A set of features is evaluated for recognition of musical instruments out of monophonic musical signals. Aiming to achieve a compact representation, the adopted features regard only spectral characteristics of sound and are limited in number. On top of these descriptors, various classification methods are implemented and tested. Over a dataset of 1007 tones from 27 musical instruments, support vector machines and quadratic discriminant analysis show comparable results with success rates close to 70% of successful classifications. Canonical discriminant analysis never had momentous results, while nearest neighbours performed on average among the employed classifiers. Strings have been the most misclassified instrument family, while very satisfactory results have been obtained with brass and woodwinds. The most relevant features are demonstrated to be the inharmonicity, the spectral centroid, and the energy contained in the first partial

A set of features is evaluated for recognition of musical instruments out of monophonic musical signals. Aiming to achieve a compact representation, the adopted features regard only spectral characteristics of sound and are limited in number. On top of these descriptors, various classification methods are implemented and tested. Over a dataset of 1007 tones from 27 musical instruments, support vector machines and quadratic discriminant analysis show comparable results with success rates close to 70% of successful classifications. Canonical discriminant analysis never had momentous results, while nearest neighbours performed on average among the employed classifiers. Strings have been the most misclassified instrument family, while very satisfactory results have been obtained with brass and woodwinds. The most relevant features are demonstrated to be the inharmonicity, the spectral centroid, and the energy contained in the first partial.

No abstract

The growth of digital music databases imposes new content-based methods of interfacing with stored data; although indexing and retrieval techniques are deeply investigated, an integrated view of querying mechanism has never been established before. Moreover, the multimodal nature of music should be exploited to match the users' expectations as well as their skills. In this paper, we propose a hierarchy of music-interfaces that is suitable for existent prototypes of music information retrieval systems; according to this framework, human/computer interaction should be improved by singing, playing or notating music. Dealing with multiple inputs poses many challenging problems for both their combination and the low-level translation needed to transform an acoustic signal into a symbolic representation. This paper addresses the latter problem in some details, aiming to develop music-interfaces available not only to trained-musician.