Musical Instrument Classification Using Pre-Trained ModelAuthor : S. Prabavathy, V. Rathikarani and P. Dhanalakshmi
Volume 9 No.1 January-June 2020 pp 45-48
Classify the musical instruments by machine is a challenging task. Musical data classification becomes very popular in research field. A huge manual process required to classify the musical instrument. This proposed system classifies the musical instruments using GoogleNet which is a pretrained network model; SVM and kNN are the two techniques which is used to classify the features. In this paper, to simply musical instruments classifications based on its features which are extracted from various instruments using recent algorithms. The performance of kNN with SVM compares in this proposed work. The musical instruments are identified and its accuracy is computed with the classifiers SVM and kNN, using the SVM with GoogleNet 99% achieve as a high accuracy rate in classifying the musical instruments. In this system sixteen musical instruments used to find the accuracy using SVM and kNN.
GoogleNet, Feature Extraction, k-Nearest Neighborhood (kNN), Musical Instrument Classification (MIC), Support Vector Machine (SVM).
- Panos Photinos, Musical Sound, Instruments and Equipment.
- Anssi Klapuri and Manuel Davy, Signal Processing Methods for Music Transcription.
- Dhanalakshmi , S. Palanivel and V. Ramalingam, “Classification of audio signals using SVM and RBFNN,” Expert Systems with Applications, Vol.36, pp. 6069–6075, 2009.
- IAN KAMINSKYJ and Tadeusz Czaszejko, “Automatic Recognition of Isolated Monophonic Musical Instrument Sounds using kNNC,” Journal of Intelligent Information Systems, Vol. 24, No. 2/3, pp. 199–221, 2005.
- Dhanalakshmi, S. Palanivel and V. Ramalingam , “Classification of audio signals using AANN and GMM,” Applied Soft Computing, Vol. 11, pp. 716–723, 2011.
- Prabavathy, V. Rathikarani and P. Dhanalakshmi, “An Enhanced Musical Instrument Classification using Deep Convolutional Neural Network,” International Journal of Recent Technology and Engineering (IJRTE) ISSN: 2277-3878, Vol.8, No.4, Nov. 2019.
- Pengjie Tang, Hanli Wang and Sam Kwong,” G-MS2F: Google Net based Multi-Stage Feature Fusion of Deep CNN for Scene Recognition,”
- K. Sudha and P. Sujatha, “A Qualitative Analysis of Googlenet and Alexnet for Fabric Defect Detection,” International Journal of Recent Technology and Engineering (IJRTE), ISSN: 2277-3878,” Vol.8, No.1, May 2019.