Music Deep Learning: Deep Learning Methods for Music Signal Processing—A Review of the State-of-the-Art

IEEE Access, Год журнала: 2023, Номер 11, С. 17031 - 17052

Опубликована: Янв. 1, 2023

The discipline of Deep Learning has been recognized for its strong computational tools, which have extensively used in data and signal processing, with innumerable promising results. Among the many commercial applications Learning, Music Signal Processing received an increasing amount attention over last decade. This work reviews most recent developments processing. Two main that are discussed Information Retrieval, spans a plethora applications, Generation, can fit range musical styles. After review both topics, several emerging directions identified future research.

Язык: Английский

---

Optimizing the configuration of deep learning models for music genre classification

Heliyon, Год журнала: 2024, Номер 10(2), С. e24892 - e24892

Опубликована: Янв. 1, 2024

Music genre categorization is a fundamental use of sound processing methods in the realm music retrieval. Typically, people are responsible for categorizing genres. Machine learning approaches can automate this procedure. Therefore, recent years, several have been suggested to achieve objective. Nevertheless, given findings indicate that there still discrepancy between observed results and an optimal method. Hence, paper introduces novel approach accurately forecasting genres by using deep methodologies. The proposed involves preprocessing input signals then representing characteristics each signal combination Mel Frequency Cepstral Coefficients (MFCC) Short-Time Fourier Transform (STFT) features. Subsequently, convolutional neural network (CNN) applied process group these characteristics. technique utilizes two CNN models analyze MFCC STFT data. Although structure identical, hyper-parameters model individually adjusted black hole optimization (BHO) algorithm. Here, method fine-tunes hyperparameters minimize their training error. Ultimately, Convolutional Neural Network combined determine classifier based on SoftMax. efficacy methodology has assessed GTZAN Extended-Ballroom datasets. experimental demonstrated achieved classification accuracies 95.2 % 95.7 datasets, respectively, indicating its superiority over earlier efforts.

Язык: Английский

---

Enhanced capsule neural network with advanced triangulation topology aggregation optimizer for music genre classification

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Янв. 2, 2025

Язык: Английский

---

Analysis of the Style Characteristics of Regional Folk Songs and Music Classification Algorithms

Journal of Advanced Computational Intelligence and Intelligent Informatics, Год журнала: 2025, Номер 29(1), С. 33 - 40

Опубликована: Янв. 19, 2025

Regional folk songs have a rich history and are filled with cultural values. In this paper, first, the style characteristics of regional briefly introduced. Using four from northwest, northeast, southwest, Hakka as examples, time domain, frequency mel-frequency cepstral coefficient (MFCC) features were extracted. Finally, bidirectional long short-term memory (BiLSTM)-based music classification algorithm is used to realize different regions. It was found that using time-frequency domain + MFCC produced better results in than only or features. The BiLSTM achieved an accuracy 0.8339 F1 value 0.8201 for 10 s fragment set, both which those K-nearest neighbor, support vector machine, other algorithms. show approach study categorize reliable it can be applied real songs.

Язык: Английский

---

Classification of Music Genres using Multimodal Deep Learning Technique

E3S Web of Conferences, Год журнала: 2025, Номер 616, С. 02012 - 02012

Опубликована: Янв. 1, 2025

The demand for automated music organization and the ever-increasing volume of digital audio recordings has both contributed to a surge in interest deep learning-based genre classification. purpose this research is examine feasibility using CNNs RNNs, two types learning architectures, task track proposed models aim achieve high accuracy robustness classification tasks by leveraging features extracted from raw signals spectrogram representations. A comprehensive dataset comprising diverse genres utilized training evaluation, with performance metrics such as accuracy, precision, recall assessed ensure reliability. results demonstrate that approaches significantly outperform traditional methods, providing insights into underlying characteristics musical styles. Potentially useful areas discovery platforms, playlist creation, recommendation services, study adds body knowledge on systems.

Язык: Английский

---

Deep neural networks and fractional grey lag Goose optimization for music genre identification

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Фев. 25, 2025

Generally, music genres have not new established framework, since they are often determined by the composer's background cultural or historical impact and geographical origin. In this work, a methodology is presented based on deep learning metaheuristic algorithms to enhance performance in style categorization. The model consists of two main parts: pre-trained model, ZFNet, through which high level features extracted from audio signals ResNeXt for classification. A fractional-order-based variant Grey Lag Goose Optimization (FGLGO) algorithm used optimize parameters boost model. dual-path recurrent network employed real-time generation evaluate benchmark datasets, ISMIR2004 extended Ballroom, compared state-of-the-art models included CNN, PRCNN, BiLSTM BiRNN. Experimental results show that with accuracy rates 0.918 Ballroom dataset 0.954 dataset, proposed improves efficiency incrementally over existing models.

Язык: Английский

---

A novel similarity-based taste features-extracted emotions-aware music recommendation algorithm

Information Sciences, Год журнала: 2025, Номер unknown, С. 122001 - 122001

Опубликована: Фев. 1, 2025

Язык: Английский

---

Music genre classification with parallel convolutional neural networks and capuchin search algorithm

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Март 20, 2025

With the primary objective of creating playlists that suggest songs, interest in music genre categorization has grown thanks to high-tech multimedia tools. To develop a strong classifier can quickly classify unlabeled and enhance consumers' experiences with media players files, machine learning deep ideas are required. This study presents unique method blends convolutional neural network (CNN) models as an ensemble system detect musical genres. The makes use discrete wavelet transform (DWT), mel frequency cepstral coefficients (MFCC), short-time fourier (STFT) characteristics provide comprehensive framework for expressing stylistic qualities music. do this, each model's hyperparameters generated using capuchin search algorithm (CapSA). Preprocessing original signals, feature description utilizing DWT, MFCC, STFT signal matrices, CNN model optimization extract features, identification based on combined features make up four main components technique. By integrating many processing techniques models, this advances field classification provides possible insights into blending diverse improved accuracy. GTZAN Extended-Ballroom datasets were two used studies. average accuracy 96.07 96.20 database, respectively, show how well our suggested strategy performs when compared earlier, comparable methods.

Язык: Английский

---

Review on Emotion-Centric Music Recommender Systems

Lecture notes in electrical engineering, Год журнала: 2025, Номер unknown, С. 117 - 128

Опубликована: Янв. 1, 2025

Язык: Английский

---

Instrument sound classification using a music-based feature extraction model inspired by Mozart's Turkish March pattern

Alexandria Engineering Journal, Год журнала: 2025, Номер 118, С. 354 - 370

Опубликована: Янв. 23, 2025

Язык: Английский

---