BEGIN:VCALENDAR
PRODID:-//eluceo/ical//2.0/EN
VERSION:2.0
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:cf9d8185c417ca73eca12e1af5480fe8
DTSTAMP:20260520T214315Z
SUMMARY:CS BSc Thesis Presentation 6 May 2026
DESCRIPTION:Kontakt: birger.swahn@cs.lth.se\n\nWednesday\, 6 May there will
  be a bachelor thesis presentation in Computer Science at Lund University\
 , Faculty of Engineering.The presentation will take place in E:2405 (Glasb
 uren).Note to potential opponents: Register as an opponent to the presenta
 tion of your choice by sending an email to the examiner for that presentat
 ion (firstname.lastname@cs.lth.se). Do not forget to specify the presentat
 ion you register for! Note that the number of opponents may be limited (of
 ten to two)\, so you might be forced to choose another presentation if you
  register too late. Registrations are individual\, just as the oppositions
  are! More instructions for opponents are found here on the LTH thesis pro
 ject page.13:15-14:00 in E:2405 (Glasburen)Presenters: Ross Ottosson\, Lud
 vig Ölund DanielssonTitle: Automatiserad tabulaturgenerering: Förbättra
 d träffsäkerhet genom domänspecifik filtrering och Viterbi-optimeringEx
 aminer: Mattias NordahlSupervisor: Ester Daniel Ytterbrink (LTH)Automatic 
 Music Transcription (AMT) of the guitar is a significant challenge due to 
 the instrument's acoustic complexity\, including overtones\, sympathetic r
 esonance\, and mechanical transients. This study investigates how a genera
 l-purpose AMT model (Spotify’s Basic Pitch) can be adapted to generate p
 hysically playable guitar tablature. By lowering the model's minimum note 
 length threshold to 40 ms\, fast musical passages are successfully capture
 d\, but this results in a "shotgun effect" of massive over-detection.&nbsp
 \;To mitigate this\, a domain-specific filtering pipeline was developed an
 d optimized based on the physical and acoustic properties of the guitar. T
 he purified MIDI data was subsequently processed using a Viterbi algorithm
  to calculate biomechanically ergonomic fingerings. Results indicate that 
 the customized pipeline outperforms standard Basic Pitch by increasing pre
 cision and F1 scores. Furthermore\, the filtering significantly reduced th
 e Viterbi algorithm’s crash rate from 11.13% to under 1% by eliminating 
 physically impossible note combinations.&nbsp\;\n\nMer information om hän
 delsen: https://www.cs.lth.se/evenemang/cs-bsc-thesis-presentation-6-may-2
 026
DTSTART;TZID=GMT:20260506T111500
DTEND;TZID=GMT:20260506T120000
LOCATION:E:2405 (Glasburen)
END:VEVENT
END:VCALENDAR