Class Of Musical Instruments Research Articles

Deep Neural Network for Musical Instrument Recognition Using MFCCs

The task of efficient automatic music classification is of vital importance and forms the basis for various advanced applications of AI in the musical domain. Musical instrument recognition is the task of instrument identification by virtue of its audio. This audio, also termed as the sound vibrations are leveraged by the model to match with the instrument classes. In this paper, we use an artificial neural network (ANN) model that was trained to perform classification on twenty different classes of musical instruments. Here we use use only the mel-frequency cepstral coefficients (MFCCs) of the audio data. Our proposed model trains on the full London philharmonic orchestra dataset which contains twenty classes of instruments belonging to the four families viz. woodwinds, brass, percussion, and strings. Based on experimental results our model achieves state-of-the-art accuracy on the same.

Emotion-related words and emotional analogies as teaching strategies for expressivity

This study was designed to investigate the effect of student performance level on teachers’ expressive-emotional discourse in musical instrument classes, the possible loci of emotions present in teachers’ discourse and the existence of a tradition of expressive factors in the interpretation of certain musical works. Forty-seven guitar master classes were recorded, and students’ performance levels were subsequently evaluated by independent judges. All material was then transcribed and coded according to the following variables: emotion words, emotional analogies and teaching of expressivity. A questionnaire administered to professional guitarists elicited information on the expressive tradition of the works played in these master classes. Statistical techniques (analysis of variance [ANOVA], the Mann–Whitney U test and the chi-square test) were used to analyse the variables. Results suggest that students’ performance levels and the expressive tradition of the repertoire played can be decisive in how teachers construct their expressive-emotional discourse. Finally, as a teaching strategy for musical expressivity, focus can be directed either towards the emotions felt by the student (i.e., internal locus), or emotions expressed by the music or another source external to the student (i.e., external locus).

Musical instrument emotion recognition using deep recurrent neural network

Music is one of the effective media to convey emotion. Emotion recognition in music is the process of identifying the emotion from the music clips. In this paper, a novel approach is proposed to recognize the emotion by classes of musical instruments using deep learning techniques. Music dataset is collected for four instrument types, string, percussion, woodwind, and brass. These instruments types are grouped into four emotions, happy, sad, neutral and fear. The Mel frequency cepstral coefficients (MFCC), Chroma energy normalized statistics (CENS), chroma short time Fourier transform (STFT), spectral features spectral centroid, bandwidth, rolloff, and temporal feature ZCR are extracted from the instrumental music data set. Based on the extracted features recurrent neural networks (RNN) are trained to recognize the emotion. The performance of RNN is compared with the baseline machine learning classification algorithms. The results indicate that MFCC features with deep RNN give better performance for instrument emotion recognition. It also shows that instrument class plays an important role in the emotion induced by the music. Music is one of the effective media to convey emotion. Emotion recognition in music is the process of identifying the emotion from the music clips. In this paper, a novel approach is proposed to recognize the emotion by classes of musical instruments using deep learning techniques. Music dataset is collected for four instrument types, string, percussion, woodwind, and brass. These instruments types are grouped into four emotions, happy, sad, neutral and fear. The Mel frequency cepstral coefficients (MFCC), Chroma energy normalized statistics (CENS), Chroma short time Fourier transform (STFT), spectral features spectral centroid, bandwidth, rolloff, and temporal feature ZCR are extracted from the instrumental music data set. Based on the extracted features recurrent neural networks (RNN) are trained to recognize the emotion. The performance of RNN is compared with the baseline machine learning classification algorithms. The results indicate that MFCC features with deep RNN give better performance for instrument emotion recognition. It also shows that instrument class plays an important role in the emotion induced by the music.

3D printing technology in musical instrument research: reviewing the potential

PurposeThis paper aims to discuss additive manufacturing (AM) in the context of applications for musical instruments. It examines the main AM technologies used in musical instruments, goes through a history of musical applications of AM and raises the questions about the application of AM to create completely new wind instruments that would be impossible to produce with conventional manufacturing.Design/methodology/approachA literature research is presented which covers a historical application of AM to musical instruments and hypothesizes on some potential new applications.FindingsAM has found extensive application to create conventional musical instruments with unique aesthetics designs. It’s true potential to create entirely new sounds, however, remains largely untapped.Research limitations/implicationsMore research is needed to truly assess the potential of additive manufacturing to create entirely new sounds for musical instrument.Practical implicationsThe application of AM in music could herald an entirely new class of musical instruments with unique sounds.Originality/valueThis study highlights musical instruments as an unusual application of AM. It highlights the potential of AM to create entirely new sounds, which could create a whole new class of musical instruments.

Tom Rossing’s influence on our understanding of the acoustics of wind instrument mechanisms

During his outstanding career, Tom Rossing studied the acoustics of every major class of musical instruments. During my first trip to the United States, to participate as a student in the ASA Columbus 1999 meeting, I was given the opportunity to measure my free-reed pipe in Tom Rossing’s lab using his novel laser vibrometer. Like many others, he soon also became my role model for his broad knowledge, scientific depth, and his sheer pragmatism (that enabled him to write so many groundbreaking books). In particular, our generation greatly benefits from his gift for accurately describing the key fundamentals of complex acoustic phenomena based on a traditional understanding of physics and the use of groundbreaking measurement techniques such as laser vibrometry and TV holography. Tom Rossing never separated the hard work required to understand the underlying mechanisms of musical instruments from the cultural importance and delight of listening to and performing music. And so, he reminded everybody, right af...

The Telematic Music System: Affordances for a New Instrument to Shape the Music of Tomorrow

New digital technologies enabled the Virtual Reality movement in the 1990s, which led to the euphoric belief that we could virtually teleport ourselves to a distant location with such great realism that we would lose our awareness of the enabling technology. Especially in the particular case of music collaborations, however, it has meanwhile become clear that this goal is unreachable because of the unavoidable transmission latency over long distances and other secondary factors. This article explores how we can create new and better design goals for telematic music collaborations by treating telematic systems as a new class of musical instruments. From this viewpoint, the creation of new art forms for the new medium becomes a central challenge, in addition to the development of better telematic technology. In particular, the new works need to focus on the affordances that the telematic system introduces, not just circumnavigate current system limitations.

Feature dependence in the automatic identification of musical woodwind instruments.

The automatic identification of musical instruments is a relatively unexplored and potentially very important field for its promise to free humans from time-consuming searches on the Internet and indexing of audio material. Speaker identification techniques have been used in this paper to determine the properties (features) which are most effective in identifying a statistically significant number of sounds representing four classes of musical instruments (oboe, sax, clarinet, flute) excerpted from actual performances. Features examined include cepstral coefficients, constant-Q coefficients, spectral centroid, autocorrelation coefficients, and moments of the time wave. The number of these coefficients was varied, and in the case of cepstral coefficients, ten coefficients were sufficient for identification. Correct identifications of 79%-84% were obtained with cepstral coefficients, bin-to-bin differences of the constant-Q coefficients, and autocorrelation coefficients; the latter have not been used previously in either speaker or instrument identification work. These results depended on the training sounds chosen and the number of clusters used in the calculation. Comparison to a human perception experiment with sounds produced by the same instruments indicates that, under these conditions, computers do as well as humans in identifying woodwind instruments.

SOUND AND MUSIC FROM CHUA'S CIRCUIT

Nonlinear Dynamics have been very inspiring for musicians, but have rarely been considered specifically for sound synthesis. We discuss here the signals produced by Chua's circuit from an acoustical and musical point of view. We have designed a real-time simulation of Chua's circuit on a digital workstation allowing for easy experimentation with the properties and behaviors of the circuit and of the sounds. A surprisingly rich and novel family of musical sounds has been obtained. The audification of the local properties of the parameter space allows for easy determination of very complex structures which could not be computed analytically and would not be simple to determine by other methods. Finally, we have found that the time-delayed Chua's circuit can model the basic behavior of an interesting class of musical instruments.

Models of musical instruments from Chua's circuit with time delay

We study a new version of Chua's circuit where the linear elements are replaced by a delay line. We show that this circuit is a model of an interesting class of musical instruments, namely, those, like the clarinet, consisting of a massless reed coupled to a passive linear system. The properties and behaviors of this circuit are studied with or without a filter in the feedback loop. In particular, the oscillation conditions are determined, and the respective role of the nonlinearity and of the linear elements are explained. Real-time simulations of the time-delayed Chua's circuit on a digital workstation makes possible easy experimentation with signals and sounds. A surprisingly rich and novel family of periodic and chaotic musical sounds has been obtained. The audification of the local properties of the parameter space permits easy determination of very complex structures that could not be computed analytically and would be difficult to determine by other methods.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Computer analysis and transcription of performed music: A project report

The purpose of this project was to create a system that would automatically transcribe musical sounds into their equivalent music notation. In other words, the system could automatically detect the notes in a played melody and write out the note patterns just as a human transcriber would. For this task, a computer system was proposed that would work solely from tape recordings of a wide class of musical instruments.

The Hocket-Technique in African Music

Studies of the musical instruments of Africa by Kirby, Wachsmann, Maquet, Solderberg and others, have demonstrated that, in addition to drums, examples of all the main classes of musical instruments are to be found in sub-Saharan Africa. In addition to drums, there is a wide variety of idiophones (including xylophones), as well as various types of lutes, zithers, flutes, etc.In spite of this variety, there appears to be a widespread tendency to use these instruments not in large heterogeneous ensembles, but in homogeneous ensembles, or in limited combinations in which one type of instrument predominates. There are, for example, ensembles of drums or xylophones, ensembles of flutes or trumpets, or ensembles in which these are combined with “secondary” instruments—usually of a percussive nature. Here and there a flute, a fiddle or a lute may be found in a secondary role in an ensemble, with the function of providing particular effects or enriching the texture of the music.