Automatska notna transkripcija muzičkog zviždanja

undergraduate thesis

• Title (english): Automatic Transcription of Musical Whistling
• Author: Mia Vidaković
• Mentor: Davor Petrinović (mentor)
• Committee member: Davor Petrinović (predsjednik povjerenstva)
• Committee member: Damir Seršić (član povjerenstva)
• Committee member: Juraj Petrović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-06-27, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Automatska notna transkripcija (AMT) postupak je u kojemu se glazbeno djelo iz zvučnog zapisa prebacuje u neki oblik pisane notacije. U ovom radu opisani su osnovni problemi i zadatci notne transkripcije. Predstavljene su neke često korištene metode i pristupi. U praktičnom dijelu radu implementirani su dijelovi jednostavnije transkripcije i klasifikacije muzičkog zviždanja. Pri detekciji visine odzviždanih tonova korištene su dvije metode; autokorelacijska funkcija u vremenskoj domeni (ACF) i... More nalaženje frekvencije najvećeg intenziteta u spektru signala. Nakon postupka izvlačenja značajki iz odzviždane melodije, dobivene informacije zapisuju se u MIDI formatu te se pokušavaju klasificirati u jednu od dostupnih melodija u bazi podataka. Odzviždana melodija uspoređuje se sa svim melodijama iz baze uz dinamičko vremensko poravnanje (DTW). Less

Abstract (english)

Automatic music transcription (AMT) is the process of converting a musical piece from an audio recording into a form of written notation. The goal of this work is to give an insight into fundamental problems and tasks of automatic transcription and to present some commonly used methods and approaches. Simpler components of transcribing and classifying the sound of musical whistling are implemented. Two methods were used for detecting the pitch: time domain autocorrelation function (ACF) and... More identifying the frequency with highest intensity in the spectrum of a given signal. After feature extraction from the whistled melody, the obtained information is recorded in MIDI format and attempts are made to classify it into one of the available melodies in the database. The whistled melody is compared with all the melodies in the database using dynamic time warping (DTW). Less

• Keywords: Automatska notna transkripcija; MIDI standard; detekcija visine tona; autokorelacijska funkcija; dinamičko vremensko poravnavanje
• Keywords (english): Automatic music transcription; MIDI standard; pitch detection; autocorrelation function; dynamic time warping
• Language: croatian
• URN:NBN: urn:nbn:hr:168:624335
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2024-10-12 22:23:53