Pitch-Dependent Musical Instrument Identification and Its Application to Musical Sound Ontology

Abstract

To augment communication channels of human-computer interaction, various kinds of sound recognition are required. In particular, musical instrument indentification is one of the primitive functions in obtaining auditory information. The pitch dependency of timbres has not been fully exploited in musical instrument identification. In this paper, we present a method using an F0-dependent multivariate. normal distribution of which mean is represented by a cubic polynomial of fundamental frequency (F0). This F0-dependent mean function represents the pitch dependency of each feature, while the F0-normalized covariance represents its non-pitch dependency. Musical instrument sounds are first analyzed by the F0-dependent multivariate normal distribution, and then identified by using the discriminant function based on the Bayes decision rule. Experimental results of identifying 6,247 solo tones of 19 musical instruments by 10-fold cross validation showed that the proposed method improved the recognition rate at individual-instrument level from 75.73% to 79.73%, and the recognition rate at category level from 88.20% to 90.65%. Based on these results, systematic generation of musical sound ontology is investigated by using the C5.0 decision tree program.

This research was partially supported by the Ministry of Education, Culture, Sports, Science and Technology, Grant-in-Aid for Scientific Research (B), No.12480090, and Informatics Research Center for Development of Knowledge Society Infrastructure (COE program of MEXT, Japan)