Genre Classification Research Articles

Generative Adversarial Networks Based Framework for Music Genre Classification

Generative Adversarial Networks Based Framework for Music Genre Classification

GenreNet: A Deep Based Approach for Music Genre Classification

GenreNet: A Deep Based Approach for Music Genre Classification

Exploring the Application of Game Engine in Creating 2D Fighting Game

With the burgeoning growth of the digital entertainment industry, 2D side-scrolling fighting games, as a classic genre, are confronted with the dual challenges of innovation and technological renewal. To address these challenges, this study aims to delve into the development techniques and methodologies of 2D side-scrolling fighting games, with a particular focus on leveraging game engines to enhance the overall quality and player experience of the games. Utilizing a combination of literature review, case study, and empirical research, this study conducts a thorough assessment of current mainstream fighting game engines. By analyzing successful cases of 2D side-scrolling fighting games both domestically and internationally, this research endeavors to distill an effective development process and key technical points to guide game developers in making more informed decisions during the design and implementation phases. The findings of this study not only contribute to improving the playability and market competitiveness of games but also offer new perspectives and strategies for the sustainable development of the gaming industry.

Analysis of the Arab singer Shadia’s lyrics

AbstractIn this work, we analyze the lyrics of one of the most famous and influential Arab artists in the twentieth century, namely "Image missing" (Shadia). Lyrics analysis provides a deep insight into the artist’s career evolution and her interactions with the surrounding environment including the social, political, and economic conditions. In order to perform such analysis, we had to collect and compile the lyrics of Shadia accompanied with the necessary meta-data into an organized and structured form. The data are preprocessed by removing stop words and doing some normalization operations over the songs prose. We did not perform any lemmatization or stemming as the original form of the tokens conveys much more information than the source words. We performed a lexical analysis in order to study both the lexical diversity and density over the course of Shadia’s career life. We have as well studied the most significant words, idioms, and terms played in the songs using tools such as word clouds and more quantitative measures such as term frequency–inverse document frequency. We have divided the career life of Shadia into sub-decades of length 5 years, and all analyses are done both in a yearly fashion and more coarsely over such sub-decades. Our quantitative analyses show strong correlations between the artistic lyrical work of Shadia and the state of affairs in Egypt and the Arab World during her time. In particular, Shadia’s lyrics reflect the radical changes in all aspects of the social, political, and economic conditions. This is especially relevant knowing that Shadia is very much truly considered the daughter of the generation of the 1952 revolution in Egypt. The significance of Shadia and her lyrics stem essentially from being contemporaneous to radical changes in Egypt across all sectors including political (support of liberation movements across the world and the conflict with Israel) and socioeconomic (especially changing the social class structure in Egypt). We also investigated the potential effectiveness of PoS (Part-of-Speech) tagging in genre analysis and classification.

Establish a novel framework for enhancing minority music genre identification

The objective of this study is to develop a new framework based on Waterwheel Plant optimization for improving minority music genre classification using Layer-tuned Long Short-Term Memory (WP-LT-LSTM). Chinese minority music includes various musical styles of different ethnic groups in China. It depends on the specific instrumentalities, the distribution of pitch classes and rhythms, and the culture. Specifically, the proposed framework will enhance the ability to efficiently detect under represented music genres, which could have applicability for cultural sustainability and more personalized music recommendation services. For this, we collected a dataset that includes a wide range of different minority music samples in audio format. These include genre labels, artist information and audio features necessary for the training of our suggested model. Using K-fold cross validation to enhances the accuracy. Min-max Normalization is used on the obtained data to perform pre-processing. To extract the important features from the processed data, we used Mel-frequency cepstral coefficients (MFCCs). In our proposed model, the WP algorithm dynamically adjusts LT-LSTM’s internal parameters, enhancing model adaptability. LT-LSTM processes sequential audio data, capturing temporal dependencies crucial for genre classification in minority music genres. The implemented model is executed in Python software. It evaluates the model’s performance across a range of parameters throughout the result analysis phase. We also performed comparison studies using standard methods. The results collected indicate the excellence and effectiveness of the proposed framework for music genre identification.

Harmonizing Heritage: A Review of Advances in Indian Music Genre Classification

Harmonizing Heritage: A Review of Advances in Indian Music Genre Classification

Efficient Music Genre Recognition Using ECAS-CNN: A Novel Channel-Aware Neural Network Architecture.

In the era of digital music proliferation, music genre classification has become a crucial task in music information retrieval. This paper proposes a novel channel-aware convolutional neural network (ECAS-CNN) designed to enhance the efficiency and accuracy of music genre recognition. By integrating an adaptive channel attention mechanism (ECA module) within the convolutional layers, the network significantly improves the extraction of key musical features. Extensive experiments were conducted on the GTZAN dataset, comparing the proposed ECAS-CNN with traditional convolutional neural networks. The results demonstrate that ECAS-CNN outperforms conventional methods across various performance metrics, including accuracy, precision, recall, and F1-score, particularly in handling complex musical features. This study validates the potential of ECAS-CNN in the domain of music genre classification and offers new insights for future research and applications.

Research on music genre recognition method based on deep learning

In this paper, we explore music genre recognition using deep learning methods, examining the application of feature extraction, model construction, and performance evaluation for different music genres. During the data preparation and preprocessing stages, data augmentation and normalization techniques were employed to enhance the model’s generalization capabilities. By constructing multilayer convolutional neural networks (CNNs) and recurrent neural networks (RNNs), we achieved automatic recognition of music genres. In the experimental results analysis, we compared the accuracy and training time of different models, validating the effectiveness of deep learning in the field of music genre recognition. The limitations of deep learning methods and future research directions are also discussed, providing a reference for further studies in music information processing. This study delves into the issue of music genre recognition and proposes a deep learning-based approach. This method leverages neural networks to extract features and learn from audio data, enabling accurate classification of different music genres. Extensive experiments have demonstrated that our method achieves highly satisfactory results in music genre recognition tasks. Furthermore, we optimized the deep learning models, improving their generalization capabilities and accuracy. Our research offers the music industry an efficient and accurate method for music genre recognition, providing new perspectives and technical support for research and applications in the music field.

Audio feature enhancement based on quaternion filtering and deep hashing

This paper aims to solve the problems of difficult convergence of audio model training, large data demand, and large dimensionality of storage space for audio-generated feature vectors. To this end, this paper proposes the use of quaternion Gabor filtering to suppress the background information of the spectrogram and reduce the interference of the data for the case of insufficient data alignment between audio data and image data after shifting the domain. In addition, different scales of window lengths and frame shifts are used to capture the connections between different vocal objects. To address the problem that the generated feature vectors are large dimensional, we use a deep hash module to map high-dimensional features to low-dimensional features and use a probability function to make the learned samples more consistent with the overall distribution. In the experimental evaluation, the proposed method was evaluated on the environmental sound classification dataset and the music genre classification dataset. The proposed method uses only a common backbone network and improves the accuracy of audio recognition.

A Deep Learning Approach for Automatic Music Genre Classification

A Deep Learning Approach for Automatic Music Genre Classification

Natur – Geschichte – Schreibung - Die Grenzsituation der <i>Naturalis Historia</i> von Plinius dem Älteren

According to the preface, Pliny’s Natural History belongs to the genre of historia, of which subject is the nature. At the same time, the preface offers other genre classifications as well: encyclios paideia, thaesaurus. Pliny himself points out the novelty of his work: Libros naturalis historiae […] novicium opus (praef. 1.). Regarding Pliny’s peculiar concept of nature, in terms of the genre and literary history, Natural History can be interpreted as a borderline case.

Media promotion of scientific knowledge among a mass audience

INTRODUCTION. Popularization of science plays a significant role in modern society, contributing to the development of domestic science and technology, the formation of an educated and critically thinking society. The purpose of the study is to consider materials on popular science topics as agents of popularization of scientific knowledge for a wide audience.MATERIALS AND METHODS. The following media were analyzed: “Izvestiya Mordovii”, “Stolitsa S”, “Zdunov zdes’”, “Igor’ Gubaidulin i GR”, “Minpromnauki Mordovii”, “MGU im. N.P. Ogareva”, “Startapstudiya “Ogarev”, “Glushko”. In total, more than 1000 media texts were analyzed; the sample for qualitative analysis consisted of 200 publications for the period from January 1, 2022 to May 31, 2024.RESULTS AND DISCUSSION. The process of promoting scientific knowledge in the media space of the Republic of Mordovia is revealed, the subject matter, genre and functional classification of popular science materials, and the university’s cooperation with the media in the process of popularizing science are considered.CONCLUSION. The classification of popular science materials in the media of the Republic of Mordovia was identified (by territorial affiliation of the study, by genre specificity, by volume of information, by visualization methods), the primary source of scientific information was identified – university media platforms and its dissemination through other communication channels in the time period. The process of formation of the term “Mordovian scientists” in media materials was traced, recommendations for covering science, both for regional and federal media, were compiled.

Movie trailer genre classification using multimodal pretrained features

We introduce a novel method for movie genre classification, capitalizing on a diverse set of readily accessible pretrained models. These models extract high-level features related to visual scenery, objects, characters, text, speech, music, and audio effects. To intelligently fuse these pretrained features, we train small classifier models with low time and memory requirements. Employing the transformer model, our approach utilizes all video and audio frames of movie trailers without performing any temporal pooling, efficiently exploiting the correspondence between all elements, as opposed to the fixed and low number of frames typically used by traditional methods. Our approach fuses features originating from different tasks and modalities, with different dimensionalities, different temporal lengths, and complex dependencies as opposed to current approaches. Our method outperforms state-of-the-art movie genre classification models in terms of precision, recall, and mean average precision (mAP). To foster future research, we make the pretrained features for the entire MovieNet dataset, along with our genre classification code and the trained models, publicly available.

A Hybrid Parallel Computing Architecture Based on CNN and Transformer for Music Genre Classification

Music genre classification (MGC) is the basis for the efficient organization, retrieval, and recommendation of music resources, so it has important research value. Convolutional neural networks (CNNs) have been widely used in MGC and achieved excellent results. However, CNNs cannot model global features well due to the influence of the local receptive field; these global features are crucial for classifying music signals with temporal properties. Transformers can capture long-range dependencies within an image thanks to adopting the self-attention mechanism. Nevertheless, there are still performance and computational cost gaps between Transformers and existing CNNs. In this paper, we propose a hybrid architecture (CNN-TE) based on CNN and Transformer encoder for MGC. Specifically, we convert the audio signals into mel spectrograms and feed them into a hybrid model for training. Our model employs a CNN to initially capture low-level and localized features from the spectrogram. Subsequently, these features are processed by a Transformer encoder, which models them globally to extract high-level and abstract semantic information. This refined information is then classified using a multi-layer perceptron. Our experiments demonstrate that this approach surpasses many existing CNN architectures when tested on the GTZAN and FMA datasets. Notably, it achieves these results with fewer parameters and a faster inference speed.

Automatic movie genre classification & emotion recognition via a BiProjection Multimodal Transformer

Analyzing, manipulating, and comprehending data from multiple sources (e.g., websites, software applications, files, or databases) and of diverse modalities (e.g., video, images, audio and text) has become increasingly important in many domains. Despite recent advances in multimodal classification (MC), there are still several challenges to be addressed, such as: the combination of modalities of very diverse nature, the optimal feature engineering for each modality, as well as the semantic alignment between text and images. Accordingly, the main motivation of our research relies in devising a neural architecture that effectively processes and combines text, image, video and audio modalities, so it can offer a noteworthy performance in different MC tasks. In this regard, the Multimodal Transformer (MulT) model is a cutting-edge approach often employed in multimodal supervised tasks, which, although effective, has the problem of having a fixed architecture that limits its performance in specific tasks as well as its contextual understanding, meaning it may struggle to capture fine-grained temporal patterns in audio or effectively model spatial relationships in images. To address these issues, our research modifies and extends the MulT model in several aspects. Firstly, we focus on leveraging the Gated Multimodal Unit (GMU) module within the architecture to efficiently and dynamically weigh modalities at the instance level and to visualize the use of modalities. Secondly, to overcome the problem of vanishing and exploding gradients we focus on strategically placing residual connections in the architecture. The proposed architecture is evaluated in two different and complex classification tasks, on the one hand, the movie genre categorization (MGC) and, on the other hand, the multimodal emotion recognition (MER). The results obtained are encouraging as they indicate that the proposed architecture is competitive against state-of-the-art (SOTA) models in MGC, outperforming them by up to 2% on the Moviescope dataset, and by 1% on the MM-IMDB datasets. Furthermore, in the MER task the unaligned version of the datasets was employed, which is considerably more difficult; we improve accuracy SOTA results by up to 1% on the IEMOCAP dataset, and attained a competitive outcome on the CMU-MOSEI11Dai et al., (2021) collection, outperforming SOTA results in several emotions.

Writing the mire – ‘for we are loom’

ABSTRACT In this essay, I am in-conversation with Proust was a Neuroscientist, by Jonah Lehrer [2008, Proust was a Neuroscientist. New York: Houghton Mifflin Company]. I engage with Lehrer’s chapters focusing Marcel Proust, Virginia Woolf and Paul Cézanne. This essay is a contribution to an ongoing conversation with Professors Kate Coles and Jen Webb regarding the distinctions, or lack thereof, between narrative and the lyric, within the context of broader discussions about genre classifications (Great Writing 2023, 2024). In this essay, I respond to Coles and Webb’s provocative question: What is it you mean, they ask, when you use the term realism? I consider this question from a practice-led perspective, as a writer who loves to read, and a writer-researcher who is drawn to neuro-psychoanalytic approaches to writing and creativity. I’m drawn to the quagmire of memory, as a primary source of stimulus for creative practice. My understanding of what I have come to call narrative lyricism is that it is a form of writing in which narrative may exist in ghost. Its incompleteness (if evaluated within traditional expectations of complication and dénouement) reflects the complicated (which is to say entangled) nature of the operations of memory.

Music genre classification: Machine Learning on GTZAN

Music genre classification: Machine Learning on GTZAN

Enhancing text-audio generation by music classification and Retrieval-Augmented Generation

Recent advancements in deep learning have propelled the development of AI systems capable of generating music that resonates with human emotions and preferences. However, current music generation models still struggle to align generated music with detailed textual descriptions and maintain consistency, especially for longer compositions. This paper presents an innovative approach to address these challenges by integrating genre classification and retrieval-augmented generation (RAG) into the music generation pipeline. We train advanced CNN architectures, including ResNet-50, GoogleNet, and VGG16, for accurate genre classification. The classifier is then incorporated into a RAG framework, where the most relevant pre-classified music piece is retrieved based on the input text query. The retrieved audio and the text description are then fed into the MUSICGEN model to generate a new music piece that inherits attributes from both inputs. We evaluate our system through a double-blind human study, comparing the outputs of the original MUSICGEN model with our RAG-enhanced model. The results demonstrate a significant improvement in the ability of the RAG-enhanced model to generate music embodying specific stylistic elements, as evidenced by higher average confidence scores from participants. Our work represents a significant step towards more personalized and context-aware AI-generated musical experiences, laying the foundation for future advancements in this exciting field.

An improved random forest model for music genre classification algorithm based on sparrow search algorithm

In this study, a random forest model optimised based on the sparrow search algorithm is explored for the music genre classification problem. By introducing the sparrow search algorithm, the model is able to search the feature space more comprehensively during the training process, which improves the learning ability of complex data relationships. After 15 iterations of optimisation, the fitness value of the model is improved from 0.2002 to 0.197, showing better convergence. The performance on the training set shows that the model predicts 2,543 music genres with an accuracy of 99.59% and only 10 incorrect predictions, which verifies its excellent performance on the training data. While on the test set, the model's prediction accuracy for 623 music genres is 79.78%, which is slightly lower than the result of the training set, but still reflects good generalisation ability. The results of this paper imply that the improved random forest model based on the sparrow search algorithm has potential application prospects in the music genre classification task. By optimising the parameter settings and feature selection, we not only improve the prediction accuracy and generalisation ability of the model, but also provide new ideas for solving other complex data classification problems. In the future, we can further expand the sample size, try different feature combinations, and conduct in-depth research by combining more domain knowledge in order to further improve the model performance and promote the development of related fields.

Film Genre Classification Based on Poster Using Convolutional Neural Network

Film Genre Classification Based on Poster Using Convolutional Neural Network