Počet záznamů: 1
Improvements of Continuous Model for Memory-based Automatic Music Transcription
- 1.
SYSNO ASEP 0347257 Druh ASEP C - Konferenční příspěvek (mezinárodní konf.) Zařazení RIV D - Článek ve sborníku Název Improvements of Continuous Model for Memory-based Automatic Music Transcription Tvůrce(i) Albrecht, Š. (CZ)
Šmídl, Václav (UTIA-B) RIDZdroj.dok. Proceedings of the 18th European signal processing conference. - Aalborg : Eurasip, 2010 - ISSN 2076-1465 Rozsah stran s. 487-491 Poč.str. 5 s. Forma vydání www - www Akce European signal processing conference Datum konání 23.07.2010-27.07.2010 Místo konání Aalborg Země DK - Dánsko Typ akce WRD Jazyk dok. eng - angličtina Země vyd. DK - Dánsko Klíč. slova music transcription ; extended Kalman filter Vědní obor RIV BD - Teorie informace CEP GP102/08/P250 GA ČR - Grantová agentura ČR CEZ AV0Z10750506 - UTIA-B (2005-2011) Anotace Automatic music transcription is a process recovering the most likely combination of sounds that produced the recorded audio signal. We are concerned with memory-based approach, where the observed signal is modeled as a superposition of sounds from a library. Moreover, we assume that only parts of the sounds can be played. The number of possible combinations is excessive and exact estimation is computationally prohibitive. We propose to transform the original discrete-event model into a less restricted parametrization and impose the constraints in a soft way via prior information. The resulting model is a non-linear state-space model with Gaussian disturbances. The posterior estimates are evaluated by the extended Kalman filter. Performance of the model is studied in simulation and it is shown that it outperforms previously published methods. Pracoviště Ústav teorie informace a automatizace Kontakt Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Rok sběru 2011
Počet záznamů: 1