Motif Spotting in an Alapana in Carnatic Music

@inproceedings{Ishwar2013MotifSI,
  title={Motif Spotting in an Alapana in Carnatic Music},
  author={Vignesh Ishwar and Shrey Dutta and Ashwin Bellur and Hema A. Murthy},
  booktitle={ISMIR},
  year={2013}
}
This work addresses the problem of melodic motif spotting, given a query, in Carnatic music. [] Key Method In the first pass, the rough longest common subsequence (RLCS) matching is performed between the saddle points of the pitch contours of the reference motif and the musical piece. These saddle points corresponding to quasi-stationary points of the motifs, are relevant entities of the raga. Multiple sequences are identified in this step, not all of which correspond to the the motif that is queried.

Figures and Tables from this paper

A modified rough longest common subsequence algorithm for motif spotting in an Alapana of Carnatic Music

  • S. DuttaH. Murthy
  • Computer Science
    2014 Twentieth National Conference on Communications (NCC)
  • 2014
The modified RLCS algorithm reduces the number of false alarms from 130 to 94 and also performs better localization of motifs and the motifs that are chosen are also long compared to earlier work.

Classification of Melodic Motifs in Raga Music with Time-series Matching

In this work, machine learning methods are used on labelled databases of Hindustani and Carnatic vocal audio concerts to obtain phrase classification on manually segmented audio using Dynamic time warping and HMM based classification on time series of detected pitch values used for the melodic representation of a phrase.

Discovering Typical Motifs of a Raga from One-Liners of Songs in Carnatic Music

Taking lines corresponding to one or more cycles of the pallavi, anupallavi and charanam as one-liner, one-liners across different songs are compared using a dynamic programming based algorithm.

A Statistical Analysis of Gamakas in Carnatic Music

This paper draws upon the two-component model of Carnatic Music, which splits it into a slowly varying ‘stage’ and a detail, called ‘dance’, and proposes slightly altered definitions of two similar components called constant-pitch notes and transients.

Discovering rāga motifs by characterizing communities in networks of melodic patterns

This work extracts melodic patterns from a collection of 44 hours of audio comprising 160 recordings belonging to 10 ra̅gas, characterize these patterns by performing a network analysis, detecting non-overlapping communities, and exploiting the topological properties of the network to determine a similarity threshold.

Computational Study of Ornaments in Hindustani Music

The hidden musical patterns and structures in Indian music which are fundamental in unfolding of a raga are discovered, and recognition of these patterns can further help in music search, retrieval, recommendation and pedagogy.

Raga Verification in Carnatic Music Using Longest Common Segment Set

An attempt is made to mimic the listener in Carnatic music concerts by introducing a novel approach for matching, called Longest Common Segment Set (LCSS), which normalized with respect to its cohorts in two different ways.

The Matrix Profile for Motif Discovery in Audio-An Example Application in Carnatic Music

The authors provide an example application on a recording of a performance in the Carnatic rāga, Rītigaul .a, finding 56 distinct patterns of varying lengths that occur at least 3 times in the recording.

Cent Filter-Banks and its Relevance to Identifying the Main Song in Carnatic Music

Song identification is performed on 50 live recordings of Carnatic music and a new feature called Cent Filter-bank based Cepstral Coefficients (CFCC) that is tonic invariant is proposed, showing that CFCC features give promising results for CarnaticMusic processing tasks.

Identifying Ragas in Indian Music

This work attempts the raga classification problem in a non-linear SVM framework using a combination of two kernels that represent the similarities of a music signal using two different features-pitch-class profile and n-gram distribution of notes.

References

SHOWING 1-10 OF 21 REFERENCES

Motivic analysis and its relevance to raga identification in carnatic music

An attempt is made to deter mine the characteristic motifs that enable identification o f a r¯ aga and distinguish between them and results do indicate that about 80% of the motifs are identified as belonging to a specific r° aga accurately.

Detection of Raga-characteristic phrases from Hindustani Classical Music Audio

The proposed method does segmentation of phrases through identification of nyas and computes similarity with the reference characteristic phrase.

Melody Extraction From Polyphonic Music Signals Using Pitch Contour Characteristics

  • J. SalamonE. Gómez
  • Computer Science
    IEEE Transactions on Audio, Speech, and Language Processing
  • 2012
A comparative evaluation of the proposed approach shows that it outperforms current state-of-the-art melody extraction systems in terms of overall accuracy.

Assessing the Tuning of Sung Indian Classical Music

The authors' results evidence that the tunings in Carnatic and Hindustani music differ, the former tending to a just intonation system and the latter having much equal-tempered influences.

Searching Musical Audio Using Symbolic Queries

This paper proposes a relative pitch approach for representing queries and pieces, and presents an algorithm for matching based on a pitch classes approach, using the longest common subsequence between a query and target.

Application of pitch tracking to South Indian classical music

  • A. Krishnaswamy
  • Physics
    2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)
  • 2003
Results of applying pitch trackers to samples of South Indian classical (Carnatic) music are presented and the various musical notes used and their intonation are investigated.

A cepstrum based approach for identifying tonic pitch in Indian classical music

A Non-Negative Matrix Factorization (NMF) technique based method is developed to identify tonic and it is shown that by identifying the musical note Sadja in the lower octave of a performance, the pitch of the tonic can be identified accurately.

Music Matching Based on Rough Longest Common Subsequence

The RLCS (rough longest common subsequence) method is an improved version of the LCS to avoid some problems occurring in global alignment matching and uses the filtering algorithm proposed by Tarhio and Ukkonen to filter the reference and discard most of the reference areas that do not match.

Probabilistic discovery of time series motifs

This work introduces a novel algorithm inspired by recent advances in the problem of pattern discovery in biosequences, which is probabilistic in nature, but can find time series motifs with very high probability even in the presence of noise or "don't care" symbols.

Detecting time series motifs under uniform scaling

This work introduces a new algorithm that allows discovery of time series motifs with invariance to uniform scaling, and shows that it produces objectively superior results in several important domains.