We propose a discriminative model for polyphonic piano transcription. Spectral features are obtained individually for each note. To solve the overlapping partial problem, we apply spectral separation by estimating the spectral envelope for each note. For classifying purposes, support vector machines (SVM) are trained on the spectral energy inferred from these spectral features. We apply a scheme of one-versus-all (OVA) SVM classifiers to discriminate frame-level note instances. To decrease the high frequency notes residual energy due to the downward notes shared partials, a method to cancel the interferences from the downward notes to the upward notes has been developed. The classifier output is filtered with a hidden Markov model. Our approach has been tested with synthesized and real piano recordings obtaining very promising results.
Authors:
Canadas-Quesada, Francisco Jesus; Carabias-Orti, Julio Jose; Mata-Campos, Raul; Ruiz-Reyes, Nicolas; Vera-Candeas, Pedro
Affiliation:
University of Jaen
AES Convention:
124 (May 2008)
Paper Number:
7384
Publication Date:
May 1, 2008
Subject:
Analysis and Synthesis of Sound
Click to purchase paper as a non-member or you can login as an AES member to see more options.
No AES members have commented on this paper yet.
To be notified of new comments on this paper you can subscribe to this RSS feed. Forum users should login to see additional options.
If you are not yet an AES member and have something important to say about this paper then we urge you to join the AES today and make your voice heard. You can join online today by clicking here.