Conference Papers

Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506

Browse

Filters

2015 - 20184

Settings

Subject: search.filters.subject.Carnatic music

Search Results

Now showing 1 - 4 of 4
  • No Thumbnail Available
    Item
    Raga classification for Carnatic music
    (Springer Verlag service@springer.de, 2015) Suma, S.M.; Koolagudi, S.G.
    In this work, an effort has been made to identify raga of given piece of Carnatic music. In the proposed method, direct raga classification without the use of note sequence has been performed using pitch as the primary feature. The primitive features that are extracted from the probability density function (pdf) of the pitch contour are used for classification. A feature vector of 36 dimension is obtained by extracting some parameters from the pdf. Since non-sequential features are extracted from the signal, artificial neural network (ANN) is used as a classifier. The database used for validating the system consists of 162 songs from 12 ragas. The average classification accuracy is found to be 89.5%. © Springer India 2015.
  • No Thumbnail Available
    Item
    Identification of allied raagas in Carnatic music
    (Institute of Electrical and Electronics Engineers Inc., 2015) Upadhyaya, P.; Suma, S.M.; Koolagudi, S.G.
    In this work, an effort has been made to differentiate the allied raagas in Carnatic music. Allied raagas are the raagas that are composed using same set of notes. The features derived from the pitch sequence are used for differentiating these raagas. The coefficients of legendre polynomials, used to fit the pitch contours of the song clips are used for identifying raagas. Obtained features are validated using different classifiers such as Neural networks, Naive Bayes, Multi class classifier, Bagging and Random forest. The proposed system is tested on 4 sets of allied raagas. Naive Bayes classifier gives an average accuracy of 86.67% for allied set of Todi-Dhanyasi and Multi class classifier gives an average accuracy of 86.67% for allied set of Kharaharapriya-Anandabhairavi-Reethigoula. In general, Neural network classifier performance is found to be better than other classifiers. © 2015 IEEE.
  • No Thumbnail Available
    Item
    Rhythm and timbre analysis for carnatic music processing
    (Springer Science and Business Media Deutschland GmbH info@springer-sbm.com, 2016) Heshi, R.; Suma, S.M.; Koolagudi, S.G.; Bhandari, S.; Sreenivasa Rao, K.S.
    In this work, an effort has been made to analyze rhythm and timbre related features to identify raga and tala from a piece of Carnatic music. Raga and Tala classification is performed using both rhythm and timbre features. Rhythm patterns and rhythm histogram are used as rhythm features. Zero crossing rate (ZCR), centroid, spectral roll-off, flux, entropy are used as timbre features. Music clips contain both instrumental and vocals. To find similarity between the feature vectors T-Test is used as a similarity measure. Further, classification is done using Gaussian Mixture Models (GMM). The results shows that the rhythm patterns are able to distinguish different ragas and talas with an average accuracy of 89.98 and 86.67 % respectively. © Springer India 2016.
  • No Thumbnail Available
    Item
    Singing Voice Synthesis System for Carnatic Music
    (Institute of Electrical and Electronics Engineers Inc., 2018) Rajan, M.
    Singing Voice Synthesis systems take speech, lyric and note information as inputs, and produce songs as the output. For converting speech to song, the duration and pitch of the speech need to be modified to match the desired pitch and duration of the song. In this paper, we propose a baseline speech to singing voice synthesis system for Carnatic music. We synthesize two popular Carnatic songs from the flat pitched recordings of a vowel sound. Pitch of the input sound is modified according to the frequencies of notes present in the original songs. To avoid abrupt pitch changes, transitions between adjacent notes are smoothed using a sinusoid-based function. To add naturalness to the synthesized song, fluctuations present in input speech are retained. Harmonic plus Noise Model is used to synthesize the songs. Subjective evaluation is performed by ten listeners, and the Mean Opinion Scores for the songs are found to be 3.1 and 3. © 2018 IEEE.