Raga Recognition in Indian Classical Music Using Deep Learning

Shah, Devansh; Jagtap, Nikhil M.; Talekar, Prathmesh T.; Gawande, Kiran

doi:10.1007/978-3-030-72914-1_17

Cited by 12 publications

(10 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study uses precision, Recall, F1, and confusion metrics [4] [16] to evaluate the test set based on the scores of True Positive (TP), True Negative (TN), False Positive (FP), and False Negative (FN). Precision gives the understanding of positive identification's proportions, which are actually true and as defined in the following equation.…”

Section: Discussionmentioning

confidence: 99%

“…Despite the fuzzy nature of the genre boundaries, music genre classification can be conducted automatically and with significantly accurate results [3]. For the past two decades, this work has been performed by many researchers by taking distinct feature sets like Spectrogram, Spectral Rolloff, Downsampling [4], Scalogram, and MFCCs to explore the timbre texture [3], pitch content, and rhythm of the audio signals. The music genre classification of the timbre surface is performed by extracting features like the MFCCs [5].…”

Section: Introductionmentioning

confidence: 99%

“…Researchers have attained tremendous success in music genre classification by taking features like MFCCs, Spectrogram, and Scalograms from the audio songs and feeding them into neural networks [13]- [15]. Besides Convolutional Neural Network (CNN) [15], VGG-16 model [16], and ResNet-50, RNN-LSTM is also used to classify music genres by taking MFCCs features of audio files and performed slightly better when compared with CNN and DNN [9] [4].…”

Section: Introductionmentioning

confidence: 99%

“…Hindustani Music is Indian Semi-Classical Music and has different genres like Tappa, Thumri, Kajri, Abhang, Ghazal, Geet, Mand, and Bhajan. Indian Semi-Classical music is generally based on Raga and Talam, equivalent to the melody in Western music [4] [16]. The complexity of Indian semi-classical music is more compared to western Music in the context of melody and scale.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Classification of Indian Classical Music (Hindustani Music) Genres through MFCCs Features using RNN-LSTM Model

Bisht

Negi

Singh

2022

Preprint

View full text Add to dashboard Cite

Music has been considered an inseparable part of our culture and tradition. In this work, we created a dataset with six Hindustani music genres: Abhang, Bhajan, Thumri, Tappa, Ghazal, and Kajri, each of which contains 100 songs in wave(.wav) format. To classify the Hindustani music genres, we employ the mel frequency ceptral coefficients features, which contain timbral information, and the Recurrent Neural Network-Long Short Term Memory. Our best three models achieved an average accuracy of 86% when trained on various feature sets with MFCC values of 18, 26, and 39. Furthermore, we use uniform manifold approximation and projection to transform and visualise higher-dimensional feature set data into two-dimensional space. Based on the results, we can infer that Hindustani music has more intricate melodies than western music, and feeding 18 MFCC features to the deep neural network is the optimum strategy to obtain better accuracy. Increasing the hop length from 512 to 1024 reduces the input dimension size, which facilitates the RNN-LSTM model. As a result, the performance of the RNN-LSTM models has been slightly improved. Our RNN-LSTM models’ test set accuracy decreased by 5% when we took 5 segments. Additionally, we evaluated and compared our model to six genres of the GTZAN dataset and achieved 90% accuracy.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Classification of Indian Classical Music (Hindustani Music) Genres through MFCCs Features using RNN-LSTM Model

Bisht

Negi

Singh

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…However, the error that occurred in the classification required manual identification. Shah et al [21] developed the raga deep learning model for recognition in ICM. The developed deep learning and signal processing based approach was presented in the research work that recognized the raga based on the audio spectrograms.…”

Section: Introductionmentioning

confidence: 99%

Raga classification using enhanced spatial bound whale optimization algorithm

Gowrishankar

Bhajantri

2023

IJEECS

View full text Add to dashboard Cite

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

show abstract