PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Polyphonic music transcription using dynamic networks
Antonio Pertusa and José Iñesta
Pattern Recognition Letters Volume 26, Number 12, pp. 1809-1818, 2005.

Abstract

The automatic extraction of the notes that were played in a digital musical signal (automatic music transcription) is an open problem. A number of techniques have been applied to solve it without concluding results. The monotimbrical polyphonic version of the problem is posed here: a single instrument is been played and more than one note can sound at the same time. This work tries to approach it through the identification of the spectral pattern of a given instrument. This is achieved using time-delay neural networks that are fed with the spectrogram of a polyphonic music recording of the instrument. The use of a learning scheme based on examples like neural networks permits our system to avoid the use of an auditory model to approach this problem. A number of issues have to be faced to have a robust and powerful system, but promising results using synthesized instruments are presented.

PDF - PASCAL Members only - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Speech
Information Retrieval & Textual Information Access
ID Code:756
Deposited By:José Iñesta
Deposited On:30 December 2004