task learning analyzer called deepGTTM-I&II, which outperformed previous analyzers for a GTTM in terms of the F-measure for generating metrical structures and involves supervised fine-tuning using a labeled dataset.
\sigma GTTM III: Learning-Based Time-Span Tree Generator Based on PCFG
TLDR
An automatic analyzer based on the generative theory of tonal music (GTTM) for acquiring a time-span tree is described and it is revealed that the new analyzer outperformed the authors' previously developed GTTM analyzer.
Implementing “A Generative Theory of Tonal Music”
TLDR
A novel computational model of GTTM that re-formalizes the rules through a computer implementation is proposed that can introduce adjustable parameters, which enables the analyser to assign priorities to the rules.
Tree-structured probabilistic model of monophonic written music based on the generative theory of tonal music
TLDR
Despite the conceptual simplicity of the model, it is found that the model automatically acquires music grammar from data and reproduces time-span trees of written music as accurately as an analyser that required elaborate manual parameter tuning.
Fatta: Full Automatic Time-Span Tree Analyzer
TLDR
A music analysis system called a full automatic time-span tree analyzer (FATTA), which analyzes a piece of music based on the generative theory of tonal music (GTTM), and experimental results showed that the performance of FATTA outperformed a baseline performance of the ATTA.
Melody Expectation Method Based on GTTM and TPS
TLDR
A method that predicts the next notes is described for assisting musical novices to play improvisations and uses the concept of melody stability based on the generative theory of tonal music and the tonal pitch space to evaluate the appropriateness of the melody.
Interactive Music Summarization Based on Generative Theory of Tonal Music
TLDR
An algorithm that checks for melodic similarity and a music summarization system called Papipuun, which can produce a music summary of good quality with a symbolic approach, reflecting the atmosphere of an entire piece through interaction with the user.
Musical Structural Analysis Database Based on GTTM
TLDR
Experiments showed that for 267 of 300 pieces the analysis results obtained by a new musicologist were almost the same as the original results in the GTTM database and that the other 33 pieces had different interpretations.
A Fast Learning Algorithm for Deep Belief Nets
TLDR
A fast, greedy algorithm is derived that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory.
Method to Detect GTTM Local Grouping Boundaries Based on Clustering and Statistical Learning
TLDR
A method that detects local grouping boundaries of the generative theory of tonal music (GTTM) based on clustering and statistical learning and hypothesized that there is some tendency of rules which have more strong influence than other rules by the case of music.
...
1
2
3
4
...