Zobrazeno 1 - 10
of 310
pro vyhledávání: '"TJ Tsai"'
Publikováno v:
Transactions of the International Society for Music Information Retrieval, Vol 7, Iss 1, Pp 159-178 (2024)
This article motivates, describes, and presents the PBSCR dataset for studying composer recognition of classical piano music. Our goal was to design a dataset that facilitates large-scale research on composer recognition that is suitable for modern a
Externí odkaz:
https://doaj.org/article/0787eef3e34546b79622f24a9775ec00
Publikováno v:
Algorithms, Vol 15, Iss 5, p 146 (2022)
This paper studies the problem of identifying piano music in various modalities using a single, unified approach called marketplace fingerprinting. The key defining characteristic of marketplace fingerprinting is choice: we consider a broad range of
Externí odkaz:
https://doaj.org/article/cd1e698ad8a94ac5835a826c31d24b0e
Publikováno v:
Applied Sciences, Vol 11, Iss 4, p 1387 (2021)
This article studies a composer style classification task based on raw sheet music images. While previous works on composer recognition have relied exclusively on supervised learning, we explore the use of self-supervised pretraining methods that hav
Externí odkaz:
https://doaj.org/article/0c61fe7ed759493eb5581fb91732ada7
Autor:
TJ Tsai
Publikováno v:
ICASSP
In this work we explore parallelizable alternatives to DTW for globally aligning two feature sequences. One of the main practical limitations of DTW is its quadratic computation and memory cost. Previous works have sought to reduce the computational
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::33b0b76a7ea07d73ed9e08874436136c
https://doi.org/10.1109/icassp39728.2021.9413827
https://doi.org/10.1109/icassp39728.2021.9413827
Publikováno v:
ICASSP
This paper studies instrument classification of solo sheet music. Whereas previous work has focused on instrument recognition in audio data, we instead approach the instrument classification problem using raw sheet music images. Our approach first co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::587ea32619ac88dcae21089c4f24600b
https://doi.org/10.1109/icassp39728.2021.9413732
https://doi.org/10.1109/icassp39728.2021.9413732
Autor:
TJ Tsai
Publikováno v:
ICASSP
This paper investigates the problem of matching a MIDI file against a large database of piano sheet music images. Previous sheet-audio and sheet-MIDI alignment approaches have primarily focused on a 1-to-1 alignment task, which is not a scalable solu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::82b349478ac0d8029f5db7805e8e33e5
https://doi.org/10.1109/icassp40776.2020.9053815
https://doi.org/10.1109/icassp40776.2020.9053815
This article investigates a cross-modal retrieval problem in which a user would like to retrieve a passage of music from a MIDI file by taking a cell phone picture of several lines of sheet music. This problem is challenging for two reasons: it has a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fa1e76dc45d5fede131394e3d3d3690f
Publikováno v:
Applied Sciences
Volume 11
Issue 4
Applied Sciences, Vol 11, Iss 1387, p 1387 (2021)
Volume 11
Issue 4
Applied Sciences, Vol 11, Iss 1387, p 1387 (2021)
This article studies a composer style classification task based on raw sheet music images. While previous works on composer recognition have relied exclusively on supervised learning, we explore the use of self-supervised pretraining methods that hav
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::02ca0eac3114154b4bb721b28ca371cc
https://doi.org/10.3390/app11041387
https://doi.org/10.3390/app11041387
Autor:
Nancy K. Lape, Angie Lee, Albert Dato, Roberta M. Ewart, Christopher M. Clark, TJ Tsai, Lori Bassman, Elizabeth J. Orwin, Matthew Spencer, Erik Spjut, Joseph Betser, Laura Palucki-Blake
Publikováno v:
AIAA SPACE and Astronautics Forum and Exposition.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b6236bb4fa157118f851e1c6d21721b1
https://doi.org/10.2514/6.2017-5175
https://doi.org/10.2514/6.2017-5175
The goal of live song identification is to allow concertgoers to identify a live performance by recording a few seconds of the performance on their cell phone. This paper proposes a multistep approach to address this problem for popular bands. In the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2a555beb8b9171101d48a35802d854ec
https://publica.fraunhofer.de/handle/publica/262735
https://publica.fraunhofer.de/handle/publica/262735