GaMaDHaNi: Hierarchical Generative Modeling of Melodic Vocal Contours in Hindustani Classical Music

1 Figures 1 & 2

Figure 1: Example of Hindustani Singing

Fig 1: Extracted pitch contour from audio recording of Hindustani classical singing. Solfege notation is highlighted as a horizontal grid.

Fig 1: Extracted pitch contour from audio recording of Hindustani classical singing. Solfege notation is highlighted as a horizontal grid.

Figure 2: Overview of GaMaDHaNi

Note: The sound of a tanpura (drone) is added to the background of the generated samples highlighted below. The use of a tanpura is common in Hindustani vocal performance, and is added here to simulate that sound.

Pitch Prime

Pitch (Prime + Pitch Generation)

Fig 2: The overall hierarchical structure of GaMaDHaNi. Given a short melodic input, i.e. ‘prime’, the model generates a pitch continuation, followed by a spectrogram which is then converted to audio using a vocoder.

Fig 2: The overall hierarchical structure of GaMaDHaNi. Given a short melodic input, i.e. ‘prime’, the model generates a pitch continuation, followed by a spectrogram which is then converted to audio using a vocoder.