Exploratory Study Of Human-AI Interaction For Hindustani Music

TL;DR

This study explores how musicians interact with a hierarchical generative model for Hindustani vocal contours, highlighting challenges and user preferences in real-world AI-assisted music performance.

Contribution

It provides initial insights into human-AI interaction in Hindustani music using a novel generative model and identifies key challenges for future model improvements.

Findings

Participants faced challenges with incoherent outputs

Lack of restrictions led to unpredictable results

User preferences varied in interaction modes

Abstract

This paper presents a study of participants interacting with and using GaMaDHaNi, a novel hierarchical generative model for Hindustani vocal contours. To explore possible use cases in human-AI interaction, we conducted a user study with three participants, each engaging with the model through three predefined interaction modes. Although this study was conducted "in the wild"- with the model unadapted for the shift from the training data to real-world interaction - we use it as a pilot to better understand the expectations, reactions, and preferences of practicing musicians when engaging with such a model. We note their challenges as (1) the lack of restrictions in model output, and (2) the incoherence of model output. We situate these challenges in the context of Hindustani music and aim to suggest future directions for the model design to address these gaps.