No description available.

Automatický přepis hudby a odhad vícero znějících tónu jsou stále výzvou v oblasti dolování informací z hudby. Moderní systémy jsou založeny na různých technikách strojového učení pro dosažení co nejpřesnějšího přepisu hudby. Některé z nich jsou také omezeny na konkrétní hudební nástroj nebo hudební žánr, aby se snížila rozmanitost analyzovaného zvuku. V této práci je navrženo, vyhodnoceno a porovnáváno několik systémů pro konverzi nahrávek elektrické kytary  do MIDI souború, založených na různých technikách strojového učení a technikách spektrální analýzy.

Considering the rapid increase in the ICT (Information & Communication Technology) products in use, there is a risk of an increase in GHG emissions and electronic waste accumulation in the ICT sector. Therefore, it becomes important to account for the emissions in the ICT sector in order to take steps to mitigate them. There are several methods put forward under ETSI, ITU-T, GHG protocol, etc., which can be used to measure the emissions in the ICT sector. Two such methods are Product Life Cycle Assessment (PLCA) and Spend-based, which are used in this study to account for scope 3, category 1 emissions in the ICT sector. Scope 3, category 1 emissions are released during the raw material acquisition and part production phase of the ICT product’s life cycle and account for a major portion of the overall emissions. As the ICT sector is a very huge field of study in itself, two ICT products, namely smartphones and laptops, are considered in this study to calculate their overall scope 3, category 1 emissions. A list of influential components in smartphones and laptops is defined to be included in the Excel Management Life Cycle Assessment (EMLCA) tool to calculate the scope 3, category 1 emissions. A comprehensive comparison between PLCA and Spend-based methods is also studied during the process of calculating their emissions. These observations are then used to make critical analyses and compare the two methods under results and discussions based on various parameters described under them. Both the methods were found to be suitable for calculating the emissions, with some uncertainty, although the Spend-based method was a quicker approach to do so. The PLCA method, although more complex, was found to be more suitable for ICT product eco-design. Both methods required a different set of primary data and were sensitive to various components in smartphones and laptops. This study illustrates the parameters that affect PLCA and Spend-based methods and discusses the pros and cons of them depending on the situations they are used in.