LEE- Müzik-Doktora
Bu koleksiyon için kalıcı URI
Gözat
Yazar "Özdemir, Taylan" ile LEE- Müzik-Doktora'a göz atma
Sayfa başına sonuç
Sıralama Seçenekleri
-
ÖgeMIXPREP: Machine learning-based multitrack mix preparation assistant(Graduate School, 2022-08-12) Yücel, İsmet Emre ; Özdemir, Taylan ; 409152003 ; MusicMusic production is a general term for describing a set of complicated processes where artistic and technical efforts are involved. Besides the artistic part, the technical side of some parts has regular iterative works. This study focuses on the mix preparation step of the multitrack audio mixing stage in music production by seeking an automatic software solution regarding the intelligent music production paradigm. The structure of the dissertation consists of four components: Theoretical background with fundamental definitions of knowledge both in music production analysis, instrument recognition theories and applications, the approach and explanation of the development of the proposed assistant software, and last but not least, an experiment stage comprising of performance testing with many multitrack projects. Before diving into the development stage, the perspective and the definition of the mix preparation are presented after introducing the music production with a brief historical background. Afterwards, delineation of the intelligent music production research field apart from subjective interests takes part. Instrument recognition literature takes an important part in the conceptualization of the automatic mix preparation solution. Because of that, an extensive historical background in the instrument recognition field is given without getting into redundant theoretical aspects. Apart from that, a reasonable amount of information about the definition of the fundamental concepts of digital audio, audio content analysis and machine learning seemed appropriate to be mentioned since the audience of this research addressed the music technology field. After providing the fundamental theoretical background, the software development approach for the mix preparation assistant is presented. This section explains the software structure by stating the basic requirements of the mix preparation regarding design concerns of the graphical user interface (GUI) consideration for practical usage. The main issues are the GUI layout, software usage, and building a dataset with a related machine learning model. Eventually, a loop-based audio dataset creation approach and ML model are put forward by testing their performance with many audio files from 80 multitrack audio projects in four musical genres (Pop, Rock, Jazz, Electronic/Dance). The experiment is set concerning instrument families provided in the dataset and genre-related performance estimations of each one. The results were interpreted by accentuating the crucial points of implementing the ML-based mix preparation solution. Detailed evaluation results are in the appendices. This study proposes a concept of intelligent mix preparation software by providing a methodology for the design concept and application.
-
ÖgePaying for premium: A critical look into technical audio quality in streaming services(Graduate School, 2024-08-19) Öztürk, Mustafa Kemal ; Özdemir, Taylan ; 409052004 ; MusicThe digital revolution has profoundly reshaped both the production and consumption of music on a global scale. The widespread adoption of mobile music streaming services has facilitated this transformation, offering users a convenient and seemingly boundless access to vast music libraries. These platforms have evolved beyond simply providing music access, offering premium packages that promise not only enhanced audio quality but also a lot of value-added features designed to elevate the user experience. These features include playlist creation capabilities, personalized song recommendations based on individual listening habits, and seamless offline listening functionalities. Moreover, the promise of better sound quality has become a key part of marketing, encouraging users to choose paid subscription models (often called "First Class" or "Premium"), rather than settling for lower audio quality and free-ads users experience. Recent research, however, building upon a foundation of prior studies, has cast doubt on the universality of this perceived distinction on audio quality. The findings suggest that individuals lacking specialized training or access to high-fidelity sound systems may struggle to notice subtle differences in certain audio qualities. Furthermore, the advancement of compression technologies like MPEG, Ogg-vorbis, and AAC has played a crucial role in ensuring a satisfactory listening experience even at lower compression ratios, further blurring the lines between varying sound qualities for the average listener. Given that smartphones and similar devices serve as the primary access point for music streaming for a vast majority of consumers, this discrepancy between promised and delivered audio quality warrants critical examination. Specifically, two key concerns emerge: • Can consumers readily notice deviations from the promised audio quality? • Are music producers and artists subject to any restrictions regarding the upload of low-quality audio files? Therefore, this study undertakes a critical evaluation of the veracity of streaming service providers' claims regarding the audio quality delivered through their premium services. Additionally, it assesses the extent to which music producers and artists can upload low-quality audio files without limitations. By focusing on two of the most prevalent global music streaming services world-wide and two local streaming services from Turkey, this investigation aims to shed light on the validity of these claims and the potential disconnect between promised and actual audio quality delivered to consumers. The findings of this study reveal that the premium options offered by these platforms do not consistently deliver the pledged audio quality, and low-quality audio files can indeed be uploaded without customer notification. Despite this discrepancy, consumers continue to subscribe to paid services, suggesting a potential acceptance or unawareness of the gap between promised and actual audio quality.