The Classification of Music and Art Genres under the Visual Threshold of Deep Learning

Abstract

Wireless networks are commonly employed for ambient assisted living applications, and artificial intelligence-enabled event detection and classification processes have become familiar. However, music is a kind of time-series data, and it is challenging to design an effective music genre classification (MGC) system due to a large quantity of music data. Robust MGC techniques necessitate a massive amount of data, which is time-consuming, laborious, and requires expert knowledge. Few studies have focused on the design of music representations extracted directly from input waveforms. In recent times, deep learning (DL) models have been widely used due to their characteristics of automatic extracting advanced features and contextual representation from actual music or processed data. This paper aims to develop a novel deep learning-enabled music genre classification (DLE-MGC) technique. The proposed DLE-MGC technique effectively classifies the music genres into multiple classes by using three subprocesses, namely preprocessing, classification, and hyperparameter optimization. At the initial stage, the Pitch to Vector (Pitch2vec) approach is applied as a preprocessing step where the pitches in the input musical instrument digital interface (MIDI) files are transformed into the vector sequences. Besides, the DLE-MGC technique involves the design of a cat swarm optimization (CSO) with bidirectional long-term memory (BiLSTM) model for the classification process. The DBTMPE technique has gained a moderately increased accuracy of 94.27%, and the DLE-MGC technique has accomplished a better accuracy of 95.87%. The performance validation of the DLE-MGC technique was carried out using the Lakh MIDI music dataset, and the comparative results verified the promising performance of the DLE-MGC technique over current methods.

Developing Smart Archives in Society 5.0: Leveraging Artificial Intelligence for Managing Audiovisual Archives in Africa

“…For instance, videos can be classified by genre, scene type, or content theme, while images can be categorised by subject matter or visual style. This classification aids in organising the archives and facilitating targeted retrieval of relevant assets (Zheng 2022). Computer vision algorithms can enhance the quality of audiovisual content by performing tasks such as image restoration, video stabilisation, noise reduction, and resolution enhancement.…”

“…These tags can include information about objects, scenes, locations, people, emotions, and actions depicted in the media. This automated tagging process speeds up the archival workflow and ensures consistent and accurate metadata generation across a large volume of assets (Zheng 2022).…”

“…By categorising content into predefined classes or tags, users can quickly locate specific assets without having to manually browse through large volumes of material. This improves the overall usability and accessibility of the archive(Zheng 2022). usability and facilitates interoperability with other systems(Jaillant 2022).…”

TruMuzic: A Deep Learning and Data Provenance-Based Approach to Evaluating the Authenticity of Music

“…Schedl [40] reviews the music recommendation systems based on deep learning. Zheng et al [41] present a deep learning-enabled music genre classification method, and Majidi et al [42] propose a deep learning-based method for automatic music generation. Yang et al [43] present a deep learning-based method for music content recognition and recommendation system, Lee et al [44], propose a deep metric learning-based music similarity evaluation system, Elbir et al [45], introduce MusicRecNet, a CNN-based model which is trained for music similarity analysis, Yesiler et al [46] and Du et al [47] present deep learning based methods for identifying cover songs, Thome et al [48] presented a CNN-based music similarity-based search engine, to help find similar songs for video production and Dhand et al [49] proposed a system that detects the mood of the user and is further trained with a logistic regression-based model to recommend music based on the user's facial expressions.…”

Applications of Deep Learning for Drug Discovery Systems with BigData

“…As methods for learning, multilayer neural networks, such as deep learning, which are currently widely used, are attracting attention due to their amazing prediction performances [32][33][34][35]. Deep learning is an AI technology that automatically extracts and learns features based on large amounts of data [36,37]. It essentially consists of a multilayer neural network and an algorithm that mimics human neurons, and it automatically processes and learns input data and passes them to the next layer, which consists of three or more layers; in these layers, it is possible to deepen the characteristics of the data to be learned using multiple layers of this neural network, which result in deep-learning models with extremely high accuracy, sometimes surpassing human recognition accuracy [38][39][40][41][42][43].…”