Hanna Lukashevich

Hanna Lukashevich

Auto-generated profile, based on publicly available information

Hanna Lukashevich

Fraunhofer IDMT

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 July 2012 in Journal of New Music Research
Verified
Journal Article
Closed access
JAJakob Abesser
Jakob Abesser
HLHanna Lukashevich
Hanna Lukashevich
PBPaul Bräuer
Paul Bräuer
In this paper, we present a comparative study of three different classification paradigms for genre classification based on repetitive basslines. In spite of a large variety in terms of instrumentation, a bass instrument can be found in most music genres. Thus, the bass track can be analysed to explore stylistic similarities between music genres. We present an extensive set of transcription-based high-level features related to rhythm and tonality that allows one to characterize basslines on a symbolic level. Traditional classification techniques based on pattern recognition techniques and audio features are compared with rule-based classification and classification based on the similarity between basslines. We use a novel dataset that consists of typical basslines of 13 music genres from different cultural backgrounds for evaluation purposes. Finally, the genre confusion results obtained in the experiments are examined by musicologists. Our study shows that several known stylistic relationships between music genres could be verified that way by classifying typical basslines. We could achieve a highest accuracy value of 64.8% for the genre classification solely based on repetitive basslines of a song.




30 August 2023
Verified
Conference Paper
Open access
HLHanna Lukashevich
Hanna Lukashevich
SGSascha Grollmisch
Sascha Grollmisch
JAJakob Abesser
Jakob Abesser
SSSebastian Stober
Sebastian Stober
JBJoachim Bös
Joachim Bös
Music classification algorithms use signal processing and machine learning approaches to extract and enrich metadata for audio recordings in music archives. Common tasks include music genre classification, where each song is assigned a single label (such as Rock, Pop, or Jazz), and musical instrument classification. Since music metadata can be ambiguous, classification algorithms cannot always achieve fully accurate predictions. Therefore, our focus extends beyond the correctly estimated class labels to include realistic confidence values for each potential genre or instrument label. In practice, many state-of-the-art classification algorithms based on deep neural networks exhibit overconfident predictions, complicating the interpretation of the final output values. In this work, we examine whether the issue of overconfident predictions and, consequently, non-representative confidence values is also relevant to music genre classification and musical instrument classification. Moreover, we describe techniques to mitigate this behavior and assess the impact of deep ensembles and temperature scaling in generating more realistic confidence outputs, which can be directly employed in real-world music tagging applications.