An Enhanced Musical Instrument Classification using Deep Convolutional Neural Network

Prabavathy*, S.; Rathikarani, V.; Dhanalakshmi, P.

doi:10.35940/ijrte.d9271.118419

Cited by 6 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The strong spread of digitalization in recent decades has not only revolutionized the areas of music composition, distribution, sales, storage, education, and music scores but also defined different musical styles. There is also an increasing trend of applying artificial intelligence or recognition algorithms such as the k-nearest neighbor (k-NN) or support vector machines (SVMs), which has been scrutinized by several scientific studies [28][29][30]. Tzanetakis and Cook's [31] work is considered to be the foundation of automatic music genre classification systems.…”

Section: Dilemmas Of Musical Genres and Their Categorizationmentioning

confidence: 99%

Musical Preferences among Students Aged 9–19: A Study on Musical Genres and Styles

Szabó,

Földi,

et al. 2024

Education Sciences

View full text Add to dashboard Cite

This study aimed to explore students’ musical genre preferences, exploring variations across gender and age groups in Hungary. Additionally, we investigated the relationships among the popularity of musical genres and connections between musical programs and related activities. With the help of stratified sampling, we examined the opinions of students aged 9–19 about each genre (N = 1159) using specific musical examples. In this study, musical genres were classified into four main types based on related music videos, including classical popular music (CPM), rock music (RM), classical art music (CAM), and folk music (FM). Different types of analyses, such as t-tests, one-way and two-way ANOVAs, and correlational analyses such as correlation coefficients (r), chi-square tests, and eta squares, were employed in this study. The results showed that the popularity of the four pieces of music classified as CPM, RM, CAM, and FM had a moderately strong correlation with each other. The correlations between FM, CPM, and RM did not differ from each other, but they showed significantly weaker correlation values than the correlation between FM and CAM. Moreover, significant differences were found in the students’ perceptions of the genres based on their gender and age groups. Among the four performances, the girls had a greater preference compared to the boys for each one, except for the folk music piece. The youngest age group (9–12) showed the highest preference for the CPM, although the difference compared to the oldest age group (17–19) was not statistically significant. Therefore, this study is beneficial for music education, focusing on students’ genre preferences, including CPM, RM, CAM, and FM.

show abstract

Section: Dilemmas Of Musical Genres and Their Categorizationmentioning

confidence: 99%

Musical Preferences among Students Aged 9–19: A Study on Musical Genres and Styles

Szabó,

Földi,

et al. 2024

Education Sciences

View full text Add to dashboard Cite

show abstract

Indian classical musical instrument classification using Timbral features

Gulhane

Shirbahadurkar

Badhe

2021

Concurrency and Computation

View full text Add to dashboard Cite

Summary Musical instrument classification becomes effective when the music signal arrives with profound characteristics. This urged the researchers to develop an automatic system of recognizing the music signals and classify the instruments interplayed through the music. Thus, this paper proposes a model for the Indian music classification system using the optimization‐based stacked autoencoder. The significance of this research is based on the proposed Cuckoo‐dragonfly optimization (CuDro)‐based stacked autoencoder, where the proposed CuDro optimization trains the stacked autoencoder for acquiring accurate classification results. The proposed CuDro technique is the combination of the standard Cuckoo search (CS) and the Dragonfly algorithm (DA) that renders optimal weights for training the stacked autoencoder (SAE). Moreover, the musical instrument classification using the proposed CuDro‐based stack autoencoder is based on the compact features, such as Timbral features and proposed FrMkMFCC features, which further add value to this research. The Timbral features like Spectral flux, spectral kurtosis (SK), Spectral skewness, Spectral pitch similarity, Roughness, In harmonicity are added in the research for efficient musical instrument classification. The proposed FrMkMFCC feature is the integration of the Fractional Fourier transforms and Multi kernel method, and Mel Frequency Cepstral Coefficient (MFCC) features. The analysis using the developed classification methodology confirms that the proposed method acquired the maximum accuracy of 96.16%, the sensitivity of 86.86%, and specificity of 92.85%, respectively.

show abstract