Raga classification using enhanced spatial bound whale optimization algorithm

A raga is a unique set of notes with certain rules that carefully followed, retain and protect its purity produce amazing musical effects. An automated transcription identification important for computational musicology, which an step musicology indexing, classifying, recommending tunes. In the present research, audio features such as mel frequency cepstrum coefficients (MFCCs), spectral flux, short time energy, feature extractor, centroid are used prediction raga. The model showed more complexity means it required lots training data. proposed enhanced spatial bound whale optimization algorithm (ESBWOA) overcome selection problem high dimensional features. addition to this, weighted salp swarm (SSA) selecting tone-based from ragas based on amplitude or each sample. were fed bidirectional long short-term memory (Bi-LSTM) network, success rate classification. research uses CompMusic dataset in work where 9 classes Carnatic music 7 Hindustani considered classification ragas.