Computational Tools for the Exploration of Melodic Characteristics - - PowerPoint PPT Presentation

▶
computational tools for the exploration of melodic
SMART_READER_LITE
LIVE PREVIEW

Computational Tools for the Exploration of Melodic Characteristics - - PowerPoint PPT Presentation

Apr 24, 2023 139 likes •799 views

Computational Tools for the Exploration of Melodic Characteristics CompMusic Seminar, IIT-Madras, Chennai, India 14 Dec, 2013 Sankalp Gulati Melodic similarity Raga recognition Motif extraction Intonation analysis Melody extraction Tonic

slide-1
SLIDE 1

Computational Tools for the Exploration

  • f Melodic Characteristics

CompMusic Seminar, IIT-Madras, Chennai, India 14 Dec, 2013 Sankalp Gulati

slide-2
SLIDE 2
slide-3
SLIDE 3
slide-4
SLIDE 4

Tonic identifjcation Melody extraction Intonation analysis Motif extraction Raga recognition Melodic similarity

slide-5
SLIDE 5

Computation al tools

slide-6
SLIDE 6

Computation al tools

Tonic

slide-7
SLIDE 7

Computation al tools

Tonic Melody

slide-8
SLIDE 8

Computation al tools

Tonic Melody Intonation

slide-9
SLIDE 9

Computation al tools

Tonic Melody Intonation Motifs

slide-10
SLIDE 10

Computation al tools

Tonic Melody Intonation Raga Motifs

slide-11
SLIDE 11

Computation al tools

Tonic Melody Intonation Raga Motifs Similarity

slide-12
SLIDE 12

Tonic Identifjcation

slide-13
SLIDE 13

Tonic Identifjcation

1000 2000 3000 4000 5000 0.2 0.4 0.6 0.8 1

f2 f3 f4 f5 f6

Tonic Signal processing Learning

Accuracy : ~90% !!!

slide-14
SLIDE 14

Tonic Identifjcation

1000 2000 3000 4000 5000 0.2 0.4 0.6 0.8 1

f2 f3 f4 f5 f6

Tonic Signal processing Learning

§ Tanpura / drone background sound § Extent of gamakas on Sa and Pa svara § Vadi, sam-vadi svara of the rāga

Salamon, J., Gulati, S., & Serra, X. (2012). A multipitch approach to tonic identification in Indian classical music. In Proc. of Int. Conf. on Music Information Retrieval (ISMIR) (pp. 499–504), Porto, Portugal. Bellur, A., Ishwar, V., Serra, X., & Murthy, H. (2012). A knowledge based signal processing approach to tonic identification in Indian classical music. In 2nd CompMusic Workshop (pp. 113–118) Istanbul, Turkey. Ranjani, H. G., Arthi, S., & Sreenivas, T. V. (2011). Carnatic music analysis: Shadja, swara identification and raga verification in Alapana using stochastic

  • models. Applications of Signal Processing to Audio and Acoustics (WASPAA), IEEE Workshop , 29–32, New Paltz, NY.

Accuracy : ~90% !!!

slide-15
SLIDE 15

Tonic Identifjcation

Vignesh Ishwar, Varnam

slide-16
SLIDE 16

Tonic Identifjcation

C#

Vignesh Ishwar, Varnam

slide-17
SLIDE 17
slide-18
SLIDE 18
slide-19
SLIDE 19

Tonic values in our music collection

A A# B C C# D D# E F F# G G# A A# B 50 100 150 Tonic Frequency Number of recordings

. ¡ . ¡ . ¡

slide-20
SLIDE 20

Melody Extraction

slide-21
SLIDE 21

§ Pitch (Fundamental frequency-F0) of the lead artist § Pitch estimation

§ Solo Vs multiple instruments § Melodic contour characteristics § Dual melodic lines in Indian art music

slide-22
SLIDE 22

§ Pitch (Fundamental frequency-F0) of the lead artist § Pitch estimation

§ Solo Vs multiple instruments § Melodic contour characteristics § Dual melodic lines in Indian art music

Signal processing Learning

Salamon, Justin, and Emilia Gómez. "Melody extraction from polyphonic music signals using pitch contour characteristics." Audio, Speech, and Language Processing, IEEE Transactions on 20.6 (2012): 1759-1770. Rao, Vishweshwara, and Preeti Rao. "Vocal melody extraction in the presence of pitched accompaniment in polyphonic music." Audio, Speech, and Language Processing, IEEE Transactions on 18.8 (2010): 2145-2154. De Cheveigné, A., & Kawahara, H. (2002). YIN, a fundamental frequency estimator for speech and music. The Journal of the Acoustical Society of America, 111, 1917.

slide-23
SLIDE 23

Original Audio

slide-24
SLIDE 24

Predominant Voice

slide-25
SLIDE 25

Pitch of the Predominant Voice

slide-26
SLIDE 26

Loudness and Timbral Facets

slide-27
SLIDE 27
slide-28
SLIDE 28
slide-29
SLIDE 29

Melody Tonic

Intonation Motifs

slide-30
SLIDE 30

Intonation Analysis

slide-31
SLIDE 31

Melody Histogram

Histogram

slide-32
SLIDE 32

Melody Histogram Computation

Sa Re Ga

1s 2s 1s

Sa Re Ga Time Svara Salience

slide-33
SLIDE 33

Tarsos Demo

slide-34
SLIDE 34

Intonation Analysis

Mohana - G Begada - G

slide-35
SLIDE 35

Motif Extraction

slide-36
SLIDE 36

Melodic Motifs (Patterns)

§ Musically repetitive patterns in melody § Various time scales

§ Gamaka § Pakad § Breath phrase

slide-37
SLIDE 37

Motif Extraction and Detection

Detection Matching Retrieval

+ ¡

Image ¡taken ¡from ¡-­‑ ¡(Mueen ¡& ¡Keogh, ¡2009) ¡

Supervised

slide-38
SLIDE 38

Motif Extraction and Detection

Extraction Induction Discovery

Image ¡taken ¡from ¡-­‑ ¡(Mueen ¡& ¡Keogh, ¡2009) ¡

Un-supervised

slide-39
SLIDE 39

Motif Detection

  • 500

1000 1500 600 700 800 900 1000 1100 1200 1300

500 1000 1500

200 400 600 800 1000

  • V. Ishwar, S. Dutta, A. Bellur, and H. Murthy, “Motif spotting in an alapana in Carnatic music,” in Proc. of Int. Conf. on Music Information Retrieval

(ISMIR), 2013, pp. 499–504, Curitiba, Brasil.

  • J. C. Ross, T. P. Vinutha, and P. Rao, “Detecting melodic motifs from audio for Hindustani classical music,” in Proc. of Int. Conf. on Music Information

Retrieval (ISMIR), 2012, pp. 193– 198, Porto, Portugal.

Signal processing Pattern detection

slide-40
SLIDE 40

P1 P1 P1

slide-41
SLIDE 41
slide-42
SLIDE 42

Rāga Recognition

slide-43
SLIDE 43

Raga Recognition

slide-44
SLIDE 44

Rāga Recognition

Yaman Begada Shree Abhogi Charukeshi Behag Darbar Durga Unknown Rāga

Similarity

Chordia, P., & Rae, A. (2007, September). Raag Recognition Using Pitch-Class and Pitch-Class Dyad Distributions. In ISMIR (pp. 431-436). Koduri, G. K., Gulati, S., Rao, P., & Serra, X. (2012). Rāga recognition based on pitch distribution methods. Journal of New Music Research, 41(4), 337-350.

slide-45
SLIDE 45

Melodic Similarity

slide-46
SLIDE 46

Melodic Similarity

slide-47
SLIDE 47

Intonation Similarity

slide-48
SLIDE 48
slide-49
SLIDE 49

Thank You!!

slide-50
SLIDE 50
slide-51
SLIDE 51

Introduction

slide-52
SLIDE 52

Computation al tools

slide-53
SLIDE 53

Computation al tools Tonic

slide-54
SLIDE 54

Computation al tools

2.215 2.22 2.225 1300 1400 1500 1600 1700 1800 1900 2000

Time (1 sample = 10 ms) Predominant F0 frequency (Cents)

Tonic Melody

slide-55
SLIDE 55

Computation al tools

2.215 2.22 2.225 1300 1400 1500 1600 1700 1800 1900 2000

Time (1 sample = 10 ms) Predominant F0 frequency (Cents)

Tonic Melody Intonatio n

slide-56
SLIDE 56

Melody Extraction

§ What is melody? § What is a complete representation for melody? § … § ……

slide-57
SLIDE 57

§ What svaras are used in a performance § What is the relative salience of these svaras § What is the intonation of each of each of these svaras § How to represent svara intonation

slide-58
SLIDE 58

Rāga Recognition

Yaman Begada Shree Abhogi Charukeshi Behag Darbar Durga Unknown Rāga

slide-59
SLIDE 59

Rāga Recognition

Yaman Begada Shree Abhogi Charukeshi Behag Darbar Durga Unknown Rāga

slide-60
SLIDE 60

Rāga Recognition

Yaman Unknown Rāga Yaman Yaman XX XX

slide-61
SLIDE 61

Rāga Recognition

Yaman Yaman Yaman Yaman XX XX

slide-62
SLIDE 62
slide-63
SLIDE 63
slide-64
SLIDE 64

Tala Rāga Artist Inst. Ed. Info.

Cover Arts Relations Biographies Description Images Ground Truth Evaluation Labels Relevance Listening Tests