Musical instrument recognition using ICA-based transform of features and discriminatively trained HMMs
- 1 January 2003
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 133-136 vol.2
- https://doi.org/10.1109/isspa.2003.1224833
Abstract
In this paper, we describe a system for the recognition of musical instruments from isolated notes or drum samples. We first describe a baseline system that uses mel-frequency cepstral coefficients and their first derivatives as features, and continuous-density hidden Markov models (HMMs). Two improvements are proposed to increase the performance of this baseline system. First, transforming the features to a base with maximal statistical independence using independent component analysis can give an improvement of 9 percentage points in recognition accuracy. Secondly, discriminative training is shown to further improve the recognition accuracy of the system. The evaluation material consists of 5895 isolated notes of Western orchestral instruments, and 1798 drum hits.Keywords
This publication has 7 references indexed in Scilit:
- A Discriminative Training Algorithm for Hidden Markov ModelsIEEE Transactions on Speech and Audio Processing, 2004
- Comparison of features for musical instrument recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Fast Independent Component Analysis in Kernel Feature SpacesLecture Notes in Computer Science, 2001
- General sound classification and similarity in MPEG-7Organised Sound, 2001
- Feature dependence in the automatic identification of musical woodwind instrumentsThe Journal of the Acoustical Society of America, 2001
- Independent component analysis applied to feature extraction for robust automatic speech recognitionElectronics Letters, 2000
- Fast and robust fixed-point algorithms for independent component analysisIEEE Transactions on Neural Networks, 1999