On an Ethical Use of Neural Networks: A Case Study on a North Indian Raga
This addresses ethical concerns in AI for cultural preservation, specifically for the Indian classical music community, but is incremental as it focuses on structural modeling rather than performance generation.
The paper tackles the ethical modeling of a North Indian raga, Bageshree, using an artificial neural network for time series analysis of pitch data, arguing against copying artist performances to avoid undermining the emotional and devotional aspects of the music.
The paper gives an artificial neural network (ANN) approach to time series modeling, the data being instance versus notes (characterized by pitch) depicting the structure of a North Indian raga, namely, Bageshree. Respecting the sentiments of the artists' community, the paper argues why it is more ethical to model a structure than try and "manufacture" an artist by training the neural network to copy performances of artists. Indian Classical Music centers on the ragas, where emotion and devotion are both important and neither can be substituted by such "calculated artistry" which the ANN generated copies are ultimately up to.