Musical instrument identification using Principal Component Analysis and Multi-Layered Perceptrons

Loughran, Róisín; Walker, Jacqueline; O’Neill, Michael; O’Farrell, Marion

doi:10.1109/icalip.2008.4590236

Cited by 11 publications

(13 citation statements)

References 8 publications

(8 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Studies performed using MLPs to classify musical instrument sounds have found able to produce a good result [1,15,18]. Deng et al [1] studied the quality of feature selection and the performance of three feature sets which are MFCC, perception-based and MPEG-7 for twenty instruments.…”

Section: Data Classification Using Mlpmentioning

confidence: 98%

“…There were assortments of sampling rate used in the previous work instead of 44.1 kHz as well. For example, 16kHz [14], 22kHz [12] and 32kHz [15]. These variety of parameters used in the literature show that there were no standard benchmarking in determining the best parameter for data representation.…”

Section: A Data Representationmentioning

confidence: 99%

“…Normally, the features used consists both spectral and temporal features. It has been highlighted by previous work that the combination of both spectral and temporal features is essential in order to provide an accurate description of sounds timbre [15]. In MPEG-7 multimedia description standard, the features are classified into two categories which are high-level and low-level descriptors [6].…”

Section: B Feature Extractionmentioning

confidence: 99%

See 2 more Smart Citations

Feature Extraction for Traditional Malay Musical Instruments Classification System

Senan

Ibrahim

Nawi

et al. 2009

2009 International Conference of Soft Computing and Pattern Recognition

View full text Add to dashboard Cite

Automatic musical instrument classification system deals with a large number of sound database and various types of features schemes. With the lack of data preprocessing, it might become invaluable asset that can impact the whole classification tasks. In handling an effective classification system, finding the best data sets with the best features schemes often a vital step in the data representation and feature extraction process. Thus, this study is conducted in order to investigate the impact of several factors that might affecting the classification accuracy such as audio length, segmented frame size and data sets size (for training and testing) towards Traditional Malay musical instruments sounds classification system. The perception-based and MFCC features schemes with total of 37 features was utilized in this study. Meanwhile, Multi-Layered Perceptrons classifier is employed to evaluate the modified data sets and extracted features schemes in terms of their classification performance. Results show that the highest accuracy of 99.57% was obtained from the best data sets with the combination of full features. It is also revealed that the identified factors had a significant role to the performance of classification accuracy. Hence, this study suggest that further feature analysis research is necessary for better solution in Traditional Malay musical instruments sounds classification system problem.

show abstract

Section: Data Classification Using Mlpmentioning

confidence: 98%

Section: A Data Representationmentioning

confidence: 99%

Section: B Feature Extractionmentioning

confidence: 99%

See 1 more Smart Citation

Feature Extraction for Traditional Malay Musical Instruments Classification System

Senan

Ibrahim

Nawi

et al. 2009

2009 International Conference of Soft Computing and Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…This classifier has been used in many machine learning tasks, including for musical instrument classification. 57 The MLP implementation used the open-source WEKA toolbox. 58 The processing and classification methodology was the same for both strategies but was performed independently to produce two alternative MFCC-based classification systems, B-1 and B-2 (see Sec.…”

Section: B Multilayer Perceptron Neural Network Classifiermentioning

confidence: 99%

A neurally inspired musical instrument classification system based upon the sound onset

Newton

Smith

2012

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

Physiological evidence suggests that sound onset detection in the auditory system may be performed by specialized neurons as early as the cochlear nucleus. Psychoacoustic evidence shows that the sound onset can be important for the recognition of musical sounds. Here the sound onset is used in isolation to form tone descriptors for a musical instrument classification task. The task involves 2085 isolated musical tones from the McGill dataset across five instrument categories. A neurally inspired tone descriptor is created using a model of the auditory system's response to sound onset. A gammatone filterbank and spiking onset detectors, built from dynamic synapses and leaky integrate-and-fire neurons, create parallel spike trains that emphasize the sound onset. These are coded as a descriptor called the onset fingerprint. Classification uses a time-domain neural network, the echo state network. Reference strategies, based upon mel-frequency cepstral coefficients, evaluated either over the whole tone or only during the sound onset, provide context to the method. Classification success rates for the neurally-inspired method are around 75%. The cepstral methods perform between 73% and 76%. Further testing with tones from the Iowa MIS collection shows that the neurally inspired method is considerably more robust when tested with data from an unrelated dataset.

show abstract

“…The results obtained with hierarchical classification that improves the score almost to 2% compared to the direct classification.RWC Music Database for musical instrument sound is chosen with isolated notes of instruments. Alicja A. Wieczorkowska, Zbigniew W. Ra´s, Xin Zhang, Rory Lewis [10] done hierarchical classification using Hornbostel-sachs classification and by fifteen different articulation method (blown, bowed, bowed vibrato, concussive, hammered, lip vibrated, muted, muted vibrato, percussive, picked, pizzicato, rubbed, scraped and shaken).Hornbostel-Sachs method gives better result than articulation method. Slim Essid, Ga¨El Richard & Bertrand David [12] selected the feature which has the first rank is selected by Linear Discriminant Analysis (LDA).Analysis and comparison of two hierarchical taxonomies natural instrument families and automatically hierarchical clustering using SVM classifiers are done.…”

Section: Introductionmentioning

confidence: 99%

Musical Instrument Classification using Higher Order Spectra and Hierarchical Taxonomies

Kazi¹,

Bhalke²

2014

IJCA

View full text Add to dashboard Cite

show abstract

Musical instrument identification using Principal Component Analysis and Multi-Layered Perceptrons

Abstract: Abstract

Cited by 11 publications

References 8 publications

Feature Extraction for Traditional Malay Musical Instruments Classification System

Feature Extraction for Traditional Malay Musical Instruments Classification System

A neurally inspired musical instrument classification system based upon the sound onset

Musical Instrument Classification using Higher Order Spectra and Hierarchical Taxonomies

Contact Info

Product

Resources

About