Overview of Research at IITB Computational studies on Hindustani - - PowerPoint PPT Presentation

1

Preeti Rao

Department of Electrical Engineering I.I.T. Bombay

CompMusic Workshop, Chennai 2013

Overview of Research at IITB

Computational studies on Hindustani music

2

• Automatic “tagging” of audio by genre, style, raga, tala and other

discovered descriptors and relationships

• Automatic creation of “navigation layer” for concert audio
• Facilitating search for musically relevant objects such as melodic

and rhythmic motifs

• Building tools that facilitate musicological research on

performance practices

Common to all the above:

Need for a music representation (aka features) and similarity measure (for classification)

Some goals

3

Music CD cover information… (YouTube has even less!)

4

Hindustani music descriptors/tags

• Artiste (instrument), accompanists
• Genre (dhrupad, khyal, tarana…), sub-genre (gharana)
• Concert structure and sections with timing

– Bada khyal, Chhota khyal

• Bandish: alap, vistaar, taan
• Raga, Tala, Laya of major sections
• Composition (bandish, identified by mukhda)

The question

Can the descriptions be obtained by audio content analysis and possibly enhanced with contextual semantic information?

5

Kishori Amonkar Deshkar: bada khyal (vistaar, taan)

Alap (slow tempo) Alap (medium tempo) Taan

6

Taan (madhylaya) Taan (drut laya)

Kishori Amonkar Deshkar: bada khyal taan, chhota khyal taan

7

alap (bada khyal) (bada khyal) chhota khyal

Kishori Amonkar Deshkar

taan vistaar

8

Alap

Jhala (alap) Jod (alap) Uday Bhawalkar (dhrupad) Yaman

9

alap jod jhala

Uday Bhawalkar (dhrupad) Yaman

10

Raga Gaud Sarang Raga Deshkar

Kishori Amonkar: Deshkar, Gaud-Sarang

11

Raga Gaud Sarang Raga Deshkar

• riginal

resynthesized

12

Raga Gaud Sarang Raga Deshkar G P R G R S G S R S P G S R S S D P G G R P R S S D S D S D S D D S S R S S R R G

13

• Pt. Vidhyadhar Vyas

Marwa and Puriya (share the same swaras)

Raga characteristics from pitch distribution

14

Melodic motif (mukhda) detection

Kishori Amonkar, Deshkar, Tintal Bandish: Piya Jaag

15

Phrase duration, dependence on tempo

16

Within-concert variability of motif

17

Kafi

Within-concert variability across concerts Intra-phrase class distance distribution

18

Ontology for Indian music

Learning metadata (textual) from forums by using NLP techniques to learn relationships between entities.

• Augment audio-based music ontology for Indian music with

information extracted from online music forums to achieve superior retrieval systems for Indian music.

Example: Get songs with phrase ‘NDNP’ and sung by a disciple

• f D.K. Pattammal
• Challenges: text sources are unstructured, ungrammatical…

19

Summary

• High-level musical attributes (melody, rhythm) can be derived

from low-level acoustic parameters such as pitch and onsets extracted by audio signal processing.

• The audio signal processing is challenging due to the mixture of

several instruments, strong diversity in the characteristics and the highly time-varying nature.

• Melody and rhythm representations that are musicologically

informed can be useful in the description of music recordings.

• Knowledge can be very helpful. Creating these from available

sources is a challenge.

20

Coming up…

• Vedhas Pandit, Kaustuv : Characterization of melodic motifs
• Vinutha T. P.: Rhythmic structure based segmentation
• Joe Cheri Ross: Ontology for Indian Music: An Approach for
• ntology learning from online music forums
• Amruta J. Vidwans and Prateek Verma: Melodic style detection in

Hindustani music

21 Department of Electrical Engineering , IIT Bombay

Thank you