DocumentCode :
2054625
Title :
Semi-supervised learning for musical instrument recognition
Author :
Diment, Aleksandr ; Heittola, Toni ; Virtanen, Tuomas
Author_Institution :
Dept. of Signal Process., Tampere Univ. of Technol., Tampere, Finland
fYear :
2013
fDate :
9-13 Sept. 2013
Firstpage :
1
Lastpage :
5
Abstract :
In this work, the semi-supervised learning (SSL) techniques are explored in the context of musical instrument recognition. The conventional supervised approaches normally rely on annotated data to train the classifier. This implies performing costly manual annotations of the training data. The SSL methods enable utilising the additional unannotated data, which is significantly easier to obtain, allowing the overall development cost maintained at the same level while notably improving the performance. The implemented classifier incorporates the Gaussian mixture model-based SSL scheme utilising the iterative EM-based algorithm, as well as the extensions facilitating a simpler convergence criteria. The evaluation is performed on a set of nine instruments while training on a dataset, in which the relative size of the labelled data is as little as 15%. It yields a noteworthy absolute performance gain of 16% compared to the performance of the initial supervised models.
Keywords :
Gaussian processes; audio signal processing; expectation-maximisation algorithm; information retrieval; iterative methods; learning (artificial intelligence); musical instruments; pattern classification; Gaussian mixture model-based SSL scheme; iterative EM-based algorithm; music information retrieval; musical instrument recognition; semi-supervised learning techniques; Accuracy; Convergence; Feature extraction; Instruments; Music; Semisupervised learning; Training; Music information retrieval; musical instrument recognition; semi-supervised learning;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing Conference (EUSIPCO), 2013 Proceedings of the 21st European
Conference_Location :
Marrakech
Type :
conf
Filename :
6811483
Link To Document :
بازگشت