Recognizing ragas of Carnatic genre using advanced intelligence: a classification system for Indian music

Abstract

<jats:sec><jats:title content-type="abstract-subheading">Purpose</jats:title><jats:p>In general, Indian Classical Music (ICM) is classified into two: Carnatic and Hindustani. Even though, both the music formats have a similar foundation, the way of presentation is varied in many manners. The fundamental components of ICM are raga and taala. Taala basically represents the rhythmic patterns or beats (Dandawate <jats:italic>et al.</jats:italic>, 2015; Kirthika and Chattamvelli, 2012). Raga is determined from the flow of swaras (notes), which is denoted as the wider terminology. The raga is defined based on some vital factors such as swaras, aarohana-avarohna and typical phrases. Technically, the fundamental frequency is swara, which is definite through duration. Moreover, there are many other problems for automatic raga recognition model. Thus, in this work, raga is recognized without utilizing explicit note series information and necessary to adopt an efficient classification model.</jats:p></jats:sec><jats:sec><jats:title content-type="abstract-subheading">Design/methodology/approach</jats:title><jats:p>This paper proposes an efficient raga identification system through which music of Carnatic genre can be effectively recognized. This paper also proposes an adaptive classifier based on NN in which the feature set is used for learning. The adaptive classifier exploits advanced metaheuristic-based learning algorithm to get the knowledge of the extracted feature set. Since the learning algorithm plays a crucial role in defining the precision of the raga recognition, this model prefers to use the GWO.</jats:p></jats:sec><jats:sec><jats:title content-type="abstract-subheading">Findings</jats:title><jats:p>Through the performance analysis, it is witnessed that the accuracy of proposed model is 16.6% better than NN with LM, NN with GD and NN with FF respectively, 14.7% better than NN with PSO. Specificity measure of the proposed model is 19.6, 24.0, 13.5 and 17.5% superior to NN with LM, NN with GD, NN with FF and NN with PSO, respectively. NPV of the proposed model is 19.6, 24, 13.5 and 17.5% better than NN with LM, NN with GD, NN with FF and NN with PSO, respectively. Thus it has proven that the proposed model has provided the best result than other conventional classification methods.</jats:p></jats:sec><jats:sec><jats:title content-type="abstract-subheading">Originality/value</jats:title><jats:p>This paper intends to propose an efficient raga identification system through which music of Carnatic genre can be effectively recognized. This paper also proposes an adaptive classifier based on NN.</jats:p></jats:sec>

Improved Expectation-Maximization Algorithm for Unknown Reverberant Audio-Source Separation

“…Second, we investigate the undecided scenario and compare the proposed approach to the current algorithm [22][23][24]. The tables 2, 3, and 4 summarize the mean SDR values derived using the various approaches.…”

Raga classification using enhanced spatial bound whale optimization algorithm

“…The overlap length is performed among the hop length and the window length which evaluates the difference. The overlap length is represented as shown in (7). The spectral flatness is measured typically in terms of dB which provide a way to quantify the sound resemblance for a pure tone that is opposed to noiselike features.…”

“…The deep learning model like LSTM based model was used for performing automated transcription for the Carnatic music. The detection of the note is solved with the problem of image classification [7], [8]. The ragas classification showed complexity that is more compared with western music in the context of scale and melody.…”