{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T05:46:04Z","timestamp":1776491164917,"version":"3.51.2"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2023,2,7]],"date-time":"2023-02-07T00:00:00Z","timestamp":1675728000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,2,7]],"date-time":"2023-02-07T00:00:00Z","timestamp":1675728000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1007\/s00034-023-02301-w","type":"journal-article","created":{"date-parts":[[2023,2,7]],"date-time":"2023-02-07T11:23:08Z","timestamp":1675768988000},"page":"4072-4095","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Multi-channel CNN-Based R\u0101ga Recognition in Carnatic Music Using Sequential Aggregation Strategy"],"prefix":"10.1007","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5488-9026","authenticated-orcid":false,"given":"Rajeev","family":"Rajan","sequence":"first","affiliation":[]},{"given":"Sreejth","family":"Sivan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,7]]},"reference":[{"key":"2301_CR1","doi-asserted-by":"publisher","unstructured":"T. Asha, M.S. Saranya, D.S.K, Pandia, S. Madikeri, H.A. Murthy, Feature Switching in the i-vector framework for speaker verification, in Proceedings Interspeech (2014), pp. 1125\u20131129. https:\/\/doi.org\/10.21437\/Interspeech.2014-288","DOI":"10.21437\/Interspeech.2014-288"},{"issue":"9\/10","key":"2301_CR2","first-page":"341","volume":"5","author":"P Boersma","year":"2001","unstructured":"P. Boersma, Praat, A system for doing phonetics by computer. Glot Int. 5(9\/10), 341\u2013345 (2001)","journal-title":"Glot Int."},{"key":"2301_CR3","first-page":"1","volume":"23","author":"S Belle","year":"2009","unstructured":"S. Belle, R. Joshi, P. Rao, R\u0101ga identification using Swara intonation. J. ITC Sangeet Res. Acad. 23, 1\u20137 (2009)","journal-title":"J. ITC Sangeet Res. Acad."},{"key":"2301_CR4","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/4606027","author":"C Chen","year":"2020","unstructured":"C. Chen, Q. Li, A multimodal music emotion classification method based on multi-feature combined network classifier. Math. Probl. Eng. (2020). https:\/\/doi.org\/10.1155\/2020\/4606027","journal-title":"Math. Probl. Eng."},{"key":"2301_CR5","unstructured":"P. Chordia, A. Rae, Raaga recognition using pitch class and pitch class distributions, in Proceedings of International Society for Music Information Retrieval Conference, vol. 43(1) (2007), pp. 431\u2013436"},{"key":"2301_CR6","doi-asserted-by":"crossref","unstructured":"S. Chowdhuri, Phononet \u201cMulti-stage deep neural networks for r\u0101ga identification in Hindustani classical music\u201d, in Proceedings of International Conference on Multimedia Retrieval (2019), pp. 197\u2013201","DOI":"10.1145\/3323873.3325039"},{"key":"2301_CR7","unstructured":"P. Dighe, H. Karnick, B. Raj, Swara histogram based structural analysis and identification of Indian classical r\u0101gas, in Proceedings of the 20th International Society for Music Information Retrieval Conference (2019), pp. 35\u201340"},{"key":"2301_CR8","doi-asserted-by":"crossref","unstructured":"P. Dighe, P. Agrawal, H. Karnick, S. Thota, B. Raj, Scale independent raga identification using chromagram patterns and swara based features, in Proceedings of International Conference on Multimedia and Expo Workshops (2013), pp. 1\u20134","DOI":"10.1109\/ICMEW.2013.6618238"},{"key":"2301_CR9","unstructured":"A. Diment, P. Rajan, T. Heittola, T. Virtanen, Modified group delay feature for musical instrument recognition, in Proceedings of 10th International Symposium on Computer Music Multidisciplinary Research (CMMR) (2013)"},{"key":"2301_CR10","doi-asserted-by":"crossref","unstructured":"K. Drossos, S.I. Mimilakis, D. Serdyuk, G. Schuller, T. Virtanen, Y. Ben-gio, M. Twinnet, Masker-denoiser architecture with twin networks form on aural sound source separation, in Proceedings of International Joint Conference on Neural Networks (2018), pp. 1\u20138","DOI":"10.1109\/IJCNN.2018.8489565"},{"key":"2301_CR11","unstructured":"S. Dutta, H.A. Murthy, R\u0101ga verification in Carnatic music using longest common segment set, in Proceedings of International Society for Music Information Retrieval Conference (2015), pp. 605\u2013611"},{"key":"2301_CR12","doi-asserted-by":"crossref","unstructured":"D. Ghosal, M.H. Kolekar, Music genre recognition using deep neural networks and transfer learning, in Proceedings of Interspeech (2018), pp. 2087\u20132091","DOI":"10.21437\/Interspeech.2018-2045"},{"key":"2301_CR13","unstructured":"K. Gopala, I. Koduri, S. Gulati, P. Rao, A survey of raaga recognition techniques and improvements to the state-of-the-art, in Proceedings of Sound and Music Computing, Padova, Italy (2011)"},{"key":"2301_CR14","doi-asserted-by":"crossref","unstructured":"S. Gulati, J. Sera, V. Ishwar, S. Senturk, X. Serra, Phrase-based r\u0101ga recognition using vector space modeling, in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (2016), pp. 66\u201370","DOI":"10.1109\/ICASSP.2016.7471638"},{"key":"2301_CR15","unstructured":"S. Gulati, J. Sera, S.K. Ganguli, S. Senturk, X. Serra, Time-delayed melody surfaces for r\u0101ga recognition, in Proceedings of the 17th International Society for Music Information Retrieval Conference (2016), pp. 751\u2013757"},{"key":"2301_CR16","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/TASL.2006.876858","volume":"15","author":"RM Hegde","year":"2007","unstructured":"R.M. Hegde et al., Significance of the modified group delay feature in speech recognition. IEEE Trans. Audio Speech Lang. Process. 15, 190\u2013202 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"2301_CR17","unstructured":"H. Hoffmann, Violin plot. Retrieved Sept 18 (2022)"},{"key":"2301_CR18","unstructured":"A. Krishnaswamy, Melodic atoms for transcribing Carnatic music, in Proceedings of International Society for Music Information Retrieval Conference (2004), pp. 345\u2013348"},{"key":"2301_CR19","unstructured":"A. Krishnaswamy, Multi-dimensional musical atoms in south Indian classical music, in Proceedings of the International Conference of Music Perception and Cognition (2004), pp. 1\u20134"},{"key":"2301_CR20","doi-asserted-by":"crossref","unstructured":"A.S. Krishna, P. Rajkumar, K. Saishankar, M. John, Identification of Carnatic raagas using hidden Markov models, in Proceedings of International Symposium on Applied Machine Intelligence and Informatics (2011), pp. 107\u2013110","DOI":"10.1109\/SAMI.2011.5738857"},{"issue":"1","key":"2301_CR21","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1080\/09298215.2013.866145","volume":"43","author":"GK Koduri","year":"2014","unstructured":"G.K. Koduri, J.S. Vignesh Ishwar, X. Serra, Intonation analysis of ragas in Carnatic music. J. New Music Res. 43(1), 72\u201393 (2014)","journal-title":"J. New Music Res."},{"key":"2301_CR22","doi-asserted-by":"crossref","unstructured":"V. Kumar, H. Pandya, C.V. Jawahar, Identifying r\u0101gas in Indian music, in Proceedings of 22nd International Conference on Pattern Recognition (2014), pp. 767\u2013772","DOI":"10.1109\/ICPR.2014.142"},{"key":"2301_CR23","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y Le Cun","year":"2015","unstructured":"Y. Le Cun, Y. Bengio, G. Hinton, Deep learning. Nature 521, 436\u2013444 (2015)","journal-title":"Nature"},{"key":"2301_CR24","unstructured":"S.T. Madhusudhan, G. Chowdhary, DeepSRGM: sequence classification and ranking in Indian classical music via deep learning, in Proceedings of the 20th International Society for Music Information Retrieval Conference (2019), pp. 533\u2013540"},{"key":"2301_CR25","unstructured":"S.T. Madhusdhan, G. Chowdhary, Tonic independent raag classification in Indian classical music. https:\/\/openreview.net\/pdf?id=HJz9K7kJcX (2018)"},{"key":"2301_CR26","doi-asserted-by":"crossref","unstructured":"A.P. Manoj Kumar, et al., Musical onset detection on Carnatic percussion instruments, in 2015 Twenty First National Conference on Communications (NCC) (2015), pp. 1\u20136","DOI":"10.1109\/NCC.2015.7084897"},{"issue":"5","key":"2301_CR27","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1007\/s12046-011-0045-1","volume":"36","author":"HA Murthy","year":"2011","unstructured":"H.A. Murthy, B. Yegnanarayana, Group delay functions and its application to speech processing. Sadhana 36(5), 745\u2013782 (2011)","journal-title":"Sadhana"},{"key":"2301_CR28","unstructured":"H.A. Murthy, Algorithms for processing Fourier transform phase of signals, Ph.D. dissertation, Indian Institute of Technology, Department of Computer Science and Engineering, Madras, India (1991)"},{"key":"2301_CR29","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1016\/0167-6393(91)90011-H","volume":"10","author":"HA Murthy","year":"1991","unstructured":"H.A. Murthy, B. Yegnanarayana, Formant extraction from minimum phase group delay function. Speech Commun. 10, 209\u2013221 (1991)","journal-title":"Speech Commun."},{"key":"2301_CR30","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1007\/s12046-011-0045-1","volume":"36","author":"HA Murthy","year":"2011","unstructured":"H.A. Murthy, B. Yegnanarayana, Group delay functions and its applications in speech technology. Sadhana 36, 745\u2013782 (2011). https:\/\/doi.org\/10.1007\/s12046-011-0045-1","journal-title":"Sadhana"},{"key":"2301_CR31","unstructured":"H.A. Murthy, Algorithms for processing Fourier transform phase of Signals, Ph.D. thesis, Department of Computer Science and Engineering, Indian Institute of Technology, Madras, July (1992)"},{"key":"2301_CR32","volume-title":"Discrete Time Signal Processing","author":"AV Oppenheim","year":"1990","unstructured":"A.V. Oppenheim, R.W. Schafer, Discrete Time Signal Processing (Prentice Hall Inc, Upper Saddle River, 1990)"},{"key":"2301_CR33","first-page":"4","volume":"5","author":"S Oramas","year":"2018","unstructured":"S. Oramas, F. Barbieri, O. Nieto Caballero, X. Serra, Multimodal deep learning for music genre classification. Trans. Int. Soc. Music Inf. Retr. 5, 4\u201321 (2018)","journal-title":"Trans. Int. Soc. Music Inf. Retr."},{"key":"2301_CR34","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1016\/j.specom.2004.08.001","volume":"45","author":"KK Paliwal","year":"2005","unstructured":"K.K. Paliwal, L.D. Alsteris, On the usefulness of STFT phase spectrum in human listening tests. Speech Commun. 45, 153\u2013170 (2005)","journal-title":"Speech Commun."},{"key":"2301_CR35","doi-asserted-by":"crossref","unstructured":"D.S. Park, W. Chan, Y. Zhang, C.-C. Chiu, B. Zoph, E.D. Cubuk, Q.V. Le, SpecAugment: a simple data augmentation method for automatic speech recognition, in Proceedings of Interspeech (2019)","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"2301_CR36","unstructured":"L. Perez, J. Wang, The effectiveness of data augmentation in image classification using deep learning. arXiv:1712.04621 (2017)"},{"key":"2301_CR37","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1016\/j.specom.2003.12.002","volume":"42","author":"VK Prasad","year":"2004","unstructured":"V.K. Prasad, T. Nagarajan, H.A. Murthy, Automatic segmentation of continuous speech using minimum phase group delay functions. Speech Commun. 42, 429\u2013446 (2004)","journal-title":"Speech Commun."},{"key":"2301_CR38","doi-asserted-by":"publisher","unstructured":"R. Rajan, H. Murthy, Group delay based melody monopitch extraction from music, in Proceedings of International Conference on Acoustics, Speech, and Signal Processing (2013), pp. 186\u2013190. https:\/\/doi.org\/10.1109\/ICASSP.2013.6637634","DOI":"10.1109\/ICASSP.2013.6637634"},{"key":"2301_CR39","unstructured":"R. Rajan, Estimating pitch of speech and music using modified group delay functions, Indian Institute of Technology Madras, Ph.D. Dissertation, Department of Computer Science and Engg, IIT Madras, India (2017)"},{"key":"2301_CR40","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/j.specom.2017.02.004","volume":"89","author":"R Rajan","year":"2017","unstructured":"R. Rajan, H.A. Murthy, Two-pitch tracking in co-channel speech using modified group delay functions. Speech Commun. 89, 37\u201346 (2017)","journal-title":"Speech Commun."},{"key":"2301_CR41","doi-asserted-by":"publisher","unstructured":"R. Rajan, H.A. Murthy, Music genre classification by fusion of modified group delay and melodic features, in Twenty-Third National Conference on Communications (NCC), 2017 (2017), pp. 1\u20136. https:\/\/doi.org\/10.1109\/NCC.2017.8077056","DOI":"10.1109\/NCC.2017.8077056"},{"issue":"1","key":"2301_CR42","first-page":"1","volume":"52","author":"J Salamon","year":"2016","unstructured":"J. Salamon, J.P. Bello, Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal Process. Lett. 52(1), 1\u20135 (2016)","journal-title":"IEEE Signal Process. Lett."},{"key":"2301_CR43","doi-asserted-by":"publisher","unstructured":"J. Sebastian, P.A. Manoj Kumar, H.A. Murthy, Pitch estimation from speech using grating compression transform on modified group-delay-gram, in Proceedings of Twenty-First National Conference on Communications (NCC) (2015), pp. 1\u20136. https:\/\/doi.org\/10.1109\/NCC.2015.7084899","DOI":"10.1109\/NCC.2015.7084899"},{"key":"2301_CR44","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0245230","volume":"16","author":"M Seeland","year":"2021","unstructured":"M. Seeland, P. Mader, Multi-view classification with convolutional neural networks. PLoS ONE 16, e0245230 (2021)","journal-title":"PLoS ONE"},{"key":"2301_CR45","doi-asserted-by":"publisher","unstructured":"D.P. Shah, N.M. Jagtap, P.T. Talekar, K. Gawande, R\u0101ga recognition in Indian classical music using deep learning, in Artificial Intelligence in Music, Sound, Art and Design. EvoMUSART 2021, ed. by J. Romero, T. Martins, N. Rodr\u00edguez Fern\u00e1ndez. Lecture Notes in Computer Science, vol. 12693 (Springer, Cham, 2021). https:\/\/doi.org\/10.1007\/978-3-030-72914-1-17","DOI":"10.1007\/978-3-030-72914-1-17"},{"key":"2301_CR46","first-page":"362","volume":"1","author":"S Shetty","year":"2009","unstructured":"S. Shetty, K. Achary, R\u0101ga mining of Indian music by extracting arohana-avarohana pattern. Int. J. Recent Trends Eng. 1, 362 (2009)","journal-title":"Int. J. Recent Trends Eng."},{"key":"2301_CR47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","volume":"6","author":"C Shorten","year":"2019","unstructured":"C. Shorten, T.M. Khoshgoftaar, A survey on image data augmentation for deep learning. J. Big Data 6, 1\u201348 (2019)","journal-title":"J. Big Data"},{"key":"2301_CR48","doi-asserted-by":"publisher","first-page":"1073","DOI":"10.1016\/j.apacoust.2020.107381","volume":"167","author":"MS Sinith","year":"2020","unstructured":"M.S. Sinith, S. Tripathi, K.V.V. Murthy, R\u0101ga recognition using Fibonacci series based pitch distribution in Indian classical music. Appl. Acoust. 167, 1073\u20131081 (2020)","journal-title":"Appl. Acoust."},{"key":"2301_CR49","doi-asserted-by":"crossref","unstructured":"O. Slizovskaia, E. Gomez, G. Haro, Musical instrument recognition in user-generated videos using a multimodal convolutional neural net-work architecture, in Proceedings of ACM on International Conference on Multimedia Retrieval (2017), pp. 226\u2013232","DOI":"10.1145\/3078971.3079002"},{"key":"2301_CR50","first-page":"571","volume":"11","author":"R Sridhar","year":"2009","unstructured":"R. Sridhar, T. Geetha, R\u0101ga identification of Carnatic music for music information retrieval. Int. J. Recent Trends Eng. 11, 571\u2013574 (2009)","journal-title":"Int. J. Recent Trends Eng."},{"key":"2301_CR51","unstructured":"M. Sukhavasi, S. Adappa, Music theme recognition using CNN and self-attention, in Proceedings of Media Eval 2019 Workshop (2019), pp. 1\u20133"},{"issue":"9","key":"2301_CR52","doi-asserted-by":"publisher","first-page":"2281","DOI":"10.1109\/78.157227","volume":"40","author":"B Yegnanarayana","year":"1992","unstructured":"B. Yegnanarayana, H.A. Murthy, Significance of group delay functions in spectrum estimation. IEEE Trans. Signal Process. 40(9), 2281\u20132289 (1992)","journal-title":"IEEE Trans. Signal Process."},{"issue":"3","key":"2301_CR53","doi-asserted-by":"publisher","first-page":"610","DOI":"10.1109\/TASSP.1984.1164365","volume":"32","author":"B Yegnanarayana","year":"1984","unstructured":"B. Yegnanarayana, D.K. Saikia, T.R.M. Krishan, Significance of group delay functions in signal reconstruction from spectral magnitude or phase. IEEE Trans. Acoust. Speech Signal Process. 32(3), 610\u2013623 (1984)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"2301_CR54","doi-asserted-by":"crossref","unstructured":"M.D. Zeiler, R. Fergus, Visualizing and understanding convolutional networks, in Proceedings of Computer Vision, ECCV 2014 (Springer, 2014), pp. 818\u2013833","DOI":"10.1007\/978-3-319-10590-1_53"}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-023-02301-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00034-023-02301-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-023-02301-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,21]],"date-time":"2023-06-21T05:06:30Z","timestamp":1687323990000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00034-023-02301-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,7]]},"references-count":54,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2023,7]]}},"alternative-id":["2301"],"URL":"https:\/\/doi.org\/10.1007\/s00034-023-02301-w","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"value":"0278-081X","type":"print"},{"value":"1531-5878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,7]]},"assertion":[{"value":"4 March 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 January 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 January 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 February 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}