Mining Melodic Patterns in Large Audio Collections of Indian Art Music

Abstract

Discovery of repeating structures in music is fundamental to its analysis, understanding and interpretation. We present a data-driven approach for the discovery of shorttime melodic patterns in large collections of Indian art music. The approach first discovers melodic patterns within an audio recording and subsequently searches for their repetitions in the entire music collection. We compute similarity between melodic patterns using dynamic time warping (DTW). Furthermore, we investigate four different variants of the DTW cost function for rank refinement of the obtained results. The music collection used in this study comprises 1,764 audio recordings with a total duration of 365 hours. Over 13 trillion DTW distance computations are done for the entire dataset. Due to the computational complexity of the task, different lower bounding and early abandoning techniques are applied during DTW distance computation. An evaluation based on expert feedback on a subset of the dataset shows that the discovered melodic patterns are musically relevant. Several musically interesting relationships are discovered, yielding further scope for establishing novel similarity measures based on melodic patterns. The discovered melodic patterns can further be used in challenging computational tasks such as automatic rāga recognition, composition identification and music recommendation Keywords-Motifs, Pattern discovery, Time series, Melodic analysis, Indian art music 1 Compare results across datasets: http://www.music-ir.org/mirex/wiki/ 2013:MIREX2013 Results

Phrase-based rĀga recognition using vector space modeling

“…In order to get a reliable input for our approach, we employ the IAM pattern discovery system we presented in [19]. This is one of the few unsupervised systems we are aware of that can discover meaningful melodic patterns in large-scale collections of IAM.…”

“…We use the same parameter settings and implementation as reported in the paper. For a detailed explanation of this approach we refer to [19]. All these discovered phrases are made available online 1 for listening.…”

“…For that, we use our earlier work on unsupervised discovery of melodic patterns in IAM [19]. We select relevant melodic phrases from the discovered patterns employing topic modeling techniques used in text classification.…”

Klasik Türk müziğinde makam tanıma için veri madenciliği kullanımı

“…Gulati vd. [9] proje kapsamında Hint Müziği ile ilgili çalışmalar yürütmektedir. Dünya, CompMusic projesinin bir protipidir [10].…”

Discovering rāga motifs by characterizing communities in networks of melodic patterns

“…The lack of melody segmentation models and the large duration of audio recordings further complicate this task. As a result, existing research on this topic within IAM is primarily focused on computing robust melodic representations and similarity measures [5][6][7][8][9][10][11]. Descriptive music scores and a reliable melody transcription system are practically non-existent for IAM.…”