Abstract

VELAZQUEZ LOPEZ, Omar; OROPEZA RODRIGUEZ, José Luis  and  SUAREZ GUERRA, Sergio. Application of Auditory Filter-Banks in Polyphonic Music Transcription. Comp. y Sist. [online]. 2022, vol.26, n.4, pp.1421-1428.  Epub Mar 17, 2023. ISSN 2007-9737.  https://doi.org/10.13053/cys-26-4-4271.

In this paper we present a frame-level transcription system for polyphonic piano music by using nonnegative matrix factorization (NMF) technique based on Fourier spectrogram as the representation of the musical signal and enhanced by application of an auditory filter-bank based on a new cochlear frequency-position equation, which was developed solving a biomechanical cochlea model without the need of physiological or psychoacoustic experiments. It is important to mention that in our days in music transcription task, a set of auditory bank filters have been used and this paper is focused precisely in this search field. Evaluation using a set of polyphonic piano pieces is performed against the system itself when it does not use filtered spectrograms and also against another system in the state-of-the-art, in both cases it is showed that the proposed method in this paper achieves an increment in precision measure.

Keywords : Automatic music transcription; auditory filter-bank; nonnegative matrix factorization.

        · text in English     · English ( pdf )