Essays about: "inspelningar"
Showing result 1 - 5 of 47 essays containing the word inspelningar.
-
1. Approach for frequency response-calibration for microphone arrays
University essay from KTH/Hälsoinformatik och logistikAbstract : Matched frequency responses are a fundamental starting point for a variety ofimplementations for microphone arrays. In this report, two methods for frequencyresponse-calibration of a pre-assembled microphone array are presented andevaluated. READ MORE
-
2. Generation of a metrical grid informed by Deep Learning-based beat estimation in jazz-ensemble recordings
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : This work uses a Deep Learning architecture, specifically a state-of-the-art Temporal Convolutional Network, to track the beat and downbeat positions in jazz-ensemble recordings to derive their metrical grid. This network architecture has been used successfully for general beat tracking purposes. READ MORE
-
3. “I’m only numbers on paper” – A qualitative evaluation of the Internalized Weight Bias Scale in a Swedish sample
University essay from Lunds universitet/Institutionen för psykologiAbstract : Weight-based stigma includes negative stereotypes and negative attitudes directed toward people with obesity or overweight. When internalized, a process also referred to as self-stigmatization, it can have detrimental effects on health. There is currently no instrument to measure internalized weight bias in a Swedish context. READ MORE
-
4. System impact of micro-production
University essay from Lunds universitet/Industriell elektroteknik och automationAbstract : The focus in this thesis has been active power from small scale solar production and what possible impacts an increased proportion of small scale production can have, in a larger context, during short circuit (SC) faults in the grid. The main research question prompting this work was whether active power from small scale solar pro- duction can help support voltages during SC faults, and meet LVRT-requirements in the RfG. READ MORE
-
5. Predicting Disengagement in Short-Term Human-Robot Interactions : A Study in a University Library Setting
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : This report presents a study that investigated the effectiveness of Support Vector Machine (SVM) as a machine learning learning technique for detecting human engagement during short-term interactions with social robots in a library setting. The goal was to build an SVM-based model trained on a dataset of recorded interactions and evaluate its performance in predicting engagement levels. READ MORE