Music Genre Classification Research Articles

English

English

Texture selection for automatic music genre classification

Music Genre Classification is the problem of associating genre-related labels to digitised music tracks. It has applications in the organisation of commercial and personal music collections. Often, music tracks are described as a set of timbre-inspired sound textures. A subset of the sound textures is often selected to represent the entire track. In this paper, we evaluate the impact of texture selection on automatic music genre classification. Although previous work has selected textures by linear downsampling, no extensive work has been done to evaluate how texture selection benefits music genre classification. We also present a novel texture selector based on K-Means aimed to identify diverse sound textures within each track. Our results show that capturing texture diversity within tracks is important towards improving classification performance. Our results also indicate that our K-Means based texture selector is able to achieve significant improvements over the baseline with fewer textures per track than the other texture selectors evaluated. We also show that using multiple texture representations allows further opportunities for feature selection to improve classification performance.

Music Genre Classification using Lyric Mining Based ontf-Idf

With the advancement in the internet technologies, music domain has flourished with better access to various music libraries. In the present times, we are able to access music files over the internet with ease. Nowadays, the lyrics sets are categorised into different genres which cater to various listener moods. Users prefer to listen to music that best suits their mood. Thus considering the need for such classification, research works are being carried out to develop methodologies that can distinguish the music based on individual mood. In this research, instead of using the traditional method of audio feature analysis, we propose to develop a system which analyses the lyrics dataset of the songs based on the features extracted from the training phase and we can predict the mood of the song that is presented to the system at the validation stage. The proposed system is considering five moods containing one hundred songs each, for the validation purpose. The system is capable of predicting the mood of the song based on the analysis of the lyric text.

Where’d You Get that Idea? Determinants of Creativity and Impact in Popular Music

What are the determinants of creativity, innovation and impact? In this paper I explore this question through an analysis of data from the Song Explorer podcast, where composers describe how they created a specific song. I mine their accounts to classify their processes into seven different, but not mutually exclusive, theories of the creative process. The result of this exercise suggests that the recombination of existing songs is a major process for the creation of new successful songs. The second step considers what kind of recombinations are associated with high impact. For each song in the sample I have one or more other songs which were explicitly indicated as an influence or inspiration. I use the music genre classification system Every Noise at Once, that provides a map of over 1,800 genres and millions of songs to create a set of descriptive statistics of the similarity of each song to their inspiration-songs. These statistics are then used as explanatory variables in a regression that seeks to explain impact (YouTube views per day since the songs' video release), while controlling for other determinants of song impact, such as the artists’ established level of popularity. The results confirm the optimal differentiation hypothesis that the simultaneous presence of conventionality together with novelty, and not just one or the other, is a major determinant of creativity and impact.

Masked Conditional Neural Networks for sound classification

The remarkable success of deep convolutional neural networks in image-related applications has led to their adoption also for sound processing. Typically the input is a time–frequency representation such as a spectrogram, and in some cases this is treated as a two-dimensional image. However, spectrogram properties are very different to those of natural images. Instead of an object occupying a contiguous region in a natural image, frequencies of a sound are scattered about the frequency axis of a spectrogram in a pattern unique to that particular sound. Applying conventional convolution neural networks has therefore required extensive hand-tuning, and presented the need to find an architecture better suited to the time–frequency properties of audio. We introduce the ConditionaL Neural Network (CLNN)11Code: https://github.com/fadymedhat/MCLNN. and its extension, the Masked ConditionaL Neural Network (MCLNN) designed to exploit the nature of sound in a time–frequency representation. The CLNN is, broadly speaking, linear across frequencies but non-linear across time: it conditions its inference at a particular time based on preceding and succeeding time slices, and the MCLNN use a controlled systematic sparseness that embeds a filterbank-like behavior within the network. Additionally, the MCLNN automates the concurrent exploration of several feature combinations analogous to hand-crafting the optimum combination of features for a recognition task. We have applied the MCLNN to the problem of music genre classification, and environmental sound recognition on several music (Ballroom, GTZAN, ISMIR2004, and Homburg), and environmental sound (Urbansound8K, ESC-10, and ESC-50) datasets. The classification accuracy of the MCLNN surpasses neural networks based architectures including state-of-the-art Convolutional Neural Networks and several hand-crafted attempts.

Comparison of Use of Music Content (Tempo) and User Context (Mood) Features On Classification of Music Genre

The development of technology in the current era in the field of multimedia, music is not just entertainment or pleasure. Nowadays, online music growth is greatly increasing, namely, music can be classified by genre. The music genre is the grouping of music according to their resemblance to each other. In previous studies, the system was built with Naive Bayes Classifier which is useful for predicting songs based on the lyrics of the song. In our study, we used a dataset that was divided into several genera, namely Blues, Electronic, R & B, Christian, Hip Hop / Rap, Rock, Country, Jazz, Ska, Dance, Pop, and Soul which obtained the accuracy of Music Content of 45 % while for Context Users get an accuracy of 60%.
 Keywords : Genre, Naive Bayes, Music Content, User Context

Neural Network Music Genre Classification

Music genre classification utilizing neural networks (NNs) has achieved some limited success in recent years. Differences in song libraries, machine learning techniques, input formats, and types of NNs implemented have all had varying levels of success. This article reviews some of the machine learning techniques utilized in this area. It also presents research work on music genre classification. The research uses images of spectrograms generated from timeslices of songs as the input into an NN to classify the songs into their respective musical genres.

Parallel Recurrent Convolutional Neural Networks-Based Music Genre Classification Method for Mobile Devices

With the rapid development of the mobile internet of things (IoTs) and mobile sensing devices, a large amount of mobile computing-oriented applications have attracted attention both from industry and academia. Deep learning based methods have achieved great success in artificial intelligence (AI) oriented applications. To advance the development of AI-based IoT systems, effective and efficient algorithms are in urgent need for IoT Edge Computing. Time-series data classification is an ongoing problem in applications for mobile devices (e.g. music genre classification on mobile phones). However, the traditional methods require field expertise to extract handcrafted features from the time-series data. Deep learning has been demonstrated to be effective and efficient in this kind of data. Nevertheless, the existing works neglect some of the sequential relationships found in the time-series data, which are significant for time-series data classification. Considering the aforementioned limitations, we propose a hybrid architecture, named the parallel recurrent convolutional neural network (PRCNN). The PRCNN is an end-to-end training network that combines feature extraction and time-series data classification in one stage. The parallel CNN and Bi-RNN blocks focus on extracting the spatial features and temporal frame orders, respectively, and the outputs of two blocks are fused into one powerful representation of the time-series data. Then, the syncretic vector is fed into the softmax function for classification. The parallel network structure guarantees that the extracted features are robust enough to represent the time-series data. Moreover, the experimental results demonstrate that our proposed architecture outperforms the previous approaches applied to the same datasets. We also take the music data as an example to conduct contrastive experiments to verify that our additional parallel Bi-RNN block can improve the performance of time-series classification compared with utilizing CNNs alone.

Segmentation process and spectral characteristics in the determination of musical genres

Abstract Over past few years there has been a tendency to store audio tracks for later use on CD-DVDs, HDD-SSDs as well as on internet, which makes it challenging to classify information either online or offline. For this purpose, audio tracks must be tagged. Tags are said to be texts based on semantic information of sound [1]. Thus, music analysis can be done in several ways [2] since music is identified by its genre, artist, instruments and structure, by a tagging system that can be manual or automatic. The manual tagging allows visualization of behavior of an audio track either in time domain or in frequency domain as in spectrogram, making it possible to classify songs without listening to them. However, this process is very time consuming and labor intensive, including health problems [3] which shows that the volume, sound sensitivity, time and cost required for a manual labeling process is generally prohibitive. Three fundamental steps are required to carry out automatic labelling: pre-processing, feature extraction and classification [4]. The present study developed an algorithm for performing automatic classification of music genres using a segmentation process employing spectral characteristics such as centroid (SC), flatness (SF) and spread (SS), as well as a time spectral characteristic.

An Analysis of the Effect of Data Augmentation Methods: Experiments for a Musical Genre Classification Task

Supervised machine learning relies on the accessibility of large datasets of annotated data. This is essential since small datasets generally lead to overfitting when training high-dimensional machine-learning models. Since the manual annotation of such large datasets is a long, tedious and expensive process, another possibility is to artificially increase the size of the dataset. This is known as data augmentation. In this paper we provide an in-depth analysis of two data augmentation methods: sound transformations and sound segmentation. The first transforms a music track to a set of new music tracks by applying processes such as pitch-shifting, time-stretching or filtering. The second one splits a long sound signal into a set of shorter time segments. We study the effect of these two techniques (and the parameters of those) for a genre classification task using public datasets. The main contribution of this work is to detail by experimentation the benefit of these methods, used alone or together, during training and/or testing. We also demonstrate their use in improving the robustness of potentially unknown sound degradations. By analyzing these results, good practice recommendations are provided.

Machine learning for music genre: multifaceted review and experimentation with audioset

Music genre classification is one of the sub-disciplines of music information retrieval (MIR) with growing popularity among researchers, mainly due to the already open challenges. Although research has been prolific in terms of number of published works, the topic still suffers from a problem in its foundations: there is no clear and formal definition of what genre is. Music categorizations are vague and unclear, suffering from human subjectivity and lack of agreement. In its first part, this paper offers a survey trying to cover the many different aspects of the matter. Its main goal is give the reader an overview of the history and the current state-of-the-art, exploring techniques and datasets used to the date, as well as identifying current challenges, such as this ambiguity of genre definitions or the introduction of human-centric approaches. The paper pays special attention to new trends in machine learning applied to the music annotation problem. Finally, we also include a music genre classification experiment that compares different machine learning models using Audioset.

Recognizing Musical Entities in User-generated Content

Recognizing Musical Entities is important for Music Information Retrieval (MIR) since it canimprove the performance of several tasks such as music recommendation, genre classification or artist similarity. However, most entity recognition systems in the music domain have concentrated on formal texts (e.g. artists’ biographies, encyclopedic articles, etc.), ignoring rich and noisy user-generated content. In this work, we present a novel method to recognize musicalentities in Twitter content generated by users following a classical music radio channel. Our approach takes advantage of both formal radio schedule and users’ tweets to improve entity recognition. We instantiate several machine learning algorithms to perform entity recognition combining task-specific and corpus-based features. We also show how to improve recognition results by jointly considering formal and user-generated content.

Deep attention based music genre classification

As an important component of music information retrieval, music genre classification attracts great attentions these years. Benefitting from the outstanding performance of deep neural networks in computer vision, some researchers apply CNN on music genre classification tasks with audio spectrograms as input instead, which has similarities with RGB images. These methods are based on a latent assumption that spectrums with different temporal steps have equal importance. However, it goes against the theory of processing bottleneck in psychology as well as our observation from audio spectrograms. By considering the differences of spectrums, we propose a new model incorporating with attention mechanism based on Bidirectional Recurrent Neural Network. Furthermore, two attention-based models (serial attention and parallelized attention) are implemented in this paper. Comparing with serial attention, parallelized attention is more flexible and gets better results in our experiments. Especially, the CNN-based parallelized attention models with taking STFT spectrograms as input outperform the previous work.

Genre of Bangla Music: A Machine Classification Learning Approach

The necessity for designing autonomous indexing tools to establish expressive and efficient means of describing musical media content is well recognized. Music genre classification systems are significant to manage and use music databases. This research paper proposes an enhanced method to automatically classify music into different genre using a machine learning approach and presents the insight and results of the application of the proposed scheme to the classification of a large set of The Bangla music content, a South-East Asian language rich with a variety of music genres developed over many centuries. Building upon musical feature extraction and decision-making techniques, we propose new features and procedures to achieve enhanced accuracy. We demonstrate the efficacy of the proposed method by extracting features from a dataset of hundreds of The Bangla music pieces and testing the automatic classification decisions. This is the first development of an automated classification technique applied specifically to the Bangla music to the best of our knowledge, while the superior accuracy of the method makes it universally applicable.

Multi-agent system application for music features extraction, meta-classification and context analysis

Manual music classification is a slow and costly process. Most recent works about music auto-classification such as genre or emotions make this process easier, but are focused on a single task. In this work, a music multi-classification platform is presented. This platform is based on multi-agent systems, allowing to distribute the extraction, classification, and service tasks among agents. The platform performs a musical genre and emotional classification and provides context information of songs from social networks such as Twitter and Last.fm. The methods chosen based on meta-classifiers to perform single-label and multi-label classification obtain great results. In the case of multi-label classification, better results are obtained than in other previous works.

Extraction of acoustic features based on auditory spike code and its application to music genre classification

A new method of extracting acoustic features based on auditory spike code is proposed. An auditory spike code represents the acoustic activities created by the signal, similar to sound encoding of the human auditory system. In the proposed method, an auditory spike code of the signal is computed using a 64-band Gammatone filterbank as the kernel functions. Then, for each spectral band, the sum and non-zero counts of the auditory spike code are determined, and the features corresponding to the population and occurrence rate of the acoustic activities for each band are computed. In addition, the distribution of the acoustic activities on a time axis is analysed based on the histogram of time intervals between the adjacent acoustic activities, and the features for expressing temporal properties of the signal are extracted. The reconstruction accuracy of the auditory spike code is also measured as the features. Different from most conventional features obtained by complex statistical modelling or learning, the features by the proposed method can directly show specific acoustic characteristics contained in the signal. These features are applied to a music genre classification, and it is confirmed that they provide a performance comparable to state-of-the-art features.

Highlights From the Audio and Acoustic Signal Processing Technical Committee [In the Spotlight

The IEEE Audio and Acoustic Signal Processing Technical Committee (AASP TC) is one of 13 TCs in the IEEE Signal Processing Society. Its mission is to support, nourish, and lead scientific and technological development in all areas of AASP. These areas are currently seeing increased levels of interest and significant growth, providing a fertile ground for a broad range of specific and interdisciplinary research and development. Ranging from array processing for microphones and loudspeakers to music genre classification, from psychoacoustics to machine learning (ML), from consumer electronics devices to blue-sky research, this scope encompasses countless technical challenges and many hot topics. The TC has roughly 30 elected volunteer members drawn equally from leading academic and industrial organizations around the world, unified by the common aim of offering their expertise in the service of the scientific community.

Feature Selection for Musical Genre Classification Using a Genetic Algorithm

Feature Selection for Musical Genre Classification Using a Genetic Algorithm

A Two-Step Approach for Classifying Music Genre on the Strength of AHP Weighted Musical Features

Music is a series of harmonious sounds well arranged by musical elements including rhythm, melody, and harmony (RMH). Since music digitalization has resulted in a wide variety of new musical applications used in daily life, the use of music genre classification (MGC), especially MGC automation, is increasingly playing a key role in the development of novel musical services. However, achieving satisfactory performance of MGC automation is a practical challenge. This paper proposes a two-step approach for music genre classification (called TSMGC) on the strength of analytic hierarchy process (AHP) weighted musical features. Compared with other MGC approaches, the TSMGC has three strong points for better performance: (1) various musical features extracted from the RMH and the calculated entropy are comprehensively considered, (2) the weight of features and their impact values determined by AHP are applied on the basis of the Exponential Distribution function, (3) music can be accurately categorized into a main-class and further sub-classes through a two-step classification process. According to the conducted experiment, the result exhibits an accuracy rate of 87%, which demonstrates the potential for the proposed TSMGC method to meet the emerging needs of MGC automation.

The Concept of Genre in Music: A New Model Suggestion for the Classification of Music Genres

The Concept of Genre in Music: A New Model Suggestion for the Classification of Music Genres