[PPT] - Tonic Identification System for Hindustani and Carnatic Music PowerPoint Presentation

SLIDE 1

Tonic Identification System for Hindustani and Carnatic Music

Sankalp Gulati, Justin Salamon and Xavier Serra Music Technology Group Universitat Pompeu Fabra {sankalp.gulati, justin.salamon, xavier.serra}@upf.edu

SLIDE 2

Introduction: Tonic in Indian art music

 The base pitch chosen by a performer that allows to explore the full pitch range in a comfortable way [1]  Anchored as ‘Sa’ swar in a performance (mostly)  All the other notes used in the raga exposition derive their meaning in relation to this pitch value  All other accompanying instruments are tuned using this pitch as reference

P i t c h time Tonic

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

2

SLIDE 3

Role of Drone Instrument

 Performer and audience needs to hear this pitch throughout the concert  Reinforces the tonic and establishes all harmonic and melodic relationships

Tanpura Sitar Surpeti or Shrutibox Electronic Tanpura

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

3

SLIDE 4

Introduction: Tonal structure of Tanpura

 Four strings  Tunings

 Sa-Sa’-Sa’-Pa  Sa-Sa’-Sa’-Ma  Sa-Sa’-Sa’-Ni

 Special bridge with thread inserted (Jvari)

 Violate Helmholtz law [2]

 Rich overtones [1]

Bridge

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

4

SLIDE 5

Introduction: Goals and Motivation

 Automatic labeling of the tonic in large databases of Indian art music  Devise a system for identification of

 Tonic pitch for vocal excerpts  Tonic pitch class profile for instrumental excerpts

 Use all the available data (audio + metadata) to achieve maximum accuracy  Confidence measure for each output from the system

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

5

SLIDE 6

Introduction: Goals and Motivation

 Fundamental information  Tonic identification: crucial input for:

 Intonation analysis  Raga recognition  Melodic motivic analysis

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

6

SLIDE 7

Relevant work: Tonic Identification

 Very little work done in the past  Based on melody [ 4,5]  Ranjani et al. take advantage of melodic characteristics

f Carnatic music [4]

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

7

SLIDE 8

Relevant work: Summary

 Utilized only the melodic aspects  Used monophonic pitch trackers for heterophonic data  Limited diversity in database

 Special raga categories, aalap sections, solo vocal recordings

 Unexplored aspects:

 Utilizing background audio content comprising drone sound  Taking advantage of different types of available data, like audio and metadata  Evaluation on diverse database

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

8

SLIDE 9

Methodology: System Overview

Manual annotation Tonic

Yes Yes No No Audio Metadata

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

9

SLIDE 10

Methodology: System Overview

 Culture specific characteristics for tonic identification

 Presence of drone*  Culture specific melodic characteristics  Raga knowledge  Melodic Motifs

 Use variable amount of data that is sufficient enough to identify tonic with maximum confidence.

 Audio data  Metadata (Male/Female, Hindustani/Carnatic, Raga etc.)

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

10

SLIDE 11

Methodology: Tonic Identification

 Audio example:  Utilizing drone sound  Chroma or multi-pitch analysis

Multi-pitch Analysis [7]

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

11

SLIDE 12

Tonic Identification: Signal Processing

Audio Sinusoids Time frequency salience

Sinusoid Extraction

Tonic candidates

Pitch Salience computation Tonic candidate generation

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

12

SLIDE 13

Tonic Identification: Signal Processing

 STFT

 Hop size: 11 ms  Window length: 46 ms  Window type: hamming  FFT = 8192 points

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

13

SLIDE 14

Tonic Identification: Signal Processing

 Spectral peak picking

 Absolute threshold: -60 dB  Relative threshold: -40 dB

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

14

SLIDE 15

Tonic Identification: Signal Processing

 Frequency/Amplitude correction

 Parabolic interpolation

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

15

SLIDE 16

Tonic Identification: Signal Processing

 Harmonic summation [7]

 Spectrum considered: 55-7200 Hz  Frequency range: 55-1760 Hz  Base frequency: 55 Hz  Bin resolution: 10 cents per bin (120 per

ctave)

 N octaves: 5  Maximum harmonics: 20  Alpha: 1  Beta: 0.8  Square cosine window across 50 cents

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

16

SLIDE 17

Tonic Identification: Signal Processing

 Tonic candidate generation

 Number of salience peaks per frame: 5  Frequency range: 110-550 Hz  After candidate selection salience is no longer considered!!!!

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

17

SLIDE 18

Tonic Identification : Two sub-tasks

 Caters to both vocal and instrumental excerpts

 Identify tonic pitch class (PC) using multi-pitch histogram  Estimate the correct octave using predominant melody

 Use predominant melody extraction approach proposed by Justin Salamon et al. [6]  Tonic PCP

 Peak Picking + Machine learning

 Tonic octave estimation

 Rule based method + Classification based approach

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

18

SLIDE 19

Tonic Identification : PC identification

 Classification based template learning  Two kind of class mappings

 Rank of the highest tonic PC  Highest peak as Tonic or Non tonic

 Feature extracted # 20 (f1-f10, a1-a10)

100 150 200 250 300 350 400 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1

Frequency bins (1 bin = 10 cents), Ref: 55Hz Normalized salience Multipitch Histogram

f2 f3 f4 f5

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

19

SLIDE 20

Tonic Identification : PC identification

 Decision Tree:

>5 <=5 >-7 <=-7 >-11 <=-11 >5 <=5 >-6 <=-6

Sa Sa Pa

salience Frequency

Sa Sa Pa

salience Frequency

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

20

SLIDE 21

Tonic Identification : Octave Identification

 Tonic octave

 Rule based method  Classification based approach

 25 Features: a1-a25

50 100 150 200 250 300 350 0.2 0.4 0.6 0.8 1

Frequency bins (1 bin = 10 cents), Ref: 55 Hz Normalized Salience Perdominent Melody Histogram

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

21

SLIDE 22

Evaluation: Database

 Subset of CompMusic database (>300 Cds) [3]

Approach 2: #540, 3min (PCP) + 238, full recordings (Octave)

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

22

SLIDE 23

Evaluation: Database

 Tonic distribution  Statistics (for 364 vocal excerpts)

 Male (80 %), Female (20%), Hindustani (38%), Carnatic (62%), Unique artist (#36)

 Statistics (for 540 vocal and instrumental excerpts)

 Hindustani (36%), Carnatic (64%), Unique artist (#55)

120 140 160 180 200 220 240 260 280 10 20 30 40 50 60 Frequency (Hz) Number of instances Female singers Male singers 2nd CompMusic Workshop, Istanbul, 2012 7/23/12

23

SLIDE 24

Evaluation: Annotations

 Annotations done by the author  Extracted 5 tonic candidates from multi-pitch histograms between 110-370 Hz  Matlab GUI to speed up the annotation procedure

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

24

SLIDE 25

Evaluation: Accuracy measures

 Output correct within 50 cents of the ground truth  10 fold cross validation + rule based classification  Weka: data mining tool  Feature selection: CfsSubsetEval (features > 80% folds)  Classifier: J48 decision tree  Performs better than

 SVM-polynomial kernel (6% difference in accuracy)  K* classifier (5% difference in accuracy)

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

25

SLIDE 26

Results

Approach\(%) Map #folds Class EQ # Features Tonic pitch Tonic PCP 5th 4th Other AP1_EXP1

85

10.7 0.93 3.3 AP1_EXP2 M1 1 no 1, S2

93.7

1.48 8.9 0.9 AP1_EXP3 M1 10 no 4, S3

92.9

1.9 3.5 1.7 AP1_EXP4 M1 10 yes 4, S4

74.2

11 7.6 6.7 AP1_EXP5 M2 1 no 1, S2

91

3.3 3 2.7 AP1_EXP6 M2 10 no 2, S5

91.8

2.2 3 3 AP1_EXP7 M2 10 yes 2, S5

87.8

4.2 4 3.9

 M1 : tonic PCP rank, M2 : highest peak tonic or non-tonic  S1: [f2, f3, f5], S2: [f2], S3: [f2, f4, f6, a5], S4: [f2, f3, a3, a5], S5: [f2, f3]

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

26

SLIDE 27

Results

 Approach 2, Octave identification

 Rule based approach – 99 %  Classification based approach – 100%

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

27

SLIDE 28

Discussion: PCP Identification

 AP-1: Performance for male singers (95%), female singers (88%)  Error cases

 Mostly Ma tuning songs  More female singers

 Sensitive to selected frequency range for tonic candidates, a range of 110-370 Hz works optimal

Sa Sa Pa

salience Frequency

Sa Sa Pa

salience Frequency

Sa Sa Ma

salience Frequency

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

28

SLIDE 29

Discussion : Octave Identification

 Challenges faced by rule based approach

 Hindustani musicians go roughly -500 cents below tonic  Carnatic musicians generally don’t go that below tonic  Melody estimation errors at low frequency  Concept of Madhyam shruti

50 100 150 200 250 300 350 0.2 0.4 0.6 0.8 1

Frequency bins (1 bin = 10 cents), Ref: 55 Hz Normalized Salience Perdominent Melody Histogram

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

29

SLIDE 30

Conclusions and Future Work

 Drone sound in the background provides an important cue for the identification of tonic and can be utilized to automatically perform this task  System should be fed with more information to differentiate between ‘Pa’ and ‘Ma’ tuning  Future Work:

 Exploring melodic characteristics for tonic identification  Deeper analysis of confidence measure concept  Study influence of cultural background on human performance for this task

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

30

SLIDE 31

REFERENCES

1. B. C. Deva. The Music of India: A Scientific Study. Munshiram Manoharlal

Publishers, Delhi, 1980.

2. C. V. Raman. On some Indian stringed instruments. In Indian Association for the

Cultivation of Science, volume 33, pages 29-33, 1921.

3. X. Serra. A multicultural approach in music information research. In 12th Int. Soc. for

Music Info. Retrieval Conf., Miami, USA, Oct. 2011.

4. R. Sengupta, N. Dey, D. Nag, A. K. Datta, and A. Mukerjee, “Automatic Tonic ( SA )

Detection Algorithm in Indian Classical Vocal Music,” in National Symposium on Acoustics, 2005, pp. 1-5.

5. T. V. Ranjani, H.G.; Arthi, S.; Sreenivas, “Carnatic music analysis: Shadja, swara

identification and rAga verification in AlApana using stochastic models,” Applications

f Signal Processing to Audio and Acoustics (WASPAA), IEEE Workshop, pp. 29-32,

2011.

6. J. Salamon and E. G´omez. Melody extraction from polyphonic music signals using

pitch contour characteristics. IEEE Transactions on Audio, Speech, and Language Processing, 20(6):1759–1770, Aug. 2012.

7. J. Salamon, E. G´omez, and J. Bonada. Sinusoid extraction and salience function

design for predominant melody estimation. In Proc. 14th Int. Conf. on Digital Audio Effects (DAFX-11), pages 73–80, Paris, France, Sep. 2011.

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

31

SLIDE 32

Thank you Questions?

2nd CompMusic Workshop, Istanbul, 2012 7/23/12

32