Content-based organization and visualization of music archives

Pampalk, Elias; Rauber, Andreas; Merkl, Dieter

doi:10.1145/641118.641121

Cited by 68 publications

(104 citation statements)

References 0 publications

Supporting

Mentioning

100

Contrasting

Unclassified

Order By: Relevance

“…In Pampalk et al (2003a) a histogram indicates how many times one of 50 loudness levels was reached or exceeded in each of 20 frequency bands. The fluctuation patterns (FP) (Pampalk et al 2002) measure the magnitude of the modulation energy in 60 frequency bins in time series of 23 frequency bands (see Fig. 5a).…”

Section: Long-term Featuresmentioning

confidence: 99%

“…Unsupervised classification can be used to group (or cluster) pieces of music together, for example by similarity of their timbre. The distribution of features like timbre over a collection of music can be used to categorize (Tzanetakis and Cook 2002), visualize (Pampalk et al 2002;Mörchen et al 2005a), and recommend (Stenzel and Kamps 2005) music. Audio features suggested to characterize the content of music pieces are discussed in Sect.…”

Section: Introductionmentioning

confidence: 99%

“…Visualization of music collection with Emergent Self-Organizing map PCA is used inTzanetakis et al (2002a) to compress audio feature vectors to 3D displays Pampalk et al (2002). use small SOM trained with song-level features and a density visualization in order to search for possible clusters of songs.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Classification in music research

Weihs

Ligges

Mörchen

et al. 2007

ADAC

View full text Add to dashboard Cite

Since a few years, classification in music research is a very broad and quickly growing field. Most important for adequate classification is the knowledge of adequate observable or deduced features on the basis of which meaningful groups or classes can be distinguished. Unsupervised classification additionally needs an adequate similarity or distance measure grouping is to be based upon. Evaluation of supervised learning is typically based on the error rates of the classification rules. In this paper we first discuss typical problems and possible influential features derived from signal analysis, mental mechanisms or concepts, and compositional structure. Then, we present typical solutions of such tasks related to music research, namely for organization of music collections, transcription of music signals, cognitive psychology of music, and compositional structure analysis.

show abstract

Section: Long-term Featuresmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Classification in music research

Weihs

Ligges

Mörchen

et al. 2007

ADAC

View full text Add to dashboard Cite

show abstract

“…The signal power and spectrogram are used in [37,38] to develop characteristic sequences. The psycho-acoustic perception of rhythm patterns is used in [39] to develop self-organizing maps of the audio pieces. In [40], audio features are extracted from audio compressed by the MPEG audio compression algorithm, which is based on a psycho-acoustic model, and the audio features are then processed by a fuzzy logic based clustering algorithm to identify the similar audio pieces.…”

Section: Related Workmentioning

confidence: 99%

Identifying the classical music composition of an unknown performance with wavelet dispersion vector and neural nets☆

Rein

Reisslein

2006

Information Sciences

View full text Add to dashboard Cite

“…Self organizing map based mappings of songs provide an intuitive method for exploring music databases (Rauber and Frühwirth, 2001). The use of appealing visualizations (Pampalk, 2001) reduces the barrier of exploring new regions in unknown music databases.…”

Section: Introductionmentioning

confidence: 99%