Musical Instrument Classification Research Articles

Musical instrument classifier for early childhood percussion instruments.

While the musical instrument classification task is well-studied, there remains a gap in identifying non-pitched percussion instruments which have greater overlaps in frequency bands and variation in sound quality and play style than pitched instruments. In this paper, we present a musical instrument classifier for detecting tambourines, maracas and castanets, instruments that are often used in early childhood music education. We generated a dataset with diverse instruments (e.g., brand, materials, construction) played in different locations with varying background noise and play styles. We conducted sensitivity analyses to optimize feature selection, windowing time, and model selection. We deployed and evaluated our best model in a mixed reality music application with 12 families in a home setting. Our dataset was comprised of over 369,000 samples recorded in-lab and 35,361 samples recorded with families in a home setting. We observed the Light Gradient Boosting Machine (LGBM) model to perform best using an approximate 93 ms window with only 12 mel-frequency cepstral coefficients (MFCCs) and signal entropy. Our best LGBM model was observed to perform with over 84% accuracy across all three instrument families in-lab and over 73% accuracy when deployed to the home. To our knowledge, the dataset compiled of 369,000 samples of non-pitched instruments is first of its kind. This work also suggests that a low feature space is sufficient for the recognition of non-pitched instruments. Lastly, real-world deployment and testing of the algorithms created with participants of diverse physical and cognitive abilities was also an important contribution towards more inclusive design practices. This paper lays the technological groundwork for a mixed reality music application that can detect children's use of non-pitched, percussion instruments to support early childhood music education and play.

Classification of ancient Greek wind musical instruments

The article offers a classification of wind music instruments of ancient Greece, the references to which have been revealed through the study of written sources (both epic and lyric poetry, as well as works of tragedians) from Homeric times to the end of the Classical period. Pictorial sources are used to characterise the appearance of the instruments.

ANCIENT CLASSIFICATIONS OF MUSICAL INSTRUMENTS

This article discusses the basic principles of classification of musical instruments of ancient theorists. Characteristics of ancient taxonomies, features of classification principles and their relationship with Western European theoretical thought about musical instruments are given. The author comes to the conclusion that ancient classification theories had a significant influence on Western European organology, both in relation to the concepts of systematization of musical instruments and in the terminology used. The study of ancient music theory allows us to identify the origins of the ideas of Western European taxonomies and modern classifications of musical instruments.

The Team Games Tournament Media Box Instrument Learning Model Can Improve Learning Outcomes On Traditional Musical Instrument Classification Materials At SMP Plus Taruna Andalan Pangkalan Kerinci

The aim of this research is to determine whether the implementation of the Team Games Tournament Learning Model with box instrument media can enhance the learning outcomes of eighth-grade students in class VIII-B at SMP Plus Taruna Andalan Pangkalan Kerinci on the topic of traditional musical instrument classification. This research is a Classroom Action Research (CAR) by Kurt Lewin, which consists of four stages to be followed: planning, acting, observing, and reflecting. Data collection was carried out over 2 cycles using both quantitative and qualitative data analysis techniques. From the test results conducted, starting from the pre-cycle, Cycle I, to Cycle II, there was an improvement in the average scores of students' learning outcomes. The initial average score in the pre-cycle was around 61.68. However, in Cycle I, students' learning outcomes reached an average of approximately 74.68, indicating an improvement of 13 points from the pre-cycle. A more significant improvement was observed in Cycle II, where the average learning outcomes increased to 93.37. This indicates that the Team Games Tournament Learning Model with Box Instrument media is highly effective in enhancing understanding and mastery of the material. Students were able to achieve much better learning outcomes at the end of Cycle II, approximately 31 points higher than the pre-cycle score.

Manyampai Perwujudan Musik Sirompak di Nagari Taeh Baruah Kabupaten Lima Puluh Kota

Sirompak is a traditional Minangkabau art originating from Taeh Baruah, Limapuluh Kota, West Sumatra. In the past, Sirompak was known as a magical ritual ceremony carried out by a sirompak handler whose aim was to avenge the heart of a woman who had insulted a man. The basirompak performance is a presentation of vocal music called dendang Minangkabau presentation of singing vocal music with the production of a wind instrument called saluang sirompak. This musical instrument is included in the classification of aerophone musical instruments (the main sound is produced by the vibration of blowing air). Traditional musical instruments accompany melodic vocals (dendang/mantras) by a singer (singer). The composition work "manyampai" consists of two parts, using a traditional reinterpretation approach, in the first part of this work using the 'emergent' technique, in the first part the composer provides several repetitive vocal compositions, using the instruments saluang Sirompak, kerinding, cymbals, didgeredo, gong, rain stick. The second part of this work emphasizes the production of several screaming vocals, screams, laughing vocals, animal sounds and crying. This second part also uses the instruments cymbals, gongs, Sirompak saluang

Discerning Sound Ethnobiology in the realm of Ethnomusicology: A Study of Deori Folk Musical Instruments

Folk music has always been known to be the best source of connecting us to our culture and keeping our identity alive as an individual and as a group. The concept of melody and the artistic pursuit of musical composition were probably unknown to early players of musical instruments. A musical instrument is used to make musical sounds. Once humans moved from making sounds with their bodies-for example, by clapping-to using objects to create music from sounds, musical instruments were born. The purpose and meaning of musical instruments differs from region to region and from culture to another. Instruments have special significance in music. The Deoris belong to the Sino-Tibetan family of Mongoloid stock. They are considered to be one of the communities found in Assam and some parts of Arunachal Pradesh in North- East India. The word ‘Deori’ means the offspring of Gods and Goddesses. The Indian Constitution has regarded the Deoris as a scheduled tribe of Assam and they are considered to be a small plains tribe. The Deoris have their own language which is the Deori language. Customarily the Deoris are divided into four clans namely ‘Dibongiya, Tengaponiya, Bongiya, Patorgoyan’ which are present till date. This paper studies the vitality of sound ethnobiology, ethics of instruments, crafting and classification of musical instruments in the field of Ethnomusicology. Musical instruments are constructed in a broad array of styles and shapes, using many different materials. It mainly explores and discerns the variety of Deori traditional musical instruments from a closer proximity in the realm of material culture under the broader context of folklore. The crafting processes and the materials used for the making of the musical instruments of the Deoris is discussed in a detailed manner.

Critical Realist Foundations for Berlin Comparative Musicology(vergleichende Musikswissenschaft)

Summary Is it possible to discover the critical realist foundations of Gestalt theory in Berlin comparative musicology (vergleichende Kunstwissenschaft) associated above all with Erich M. von Hornbostel? The balance of natural science explanation and phenomenal experience is a useful model for overcoming Eurocentrism in comparative ethnomusicology, relying both on third-person tools and indigenous music systems. This paper uses Gestalt critical realist epistemology and methodology and a portrayal of the strata making up the understanding of a musical act with chemico-physical, phenomenal and cultural components to create an “amphibian” ethnomusicology. Using this framework it is possible to understand Hornbostel and Sachs’ musical instrument classification system and Hornbostel’s account of “primitive” music as strata in a Gestalt explanatory system. The potential binding agent through the strata is isomorphism.

Музыкальные инструменты крымских татар в собрании Бахчисарайского музея-заповедника

The article gives a detailed descripton of the musical instruments of the Crimean Tatars, which are presented in the collection of the Bakhchisarai Museum-Reserve and are interesting for studying musical culture in general. The history of formation of the collection of musical instruments is connected with the creation of the Museum of Turkic-Tatar Culture in Bakhchisarai. In the 1920s and 30s, the staff of the institution collected a large number of antiquities, including musical instruments. In scientific works devoted to the music of the Crimean Tatar people, researchers mainly paid attention to the songs, melodies and partially mentioned traditional instruments. In this work, it is assumed to study the issues of acquisition, cataloging, classification of musical instruments, as well as determining the characteristic features of these items. The research will be relevant for further use in creating expositions, excursion stories, possibly also in recreating folk instruments and playing them.

On the Organological Potential of Video Games

The various—and often unpredictable—musical applications given to new digital technologies have fundamentally altered our ways of creating, performing, representing, and understanding musical instruments, giving way to new sounding artifacts that pose unprecedented challenges to musical iconography and organology. The multifaceted nature of digital musical instruments has exposed the limitations of traditional organology, prompting a redefinition of the concept of instrumentality and an upsurge of new methodologies. This renovation, however, has yet to recognize the organological potential of video games, which often make use of visual depictions and reconfigurations of musical instruments in the creation and characterization of virtual universes and characters. Musical instruments play an essential role in regulating the tensions between fiction and reality that underlie videoludic experiences by constituting an active agent in the player’s interaction and emerging relationships with the gameworld and its music. Research on these artifacts has been scarce yet promising thus far, providing this article with a wide-ranging collection of references that have served to inform the proposal of a new cataloguing card model for the identification, examination, and classification of musical instruments represented in, and constituted by, video games and consoles. This model merges traditional organological knowledge inherited from hierarchical systems of classification—such as the Hornbostel-Sachs—with new paradigms and taxonomical categories. In so doing, this model aims to accommodate the dual nature of ludomusical instruments as both iconographical resources of undeniable sociocultural transcendence, and organological artifacts with a set of assigned roles within their virtual worlds. The ultimate goal is to provide a framework that fully recognizes the impact of ludomusical instruments in musical experiences and organological knowledge and expectations both inside and outside the medium.

A study on the classification of Chinese folk instruments based on deep learning

Due to the Internet's tremendous expansion in recent years, digital music has seen explosive growth. It is becoming increasingly important to provide fast and accurate music retrieval for users, and music information retrieval has gradually become a research hotspot. Among them, the classification of musical instruments is one of the hot research directions. As an important part of the world's musical instruments, the Chinese folk musical instrument tradition has great research value, but there is less research in this direction. Traditional music classification methods can be roughly divided into two steps: manual feature extraction and traditional machine learning. But traditional music classification has several shortcomings, as follows. Firstly, manual extraction of music features has a high error rate and it is very difficult to ensure the accuracy of the features, and the labor cost is high; secondly, traditional machine learning still has problems with multiple classifications and training on large scale data. Therefore, in this paper, based on previous research, the original data features are extracted from the Mel Frequency Cepstrum Coefficient (MFCC), which is a feature that can represent musical timbre, and deep learning is proposed to be used to classify traditional Chinese folk instruments. This paper finds that the results of identifying and classifying Chinese folk musical instruments using different classical classification methods are compared when the training set and test set data are the same. According to the experimental results, the use of KNN has the best performance among these classification methods.

The Organology of Rotenese Musical Instruments According to the Hornbostel-Sachs Classification System

This article aims to propose a classification of Rotenese traditional musical instruments based on the Hornbostel-Sachs (the H-S) method. The author conducted this ethnographic field research on the island of Rote, East Nusa Tenggara Province, from 2015 to 2016. The seven existing Rotenese traditional musical instruments analyzed in this article are: 1) meko ai or the meko o (the wooden or the bamboo xylophone); 2) the meko besik or the meko lilok (the hanging iron or brass gongs); 3) the meko besik or the meko lilok (the iron or brass metallophone); 4) the labu kici or the labu so’e (the single-headed, bowl-shaped drum); 5) the tambur or the labu (the single-headed, long cylindrical drum); 6) the bitala (the crash cymbals); and 7) the sasandu (the heterochord tube-zither). The only Rotenese traditional musical instrument that is not discussed in this article is kianuk, the two-holed bamboo flute, approximately ten centimeters long. This instrument does not exist anymore. The four aspects discussed in this article are 1) the construction, 2) the materials, 3) the ways of playing, and 4) the size of the instruments. Information was gathered from interviews with some key persons and through photography and video recording. This research acknowledges some limitations; for instance, providing exact information is challenging and limiting in the absence of a standard for meko tuning and making. Therefore, the information given here about the size, the material, the tuning, and the note intervals is an approximation.

The Kundung (Xylophone) of The Berom People and The Classification of Indigenous African Musical Instruments

The Kundung (Xylophone) of The Berom People and The Classification of Indigenous African Musical Instruments

Acoustic Descriptors for Characterization of Musical Timbre Using the Fast Fourier Transform

The quantitative assessment of the musical timbre in an audio record is still an open-ended issue. Evaluating the musical timbre allows not only to establish precise musical parameters but also the recognition, classification of musical instruments, and assessment of the musical quality of a sound record. In this paper, we present a minimum set of dimensionless descriptors, motivated by musical acoustics, using the spectra obtained by the Fast Fourier Transform (FFT), which allows describing the timbre of wooden aerophones (Bassoon, Clarinet, Transverse Flute, and Oboe) using individual sound recordings of the musical tempered scale. We postulate that the proposed descriptors are sufficient to describe the timbral characteristics in the aerophones studied, allowing their recognition using the acoustic spectral signature. We believe that this approach can be further extended to use multidimensional unsupervised machine learning techniques, such as clustering, to obtain new insights into timbre characterization.

MIC_FuzzyNET: Fuzzy Integral Based Ensemble for Automatic Classification of Musical Instruments From Audio Signals

MIC_FuzzyNET: Fuzzy Integral Based Ensemble for Automatic Classification of Musical Instruments From Audio Signals

Sound classification using evolving ensemble models and Particle Swarm Optimization

Automatic sound classification attracts increasing research attention owing to its vast applications, such as robot navigation, environmental sensing, musical instrument classification, medical diagnosis, and surveillance. In this research, we propose an ensemble convolutional bidirectional Long Short-Term Memory (CBiLSTM) network with optimal hyper-parameter selection for undertaking sound classification. We first transform each audio signal into a spectrogram representation using the Short-time Fourier transform (STFT). A Particle Swarm Optimization (PSO) variant is subsequently proposed to optimize the learning rate, weight decay, numbers of filters and hidden units in the convolutional and BiLSTM layers, respectively, in order to extract effective spatial–temporal characteristics from the spectrogram inputs. To tackle the issue of stagnation in optimization, the proposed algorithm incorporates local exploitation using secant and Newton–Raphson methods, promising leader generation using regular and irregular super-ellipse formulae, and three-dimensional spherical search coefficients. Moreover, it takes into account multiple fused elite signals in conjunction with numerical analysis based exploitation to balance between diversification and intensification. A variety of CBiLSTM networks with distinctive optimized settings are devised. An ensemble model is then constructed by incorporating a set of three yielded networks based on a majority voting scheme. Evaluated using several audio data sets, our ensemble CBiLSTM networks outperform those with default and optimal settings identified by other search methods, existing deep architectures and state-of-the-art related studies. In addition to sound classification tasks, the proposed PSO algorithm also outperforms a number of classical and advanced search methods for solving diverse unimodal and multimodal benchmark functions with statistical significance.

Re-Contemplating the Classification of Multiple Reeds

The 2011 Revision of the Hornbostel-Sachs Classification of Musical Instruments by the MIMO Consortium categorises the “reedpipes with double (or quadruple) reeds” (422.1) according to the number of pipes, bore shapes, and finger holes, as it does to many other instrument groups. However, this scheme rather overlooks the significantly varied features of the multiple reeds themselves – their structural difference that determines their making and functioning, and how they connect to the pipe body – especially considering the vast varieties and distribution of multiple reeds compared with other types of reed pipes. Following the hierarchical classification of reed pipes (422) primarily according to the types of reeds, this paper would propose a further classification based on the “subtypes” of multiple reeds. The first level divides into “idioglot reeds” and “staple-mounted reeds” based on the connection of reeds with the pipe body. Idioglot reeds make one-part and two-part reed pipes, the former “usually a flattened stem” of the upper end of the pipe itself and the latter made from unbroken thick cane that fits inside the pipe bore. In contrast, staple-mounted reeds make three-part reed pipes. Some have fixed sides so that only the tips of reed blades are free to vibrate, while others have detached individual leaves that can vibrate on all sides. Given that reeds, as the primary source of sonic vibration, decide many fundamental features of a reed pipe, this recontemplated classification is likely to provide more distinct insight into their construct, functioning, and historical lineages.

Indian classical musical instrument classification using Timbral features

SummaryMusical 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.

Monophonic Musical Instrument Sound Classification Using Impulse Response Modeling

The field of music has promising commercial and social applications. Hence it has attracted the attention of researchers, engineers, sociologists and health care peoples. Therefore this particular research area has been selected.
 In this manuscript the monophonic musical classificationsystem using impulse response of the system is presented. In this research work 19 musical instruments monophonic sounds from 4 families are classified using WEKA classifier. The impulse response is of all musical instruments and families are computed in Cepstral Domain. AsImpulse response is used to model the body response of the musical instruments and helps to capture the information. It is different for different instruments. The features are extracted from impulse response and presented to WEKA Classifier.
 The Musical instrument classification for individual instruments and family is verified using impulse response modeling. It is found that the impulse response is different for different instruments. It helps to easily distinguish between instrument to instrument and family to family. For individual instruments, the average classification accuracy has been obtained is 83.23% and 85.55% for family classification.

PureMIC: A New Audio Dataset for the Classification of Musical Instruments based on Convolutional Neural Networks

Automatic classification of musical instruments from audio relies heavily on datasets of acoustic recordings of the instruments to train models of those instruments. To do this, precise labels of the instrument’s events are mandatory. Also, it is very difficult to obtain such labels, especially in polyphonic performances. OpenMic-2018 is a polyphonic dataset created specifically with the aim to train instrument models. However, this dataset is based on weak and incomplete labels. The automatic classification of sound events, based on the VGGish bottleneck layer as proposed before by the AudioSet, implies the classification of only one second at a time, making it hard to find the label of that exact moment. To answer this question, this paper proposes PureMIC, a new strongly labeled dataset (SLD) that isolates 1000 single instrument clips manually labeled. Moreover, the proposed model classifies clips over time and also enhances the labeling robustness of a high number of unlabeled samples in OpenMIC-2018 due to its ability of classification over time. In the paper we disambiguate and report the automatic labeling of previously unlabeled samples. The proposed new labels achieve a mean average precision (mAP) of 0.701 for OpenMIC test data, outperforming its baseline (0.66). The code is released online so that the research community can replicate and follow the proposed implementation.

Андураан дууг* ангилал зyйгээр шинжих нь (хөгжмийн археологи судлалын илтгэл) (=Исследование «андуран дуу» с использованием системы классификации (доклад по музыкальной археологии))

A musical artifact, unique not only in history of ethnic music of Mongolia, but also in world history and archeology was found in rock burials in the area of Zhargalant Khairkhan, Khovd aimak of Mongolia. A joint study of Mongolian and German scientists, based on the age of the artifact, confirms that the unique find dates back to the 7thand 8thcenturies of our era. This musical artifact has been successfully studied by Mongolian, German and American scientists in the fields of archeology, paleoanthropology, ancient writing, line drawing and musicology. The author of the article admits that in the future, by studying the structure of this original artifact, its parts, the original design and classification of ancient musical instruments, one of the most ancient musical instruments on which the ancient Mongolian epic was performed, an instrument that was lost throughout history, can be restored.