Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Automatic legato transcription based on onset detection
KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Tal, musik och hörsel, TMH.
KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Tal, musik och hörsel, TMH.ORCID-id: 0000-0003-2549-6367
DoReMIR Music Research AB.
2023 (engelsk)Inngår i: SMC 2023: Proceedings of the Sound and Music Computing Conference 2023, Sound and Music Computing Network , 2023, s. 214-221Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

This paper focuses on the transcription of performance expression and in particular, legato slurs for solo violin performance. This can be used to improve automatic music transcription and enrich the resulting notations with expression markings. We review past work in expression detection, and find that while legato detection has been explored its transcription has not. We propose a method for demarcating the beginning and ending of slurs in a performance by combining pitch and onset information produced by ScoreCloud (a music notation software with transcription capabilities) with articulated onsets detected by a convolutional neural network. To train this system, we build a dataset of solo bowed violin performance featuring three different musicians playing several exercises and tunes. We test the resulting method on a small collection of recordings of the same excerpt of music performed by five different musicians. We find that this signal-based method works well in cases where the acoustic conditions do not interfere largely with the onset strengths. Further work will explore data augmentation for making the articulation detection more robust, as well as an end-to-end solution. 

sted, utgiver, år, opplag, sider
Sound and Music Computing Network , 2023. s. 214-221
HSV kategori
Identifikatorer
URN: urn:nbn:se:kth:diva-327112Scopus ID: 2-s2.0-85171797881OAI: oai:DiVA.org:kth-327112DiVA, id: diva2:1757910
Konferanse
20th Sound and Music Computing Conference, SMC 2023, Hybrid, Stockholm, Sweden, Jun 15 2023 - Jun 17 2023
Forskningsfinansiär
EU, Horizon 2020, 864189
Merknad

Part of ISBN 9789152773727

QC 20230525

Tilgjengelig fra: 2023-05-19 Laget: 2023-05-19 Sist oppdatert: 2024-01-09bibliografisk kontrollert

Open Access i DiVA

fulltext(1934 kB)212 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 1934 kBChecksum SHA-512
abaeb159b7967b3b4dbfaaf427db553781f0a1b966a8a875aa2c8b98a6135569ca94bd26e6dfb7bca5f6c485f69f1eeaa201f601d048e004387943bf0687b779
Type fulltextMimetype application/pdf

Andre lenker

ScopusConference

Person

Falk, SimonSturm, Bob

Søk i DiVA

Av forfatter/redaktør
Falk, SimonSturm, Bob
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 212 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

urn-nbn

Altmetric

urn-nbn
Totalt: 702 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf