Modeling musical style using grammatical inference techniques: a tool for classifying and generating melodies

Cruz-Alcázar, Pedro P.; Vidal-Ruiz, E.

doi:10.1109/wdm.2003.1233878

Cited by 8 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The harmony dimension consists of a sequence of chords, represented by symbols from a finite dictionary. The modeling of chord sequences is useful for many tasks, such as polyphonic symbolic music retrieval [1,2], composer characterization [3], chord transcription from audio [4] and computer-assisted composition or harmonization [5].…”

Section: Introductionmentioning

confidence: 99%

“…In this article, we investigate the modeling of chord sequences via probabilistic N-gram models with N ≥ 2. Such models have been used for other types of data, such as melody [5] and spoken language [6]. The first attempts to model chord sequences via this approach [2,3,7] achieved limited success, due to fixed model inputs and parameters and to overfitting issues.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robust modeling of musical chord sequences using probabilistic N-grams

Scholz

Vincent

Bimbot

2009

2009 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

The modeling of music as a language is a core issue for a wide range of applications such as polyphonic music retrieval, automatic style identification, audio to symbolic music transcription and computer-assisted composition. In this paper, we focus on the modeling of chord sequences by probabilistic N-grams. Previous studies using these models have achieved limited success, due to overfitting and to the use of a single chord labeling scheme. We investigate these issues using model smoothing and selection techniques initially designed for spoken language modeling. This approach is evaluated over a set of songs by The Beatles, considering several chord labeling schemes. Initial results show that the accuracy of N-grams is increased but that additional improvements may still be achieved in the future using more advanced, possibly music-specific, smoothing techniques.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Robust modeling of musical chord sequences using probabilistic N-grams

Scholz

Vincent

Bimbot

2009

2009 IEEE International Conference on Acoustics, Speech and Signal Processing

View full text Add to dashboard Cite

show abstract

“…Cruz-Alcázar et al [23] developed a grammatical inference system for modeling a musical style which was then used in generating automatic compositions. They expanded on their work in [24] adding more comparisons between different inference techniques and music coding schemes (absolute pitch, relative pitch, melody contour, and relative to tonal center).…”

Section: Generative Grammar In Algorithmic Compositionmentioning

confidence: 99%

Top 10 Artificial Intelligence Algorithms in Computer Music Composition

Siphocly¹,

El-Horbaty²,

Salem³

2021

IJCDS

View full text Add to dashboard Cite

Music composition is now appealing to both musicians and non-musicians equally. It branches into various musical tasks such as the generation of melody, accompaniment, or rhythm. This paper discusses the top ten artificial intelligence algorithms with applications in computer music composition from 2010 to 2020. We give an analysis of each algorithm and highlight its recent applications in music composition tasks, shedding the light on its strengths and weaknesses. Our study gives an insight on the most suitable algorithm for each musical task, such as rule-based systems for music theory representation, case-based reasoning for capturing previous musical experiences, Markov chains for melody generation, generative grammars for fast composition of musical pieces that comply to music rules, and linear programming for timbre synthesis. Additionally, there are biologically inspired algorithms such as: genetic algorithms, and algorithms used by artificial immune systems and artificial neural networks, including shallow neural networks, deep neural networks, and generative adversarial networks. These relatively new algorithms are currently heavily used in performing numerous music composition tasks.

show abstract

“…This algorithm infers probabilistic grammar from positive examples using state-merging technique on probabilistic criteria. This grammar inference algorithm has been successfully applied in music genre recognition [7], normal or abnormal chromosome recognition [8], digit and shape recognition [9], and text and speech recognition [10,11].…”

Section: IImentioning

confidence: 99%

Stochastic regular grammar-based learning for basic dance motion recognition

Heryadi

Fanany

Arymurthy

2013

2013 International Conference on Advanced Computer Science and Information Systems (ICACSIS)

View full text Add to dashboard Cite

this paper presents a simple and computationally efficient framework for 3D dance basic motion recognition based on syntactic pattern recognition. In this research, a class of basic dance motions is modeled by a stochastic regular grammar (SRG), inferred from training dataset, in which key body poses that are learned from training dataset are selected as gesture primitives. To represent a dance motion, body pose of a dancer is represented by angular coordinate of 15 skeleton joints. This feature is later compacted into one-dimensional string of labels for grammar inference which makes the recognition process is considerably fast compared to statistical pattern classifier such as k-nearest neighbor (kNN). A single test using the learned grammar in average takes only about 5 ms compared to around 20s using kNN whilst the overhead time to build all grammars takes only about 3.4s. This compacting process, however, leads to information loss which is observed in slightly degraded recognition performance for low articulated motions but quite large degradation for high articulated dance motions. To overcome this, we investigate several reliable feature selection methods such as Sequential Feature Selection (SFS), Principal Component Analysis (PCA), and Heuristic Sequential Feature Selection (HSFS) compared to the use of whole features. Based on our experiment, the HSFS is the most suitable feature selection to overcome this problem.

show abstract

Modeling musical style using grammatical inference techniques: a tool for classifying and generating melodies

Cited by 8 publications

References 10 publications

Robust modeling of musical chord sequences using probabilistic N-grams

Robust modeling of musical chord sequences using probabilistic N-grams

Top 10 Artificial Intelligence Algorithms in Computer Music Composition

Stochastic regular grammar-based learning for basic dance motion recognition

Contact Info

Product

Resources

About