Show simple item record

dc.contributor.authorSchramm, Ren_US
dc.contributor.authorBenetos, Een_US
dc.contributor.author2017 AES International Conference on Semantic Audioen_US
dc.date.accessioned2017-04-12T13:22:20Z
dc.date.available2017-03-22en_US
dc.date.issued2017-06-22en_US
dc.date.submitted2017-04-07T10:00:50.632Z
dc.identifier.urihttp://qmro.qmul.ac.uk/xmlui/handle/123456789/22496
dc.description.abstractThis work presents a spectrogram factorisation method applied to automatic music transcription of a cappella performances with multiple singers. A variable-Q transform representation of the audio spectrogram is factorised with the help of a 6-dimensional sparse dictionary which contains spectral templates of vowel vocalizations. A post-processing step is proposed to remove false positive pitch detections through a binary classifier, where overtone-based features are used as input into this step. Preliminary experiments have shown promising multi-pitch detection results when applied to audio recordings of Bach Chorales and Barbershop music. Comparisons made with alternative methods have shown that our approach increases the number of true positive pitch detections while the post-processing step keeps the number of false positives lower than those measured in comparative approaches.en_US
dc.format.extent? - ? (8)en_US
dc.publisherAudio Engineering Societyen_US
dc.titleAutomatic Transcription of a Cappella Recordings from Multiple Singersen_US
dc.typeConference Proceeding
dc.rights.holder© 2017 Audio Engineering Society
dc.identifier.doi10.17743/aesconf.2017.978-1-942220-15-2en_US
pubs.author-urlhttp://professor.ufrgs.br/rschrammen_US
pubs.notesNot knownen_US
pubs.publication-statusPublisheden_US
pubs.publisher-urlhttp://www.aes.org/conferences/2017/semantic/en_US
dcterms.dateAccepted2017-03-22en_US
qmul.funderA Machine Learning Framework for Audio Analysis and Retrieval::Royal Academy of Engineeringen_US
qmul.funderA Machine Learning Framework for Audio Analysis and Retrieval::Royal Academy of Engineeringen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record