DeepSRGM -- Sequence Classification and Ranking in Indian Classical Music with Deep Learning
This work addresses the music information retrieval task of Raga recognition, which can aid applications like music recommendations and organizing collections, but it is incremental as it applies existing LSTM-RNN methods to this specific domain.
The authors tackled the problem of Raga recognition in Indian Classical Music using a deep learning approach, achieving state-of-the-art accuracies of 88.1% on the Comp Music Carnatic dataset and 97% on a 10 Raga subset.
A vital aspect of Indian Classical Music (ICM) is Raga, which serves as a melodic framework for compositions and improvisations alike. Raga Recognition is an important music information retrieval task in ICM as it can aid numerous downstream applications ranging from music recommendations to organizing huge music collections. In this work, we propose a deep learning based approach to Raga recognition. Our approach employs efficient pre possessing and learns temporal sequences in music data using Long Short Term Memory based Recurrent Neural Networks (LSTM-RNN). We train and test the network on smaller sequences sampled from the original audio while the final inference is performed on the audio as a whole. Our method achieves an accuracy of 88.1% and 97 % during inference on the Comp Music Carnatic dataset and its 10 Raga subset respectively making it the state-of-the-art for the Raga recognition task. Our approach also enables sequence ranking which aids us in retrieving melodic patterns from a given music data base that are closely related to the presented query sequence.