Automatic Musical Instrument Recognition Using K-NN and MLP Neural Networks

Azarloo, Akram; Farokhi, Fardad

doi:10.1109/cicsyn.2012.61

Cited by 14 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From our collected skeleton data we developed two datasets: (1) a ground-truth labelled dataset; and (2) a bone segment feature space dataset. Then, we built two separate classifiers, k-Nearest Neighbour (k-NN) and a Multi-layer Perceptron (MLP) model (see Azarloo & Farokhi, 2012;García, Mollineda, & Sánchez, 2008;Kayikcioglu & Aydemir, 2010;Pacheco & López, 2019) to demonstrate the discrimination of our new feature and to evaluate our feature's performance using representative batch processing and real-time classifiers.…”

Section: Human Recognition With Anonymised Skeleton Datamentioning

confidence: 99%

“…Several statistical classification approaches currently exist that have been shown to be effective with datasets like ours. Building on the work of Azarloo and Farokhi (2012), García et al (2008), Kayikcioglu and Aydemir (2010) and Pacheco and López (2019), we consider the k-NN algorithm (Altman, 1992); a non-parametric method which is arguably the most naive and commonly used method for classification and regression (Altman, 1992). The k-NN algorithm has been directly applied to images in a broad range of applications such as handwriting recognition (Wu & Zhang, 2010) and medical image classification (Warfield, 1996).…”

Section: Batch Processing Human Recognition: K-nearest Neighbourmentioning

confidence: 99%

See 1 more Smart Citation

Automated recognition of individual performers from de-identified video sequences

Chen

Czarnuch

Dove

et al. 2023

Machine Learning with Applications

View full text Add to dashboard Cite

Section: Human Recognition With Anonymised Skeleton Datamentioning

confidence: 99%

Section: Batch Processing Human Recognition: K-nearest Neighbourmentioning

confidence: 99%

Automated recognition of individual performers from de-identified video sequences

Chen

Czarnuch

Dove

et al. 2023

Machine Learning with Applications

View full text Add to dashboard Cite

“…While the applicability of such STRF features for continuous solo performances is remarkably accurate, the cross-domain transition from single notes to musical phrases (even for solos) is not a trivial one. As our analysis shows, the classic windowing approach to parse musical phrases is suboptimal [23, 26, 28, 53]. It coarsely bins the time signal into segments of equal length; but with no consideration to the underlying structure.…”

Section: Discussionmentioning

confidence: 99%

Biomimetic spectro-temporal features for music instrument recognition in isolated notes and solo phrases

Patil

Elhilali

2015

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

The identity of musical instruments is reflected in the acoustic attributes of musical notes played with them. Recently, it has been argued that these characteristics of musical identity (or timbre) can be best captured through an analysis that encompasses both time and frequency domains; with a focus on the modulations or changes in the signal in the spectrotemporal space. This representation mimics the spectrotemporal receptive field (STRF) analysis believed to underlie processing in the central mammalian auditory system, particularly at the level of primary auditory cortex. How well does this STRF representation capture timbral identity of musical instruments in continuous solo recordings remains unclear. The current work investigates the applicability of the STRF feature space for instrument recognition in solo musical phrases and explores best approaches to leveraging knowledge from isolated musical notes for instrument recognition in solo recordings. The study presents an approach for parsing solo performances into their individual note constituents and adapting back-end classifiers using support vector machines to achieve a generalization of instrument recognition to off-the-shelf, commercially available solo music.

show abstract

“…The proposed work uses GMM as a classifier and the instance of the instruments are randomized into 70% for training and 30% for testing. It classifies the 16 different instruments efficiently with complex signals.The proposed algorithm [8] uses MLP and K-Nearest Neighbors for classifying musical instrument.…”

Section: Literature Reviewmentioning

confidence: 99%

An Enhanced Musical Instrument Classification using Deep Convolutional Neural Network

Prabavathy*¹,

Rathikarani²,

Dhanalakshmi³

2019

IJRTE

View full text Add to dashboard Cite

Retrieval of musical information from musical databases is a major challenging issue in a digital world. Therefore, it is necessary to develop an efficient tool for retrieving the musical information. Musical instrument classification plays a major role for retrieving the information from musical database. In order to retrieve the musical instrument efficiently, an enhanced musical instrument classification algorithm using deep Convolutional Neural Network is proposed in this paper. The proposed algorithm consists of convolutional layers interleaved with two pooling functions followed by two fully interconnected layers. There are sixteen instruments from different instrument families are taken for evaluating the performance of proposed algorithm. The experimental result shows that the proposed algorithm recognizes the instruments significantly and achieves the greater accuracy than existing algorithm

show abstract

Automatic Musical Instrument Recognition Using K-NN and MLP Neural Networks

Cited by 14 publications

References 8 publications

Automated recognition of individual performers from de-identified video sequences

Automated recognition of individual performers from de-identified video sequences

Biomimetic spectro-temporal features for music instrument recognition in isolated notes and solo phrases

An Enhanced Musical Instrument Classification using Deep Convolutional Neural Network

Contact Info

Product

Resources

About