Logo des Repositoriums

Auflistung nach Autor:in "Lukashevich, Hanna"

1 - 3 von 3
  • Konferenzbeitrag
    Automated Classification of Film Scenes based on Film Grammar
    (Workshop Audiovisuelle Medien WAM 2010, 2010) Lanz, Cornelia; Lukashevich, Hanna; Nowak, Stefanie
    Whenever there are extensive data collections to handle, metadata can help to structure and simplify this task. On websites for Video on Demand services or for film recommendations, we often find tags to describe and to search for films. However, manual tagging of films is a time-consuming task with a strong demand for human resources. In this paper, we present an approach for automated classification and indexing of film scenes. Although the classification algorithm uses audiovisual information, we mainly focus on visual information. The conception of the visual features is based on film grammar. In order to cover multiple aspects of film grammar, we enrich the row of state-of-the-art visual features by several novel ones. The evaluation of the classification framework is performed on five categories Suspense, Interaction, Essential Features, Dynamic and Valence. Altogether, the best classification rate equals an accuracy of 83.60% for the classification of the amount of dynamics in film scenes.
  • Textdokument
    Automatic speech/music discrimination for broadcast signals
    (INFORMATIK 2017, 2017) Kruspe, Anna; Zapf, Dominik; Lukashevich, Hanna
    Automatic speech/music discrimination describes the task of automatically detecting speech and music audio within a recording. This is useful for a great number of tasks in both research and industry. In particular, this approach can be used for broadcast signals (e.g. from TV or radio stations) in order to determine the amount of music played. The results can then be used for various reporting purposes (e.g. for royalty collection societies such as the German GEMA). Speech/music discrimination is commonly performed by using machine learning technologies, where models are first trained on manually annotated data, and can then be used to classify previously unseen audio data. In this paper, we give an overview over the applications and the state of the art of speech/music discrimination. Afterwards, we present our approaches based on a set of audio features, Gaussian Mixture Models and Deep Learning. Finally, we give suggestions for the direction of new research into this topic.
  • Textdokument
    Soundslike
    (INFORMATIK 2017, 2017) Grollmisch, Sascha; Lukashevich, Hanna
    A manual indexing of large music libraries is both tedious and costly, that is why a lot of music datasets are incomplete or wrongly annotated. An automatic content-based annotation and recommendation system for music recordings is independent of originally available metadata. It allows for generating an objective metadata that can complement manual expert annotations. These metadata can be effectively used for navigation and search in large music databases of broadcasting stations, streaming services, or online music archives. Automatically determined similar music pieces can serve for user-centered playlist creation and recommendation. In this paper we propose a combined approach to automatic music annotation and similarity search based on musically relevant low-level and mid-level descriptors. First, we use machine learning to infer the high-level metadata categories like genre, emotion, and perceived tempo. These descriptors are then used for similarity search. The similarity criteria can be individually weighted and adapted specifically to specific user requirements and musical facets as rhythm or harmony. The proposed method on music annotation is evaluated on an expert-annotated dataset reaching average accuracies of 60% to 90%, depending on a metadata category. An evaluation for the music recommendation is conducted for different similarity criteria showing good results for rhythm and tempo similarity with precision of 0:51 and 0:71 respectively.