An adaptive penalty approach to multi-pitch estimation

Ted Kronvall, Filip Elvander, Stefan Ingi Adalbjörnsson, Andreas Jakobsson

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference article in proceedingsScientificvertaisarvioitu

Abstrakti

This work treats multi-pitch estimation, and in particular the common misclassification issue wherein the pitch at half of the true fundamental frequency, here referred to as a suboctave, is chosen instead of the true pitch. Extending on current methods which use an extension of the Group LASSO for pitch estimation, this work introduces an adaptive total variation penalty, which both enforce group- and block sparsity, and deal with errors due to sub-octaves. The method is shown to outperform current state-of-the-art sparse methods, where the model orders are unknown, while also requiring fewer tuning parameters than these. The method is also shown to outperform several conventional pitch estimation methods, even when these are virtued with oracle model orders.
AlkuperäiskieliEnglanti
Otsikko2015 23rd European Signal Processing Conference (EUSIPCO)
KustantajaIEEE
Sivut31-35
Sivumäärä5
ISBN (painettu)978-0-9928-6263-3
DOI - pysyväislinkit
TilaJulkaistu - 4 syysk. 2015
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaEuropean Signal Processing Conference - Nice, Ranska
Kesto: 31 elok. 20154 syysk. 2015
Konferenssinumero: 23

Julkaisusarja

NimiEuropean Signal Processing Conference
ISSN (painettu)2219-5491
ISSN (elektroninen)2076-1465

Conference

ConferenceEuropean Signal Processing Conference
LyhennettäEUSIPCO
Maa/AlueRanska
KaupunkiNice
Ajanjakso31/08/201504/09/2015

Sormenjälki

Sukella tutkimusaiheisiin 'An adaptive penalty approach to multi-pitch estimation'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä