Novel audio features for capturing tempo salience in music recordings

Abstract

In music compositions, certain parts may be played in an improvisational style with a rather vague notion of tempo, while other parts are characterized by having a clearly perceivable tempo. Based on this observation, we introduce in this paper some novel audio features for capturing tempo-related information. Rather than measuring the specific tempo of a local section of a given recording, our objective is to capture the existence or absence of a notion of tempo, a kind of tempo salience. By a quantitative analysis within an Indian music scenario, we demonstrate that our audio features capture the aspect of tempo salience well, while being independent of continuous fluctuations and local changes in tempo

Structural Segmentation of Alap in Dhrupad Vocal Concerts

“…Reviewing structural segmentation in the context of Indian art music, Ranjani and Sreenivas (2013) carried out a hierarchical classification of concert sections in the South Indian genre of Carnatic music based on rhythmicity and percussiveness, strongly signaled by the onsets and low frequency content of the accompanying percussion instrument. Thoshkahna et al (2015) exploited the salience of the estimated tempo to distinguish sections with ambiguous tempo (alapana) from the later concerts sections with clear rhythmic properties in Carnatic music concerts. Rhythmic analysis of Indian and Turkish music was explored by Srinivasamurthy et al (2014), where beat tracking, meter estimation and downbeat detection were identified as musically relevant tasks that could benefit from computational methods.…”

Tracking metrical structure changes with sparse-NMF

“…In this paper we propose an unsupervised method for the detection of metric modulations within a music piece. We formulate the task as a metrical structure based segmentation This work is supported by the EPSRC award 1325200 and the AHRC Grant AH/L006820/1 retrieval problem [7]. We restrict this study to abrupt modulations from one section of stable metrical structure to another section with a different but still stable metrical structure.…”

Tempo estimation via self-supervised learning

“…Tempograms can also be the first step to more complex mid-level representations, such as the tempo salience map (Thoshkahna et al, 2015), rhythmic salience map (Quinton et al, 2016). Tian et al (2015) uses tempogram-based features, such as Tempogram Principal Component Analysis (TPCA), Tempogram Cepstral Coefficients (TCC), Tempo Intensity (TI) and Tempo Intensity Ratio (TIR) in order to perform music structural segmentation.…”

“…As shown in Thoshkahna et al (2015), cyclic tempogram features can be used as the foundation to understand if a part of a song has or not a salient tempo, i.e. whether that part has a clear rhythm or a vague tempo.…”