Evolutionary Algorithm for Generation of Air Pressure and Lip Pressure Parameters for Automated Performance of Brass Instruments

منو

" Evolutionary Algorithm for Generation of Air Pressure and Lip Pressure Parameters for Automated Performance of Brass Instruments "

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	149849
Doc. No	:	ET21641
Main Entry	:	James A. Bilitski
Title Proper	:	Evolutionary Algorithm for Generation of Air Pressure and Lip Pressure Parameters for Automated Performance of Brass Instruments
Note	:	This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract	:	The artificial mouth is a robotic device that simulates a human mouth. It consistsof moveable lips and an adjustable air supply. The uses of an artificial mouth includeresearch for physical modeling of the lips and automatic performance. Automaticperformance of a musical instrument is when an instrument is played without the directinteraction of a human. Typically mechanics and robotics are used instead of a human.In this study the use of a genetic algorithm to compute air pressure and lip pressurevalues so that the artificial mouth can correctly play five notes on a brass instrument isinvestigated. In order to properly play a brass instrument, a player must apply propertension between the lips and apply proper airflow so that the lips vibrate at the properfrequency. A player changes the notes on a brass instrument by depressing keys andchanging lip pressure and air flow. This study investigated a machine learning approachto finding lip pressure and air pressure parameters so that an artificial mouth could playfive notes of a scale on a trumpet. A fast search algorithm was needed because it takesabout 4 seconds to measure the frequency produced by each combination of pressureparameters. This measurement is slow because of the slow moving mechanics of thesystem and a delay produced while the notes are measured for pitch. Two differentmouthpieces were used to investigate the ability to adapt to different mouthpieces. Thealgorithm started with a randomly generated population and evolved the lip pressure andair pressure parameters with an evolutionary algorithm using crossover and mutationdesigned for the knowledge scheme in this application. The efficiency of this algorithmwas compared to an exhaustive search. Experimentation was performed using variouscombinations of genetic parameters including population..tested for theQ1 PC1 bus cardBoth these projects mere sofixare des elopment efforts tonards contributing to dlfferentaspects of Roboucs and lZ1echatronics projects m the Controls and Roboucs Group..
Subject	:	Electericl tess
	:	برق
electronic file name	:	TL44818.pdf
Title and statement of responsibility and	:	Evolutionary Algorithm for Generation of Air Pressure and Lip Pressure Parameters for Automated Performance of Brass Instruments [Thesis]