{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T06:20:40Z","timestamp":1773469240559,"version":"3.50.1"},"reference-count":63,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T00:00:00Z","timestamp":1755129600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T00:00:00Z","timestamp":1755129600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"SERB IMPRINT IIC.2","award":["IMC\/2020\/000003"],"award-info":[{"award-number":["IMC\/2020\/000003"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Circuits Syst Signal Process"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s00034-025-03278-4","type":"journal-article","created":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T12:03:43Z","timestamp":1755173023000},"page":"1237-1269","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring Synthesized Electroglottograph Signals for F0 Estimation using Deep Feature Loss Network"],"prefix":"10.1007","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6862-2162","authenticated-orcid":false,"given":"Supritha M.","family":"Shetty","sequence":"first","affiliation":[]},{"given":"K. T.","family":"Deepak","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,8,14]]},"reference":[{"key":"3278_CR1","doi-asserted-by":"crossref","unstructured":"L. Ardaillon, A. Roebel, Fully-convolutional network for pitch estimation of speech signals, in Interspeech 2019 (2019)","DOI":"10.21437\/Interspeech.2019-2815"},{"key":"3278_CR2","doi-asserted-by":"crossref","unstructured":"L. Attorresi, D. Salvi, C. Borrelli, P. Bestagini, S. Tubaro, Combining automatic speaker verification and prosody analysis for synthetic speech detection, in International Conference on Pattern Recognition (Springer, 2022), pp. 247\u2013263","DOI":"10.1007\/978-3-031-37742-6_21"},{"key":"3278_CR3","doi-asserted-by":"crossref","unstructured":"O. Babacan, T. Drugman, N. d\u2019Alessandro, N. Henrich, T. Dutoit, A comparative study of pitch extraction algorithms on a large variety of singing sounds, in 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE, 2013), pp. 7815\u20137819","DOI":"10.1109\/ICASSP.2013.6639185"},{"key":"3278_CR4","doi-asserted-by":"publisher","first-page":"1417","DOI":"10.1121\/1.1850031","volume":"117","author":"NH Bernardoni","year":"2005","unstructured":"N.H. Bernardoni, C. d\u2019Alessandro, B. Doval, M. Castellengo, Glottal open quotient in singing: Measurements and correlation with laryngeal mechanisms, vocal intensity, and fundamental frequency. J. Acoust. Soc. Am. 117, 1417\u20131430 (2005)","journal-title":"J. Acoust. Soc. Am."},{"key":"3278_CR5","doi-asserted-by":"crossref","unstructured":"F. Burkhardt, A. Paeschke, M. Rolfes, W.F. Sendlmeier, B. Weiss, et\u00a0al. A database of German emotional speech, in Interspeech (2005), vol.\u00a05, pp. 1517\u20131520","DOI":"10.21437\/Interspeech.2005-446"},{"key":"3278_CR6","doi-asserted-by":"publisher","first-page":"1638","DOI":"10.1121\/1.2951592","volume":"124","author":"A Camacho","year":"2008","unstructured":"A. Camacho, J.G. Harris, A sawtooth waveform inspired pitch estimator for speech and music. J. Acoust. Soc. Am. 124, 1638\u201352 (2008)","journal-title":"J. Acoust. Soc. Am."},{"key":"3278_CR7","doi-asserted-by":"publisher","first-page":"469","DOI":"10.3390\/app13010469","volume":"13","author":"L Chen","year":"2022","unstructured":"L. Chen, Z. Mo, J. Ren, C. Cui, Q. Zhao, An electroglottograph auxiliary neural network for target speaker extraction. Appl. Sci. 13, 469 (2022)","journal-title":"Appl. Sci."},{"key":"3278_CR8","doi-asserted-by":"publisher","first-page":"4338","DOI":"10.3390\/app12094338","volume":"12","author":"L Chen","year":"2022","unstructured":"L. Chen, J. Ren, X. Mao, Q. Zhao, Electroglottograph-based speech emotion recognition via cross-modal distillation. Appl. Sci. 12, 4338 (2022)","journal-title":"Appl. Sci."},{"key":"3278_CR9","doi-asserted-by":"crossref","unstructured":"Y. Cheng, H.C. Leung, Speaker verification using fundamental frequency, in ICSLP (1998)","DOI":"10.21437\/ICSLP.1998-220"},{"key":"3278_CR10","doi-asserted-by":"publisher","first-page":"1917","DOI":"10.1121\/1.1458024","volume":"111","author":"AD Cheveign\u00e9","year":"2002","unstructured":"A.D. Cheveign\u00e9, H. Kawahara, Yin, a fundamental frequency estimator for speech and music. J. Acoust. Soc. Am. 111, 1917\u20131930 (2002)","journal-title":"J. Acoust. Soc. Am."},{"key":"3278_CR11","doi-asserted-by":"crossref","unstructured":"W. Chu, A. Alwan, Reducing f0 frame error of f0 tracking algorithms under noisy conditions with an unvoiced\/voiced classification frontend, in 2009 IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE, 2009), pp. 3969\u20133972","DOI":"10.1109\/ICASSP.2009.4960497"},{"key":"3278_CR12","doi-asserted-by":"crossref","unstructured":"K.T. Deepak, P. Kulkarni, U. Mudenagudi, S.R.M. Prasanna, Glottal instants extraction from speech signal using generative adversarial network, in ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2019), pp. 5946\u20135950","DOI":"10.1109\/ICASSP.2019.8683298"},{"key":"3278_CR13","doi-asserted-by":"crossref","unstructured":"M. Dong, J. Wu, J. Luan, Vocal pitch extraction in polyphonic music using convolutional residual network, in 20th Annual Conference of the International Speech Communication Association (2019), pp. 2010\u20132014","DOI":"10.21437\/Interspeech.2019-2286"},{"key":"3278_CR14","doi-asserted-by":"crossref","unstructured":"T. Drugman, A. Alwan, Joint robust voicing detection and pitch estimation based on residual harmonics, in Interspeech (2011), pp. 1973\u20131976","DOI":"10.21437\/Interspeech.2011-519"},{"key":"3278_CR15","doi-asserted-by":"crossref","unstructured":"T. Drugman, T. Dutoit, Glottal closure and opening instant detection from speech signals (2009)","DOI":"10.21437\/Interspeech.2009-47"},{"key":"3278_CR16","unstructured":"P. Fabre, Un procede electrique percutane d\u2019inscrition de l\u2019accolement glottique au cours de la phonation: glottographie de haute frequence. premiers resultats. Bulletin de l\u2019Acad\u00e9mie nationale de m\u00e9decine (1957)"},{"key":"3278_CR17","doi-asserted-by":"crossref","unstructured":"F.G. Germain, Q. Chen, V. Koltun, Speech denoising with deep feature losses, in Interspeech (2019)","DOI":"10.21437\/Interspeech.2019-1924"},{"key":"3278_CR18","doi-asserted-by":"publisher","first-page":"1118","DOI":"10.1109\/TASLP.2020.2982285","volume":"28","author":"B Gfeller","year":"2020","unstructured":"B. Gfeller, C. Frank, D. Roblek, M. Sharifi, M. Tagliasacchi, M. Velimirovi\u0107, Spice: self-supervised pitch estimation. IEEE\/ACM Trans. Audio Speech Lang. Process. 28, 1118\u20131128 (2020)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"3278_CR19","doi-asserted-by":"crossref","unstructured":"P. Ghahremani, B. BabaAli, D. Povey, K. Riedhammer, J. Trmal, S. Khudanpur, A pitch extraction algorithm tuned for automatic speech recognition, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2014), pp. 2494\u20132498","DOI":"10.1109\/ICASSP.2014.6854049"},{"key":"3278_CR20","doi-asserted-by":"publisher","first-page":"2158","DOI":"10.1109\/TASLP.2014.2363410","volume":"22","author":"K Han","year":"2014","unstructured":"K. Han, D. Wang, Neural network based pitch tracking in very noisy speech. IEEE Trans. Audio Speech Lang. Process. 22, 2158\u20132168 (2014)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"3278_CR21","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1016\/j.jvoice.2018.01.003","volume":"33","author":"C Herbst","year":"2018","unstructured":"C. Herbst, J.C. Dunn, Fundamental frequency estimation of low-quality electroglottographic signals. J. Voice 33, 401\u2013411 (2018)","journal-title":"J. Voice"},{"key":"3278_CR22","unstructured":"Y. Hosada, A. Kawamura, Y. Iiguni, Pitch estimation algorithm for narrowband speech signal using phase differences between harmonics, in Proceedings, APSIPA Annual Summit and Conference (2021), pp. 920\u2013925"},{"issue":"2","key":"3278_CR23","first-page":"310","volume":"18","author":"CL Hsu","year":"2009","unstructured":"C.L. Hsu, J.S.R. Jang, On the improvement of singing voice separation for monaural recordings using the MIR-1k dataset. IEEE Trans. Audio Speech Lang. Process. 18(2), 310\u2013319 (2009)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"3278_CR24","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1109\/TASL.2012.2215589","volume":"21","author":"F Huang","year":"2013","unstructured":"F. Huang, T. Lee, Pitch estimation in noisy speech using accumulated peak spectrum and sparse estimation technique. IEEE Trans. Audio Speech Lang. Process. 21, 99\u2013109 (2013)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"3278_CR25","doi-asserted-by":"crossref","unstructured":"Z. Imani, S.J. Kabudian, A neural network-based optimal nonlinear fusion of speech pitch detection algorithms, in Conference on Knowledge-Based Engineering and Innovation (2019), pp. 794\u2013798","DOI":"10.1109\/KBEI.2019.8734917"},{"key":"3278_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.wocn.2018.07.001","volume":"71","author":"Y Jadoul","year":"2018","unstructured":"Y. Jadoul, B. Thompson, B. De Boer, Introducing parselmouth: a python interface to Praat. J. Phon. 71, 1\u201315 (2018)","journal-title":"J. Phon."},{"issue":"4","key":"3278_CR27","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1016\/S0030-6665(05)70238-3","volume":"33","author":"J Jiang","year":"2000","unstructured":"J. Jiang, E. Lin, D.G. Hanson, Vocal fold physiology. Otolaryngol. Clin. North Am. 33(4), 699\u2013718 (2000)","journal-title":"Otolaryngol. Clin. North Am."},{"key":"3278_CR28","doi-asserted-by":"crossref","unstructured":"J. Johnson, A. Alahi, L. Fei-Fei, Perceptual losses for real-time style transfer and super-resolution, in Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part II 14 (Springer, 2016), pp. 694\u2013711","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"3278_CR29","doi-asserted-by":"crossref","unstructured":"S.R. Kadiri, B. Yegnanarayana, Estimation of fundamental frequency from singing voice using harmonics of impulse-like excitation source, in Interspeech (2018)","DOI":"10.21437\/Interspeech.2018-2495"},{"key":"3278_CR30","doi-asserted-by":"crossref","unstructured":"K. Kasi, S.A. Zahorian, Yet another algorithm for pitch tracking, in IEEE International Conference on Acoustics, Speech, and Signal Processing (2002)","DOI":"10.1109\/ICASSP.2002.1005751"},{"key":"3278_CR31","doi-asserted-by":"crossref","unstructured":"J.W. Kim, J. Salamon, P. Li, J.P. Bello, Crepe: a convolutional representation for pitch estimation, in ICASSP (2018)","DOI":"10.1109\/ICASSP.2018.8461329"},{"key":"3278_CR32","unstructured":"J. Kominek, A.W. Black, The CMU arctic speech databases. ISCA Speech Synthesis Workshop (2004)"},{"issue":"6","key":"3278_CR33","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1016\/j.jvoice.2017.01.016","volume":"31","author":"LM Kopf","year":"2017","unstructured":"L.M. Kopf, C. Jackson-Menaldi, A.D. Rubin, J. Skeffington, E.J. Hunter, M.D. Skowronski, R. Shrivastav, Pitch strength as an outcome measure for treatment of dysphonia. J. Voice 31(6), 691\u2013696 (2017)","journal-title":"J. Voice"},{"key":"3278_CR34","doi-asserted-by":"crossref","unstructured":"S. Liu, S. Hu, X. Liu, H. Meng, On the use of pitch features for disordered speech recognition, in Interspeech (2019)","DOI":"10.21437\/Interspeech.2019-2609"},{"key":"3278_CR35","unstructured":"A.L. Maas, A.Y. Hannun, A.Y. Ng, et\u00a0al. Rectifier nonlinearities improve neural network acoustic models, in Proc. ICML (Atlanta, 2013), vol.\u00a030, p.\u00a03."},{"key":"3278_CR36","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1109\/TAU.1972.1162410","volume":"20","author":"JD Markel","year":"1972","unstructured":"J.D. Markel, The SIFT algorithm for fundamental frequency estimation. IEEE Trans. Audio Electroacoust. 20, 367\u2013377 (1972)","journal-title":"IEEE Trans. Audio Electroacoust."},{"issue":"10","key":"3278_CR37","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1016\/j.specom.2008.04.010","volume":"50","author":"L Mary","year":"2008","unstructured":"L. Mary, B. Yegnanarayana, Extraction and representation of prosodic features for language and speaker recognition. Speech Commun. 50(10), 782\u2013796 (2008)","journal-title":"Speech Commun."},{"key":"3278_CR38","doi-asserted-by":"crossref","unstructured":"M. Mauch, S. Dixon, pYIN: a fundamental frequency estimator using probabilistic threshold distributions, in 2014 IEEE international conference on acoustics, speech and signal processing (ICASSP) (IEEE, 2014), pp. 659\u2013663","DOI":"10.1109\/ICASSP.2014.6853678"},{"key":"3278_CR39","unstructured":"M. Morrison, C. Hsieh, N. Pruyne, B. Pardo, Cross-domain neural pitch and periodicity estimation. arXiv preprint arXiv:2301.12258 (2023)"},{"issue":"3","key":"3278_CR40","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1016\/j.specom.2007.09.003","volume":"50","author":"T Nakatani","year":"2008","unstructured":"T. Nakatani, S. Amano, T. Irino, K. Ishizuka, T. Kondo, A method for fundamental frequency estimation and voicing decision: application to infant utterances recorded in real acoustical environments. Speech Commun. 50(3), 203\u2013214 (2008)","journal-title":"Speech Commun."},{"key":"3278_CR41","doi-asserted-by":"crossref","unstructured":"J.K. Nielsen, T.L. Jensen, J.R. Jensen, M.G. Christensen, S.H. Jensen, Fast and statistically efficient fundamental frequency estimation, in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE, 2016), pp. 86\u201390","DOI":"10.1109\/ICASSP.2016.7471642"},{"key":"3278_CR42","doi-asserted-by":"crossref","unstructured":"V. Pannala, G. Aneeja, S.R. Kadiri, B. Yegnanarayana, Robust estimation of fundamental frequency using single frequency filtering approach, in Interspeech (2016), pp. 8\u201312","DOI":"10.21437\/Interspeech.2016-1401"},{"key":"3278_CR43","doi-asserted-by":"crossref","unstructured":"S. Pascual, A. Bonafonte, J. Serr\u00e0, Segan: Speech enhancement generative adversarial network, in Interpeech (2017)","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"3278_CR44","doi-asserted-by":"crossref","unstructured":"G. Pirker, M. Wohlmayr, S. Petrik, F. Pernkopf, A pitch tracking corpus with evaluation on multipitch tracking scenario, in Interspeech (2011)","DOI":"10.21437\/Interspeech.2011-317"},{"issue":"12","key":"3278_CR45","first-page":"30","volume":"8","author":"F Plante","year":"1995","unstructured":"F. Plante, G. Meyer, W. Ainsworth, A pitch extraction reference database. Children 8(12), 30\u201350 (1995)","journal-title":"Children"},{"issue":"4","key":"3278_CR46","doi-asserted-by":"publisher","first-page":"1247","DOI":"10.1109\/TASL.2006.889797","volume":"15","author":"GE Poliner","year":"2007","unstructured":"G.E. Poliner, D.P. Ellis, A.F. Ehmann, E. G\u00f3mez, S. Streich, B. Ong, Melody transcription from music audio: approaches and evaluation. IEEE Trans. Audio Speech Lang. Process. 15(4), 1247\u20131256 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"12","key":"3278_CR47","doi-asserted-by":"publisher","first-page":"2183","DOI":"10.1109\/TASLP.2019.2942140","volume":"27","author":"A Prathosh","year":"2019","unstructured":"A. Prathosh, V. Srivastava, M. Mishra, Adversarial approximate inference for speech to electroglottograph conversion. IEEE\/ACM Trans. Audio Speech Lang. Process. 27(12), 2183\u20132196 (2019)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"3278_CR48","unstructured":"M. P\u00fctzer, J. Koreman, A German database of patterns of pathological vocal fold vibration. Phonus 3 Institute of Phonetics, University of the Saarland (1997), pp. 143\u2013153"},{"key":"3278_CR49","unstructured":"C. Raffel, B. McFee, E.J. Humphrey, J. Salamon, O. Nieto, D. Liang, D.P.W. Ellis, MIR_EVAL: a transparent implementation of common MIR metrics, in ISMIR (2014)"},{"issue":"8","key":"3278_CR50","doi-asserted-by":"publisher","first-page":"1133","DOI":"10.1109\/LSP.2017.2712646","volume":"24","author":"MK Reddy","year":"2017","unstructured":"M.K. Reddy, K.S. Rao, Robust pitch extraction method for the hmm-based speech synthesis system. IEEE Signal Process. Lett. 24(8), 1133\u20131137 (2017)","journal-title":"IEEE Signal Process. Lett."},{"key":"3278_CR51","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101029","volume":"60","author":"MK Reddy","year":"2020","unstructured":"M.K. Reddy, K.S. Roa, Excitation modelling using epoch features for statistical parametric speech synthesis. Comput. Speech Lang. 60, 101029 (2020)","journal-title":"Comput. Speech Lang."},{"issue":"1","key":"3278_CR52","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1007\/s00034-020-01468-w","volume":"40","author":"P Rengaswamy","year":"2021","unstructured":"P. Rengaswamy, M.G. Reddy, K.S. Rao, P. Dasgupta, hf0: a hybrid pitch extraction method for multimodal voice. Circuits Syst. Signal Process. 40(1), 262\u2013275 (2021)","journal-title":"Circuits Syst. Signal Process."},{"key":"3278_CR53","unstructured":"A. Riou, S. Lattner, G. Hadjeres, G. Peeters, Pesto: pitch estimation with self-supervised transposition-equivariant objective, in International Society for Music Information Retrieval Conference (ISMIR 2023) (2023)"},{"key":"3278_CR54","unstructured":"J. Salamon, R.M. Bittner, J. Bonada, J.J. Bosch, E. G\u00f3mez\u00a0Guti\u00e9rrez, J.P. Bello, An analysis\/synthesis framework for automatic f0 annotation of multitrack datasets, in Hu X, Cunningham SJ, Turnbull D, Duan Z. ISMIR 2017 Proceedings of the 18th International Society for Music Information Retrieval Conference; 2017 Oct 23\u201327; Suzhou, China. [Suzhou]: ISMIR; 2017. International Society for Music Information Retrieval (ISMIR) (2017)"},{"key":"3278_CR55","doi-asserted-by":"crossref","unstructured":"X. Shao, B.P. Milner, S.J. Cox, Integrated pitch and MFCC extraction for speech reconstruction and speech recognition applications, in INTERSPEECH (2003), pp. 1725\u20131728","DOI":"10.21437\/Eurospeech.2003-24"},{"key":"3278_CR56","doi-asserted-by":"crossref","unstructured":"S.M. Shetty, S. Durgesht, K.T. Deepak, Glottal instants extraction from speech signal using deep feature loss, in IEEE International Conference on Signal Processing and Communications (SPCOM) (2022)","DOI":"10.1109\/SPCOM55316.2022.9840808"},{"key":"3278_CR57","doi-asserted-by":"crossref","unstructured":"S.M. Shetty, S. Revankar, N.C. Iyer, K.T. Deepak, F0 estimation from telephone speech using deep feature loss, in ICASSP (2023)","DOI":"10.1109\/ICASSP49357.2023.10094916"},{"key":"3278_CR58","doi-asserted-by":"crossref","unstructured":"S. Singh, R. Wang, Y. Qiu, Deepf0: end-to-end fundamental frequency estimation for music and speech signals, in ICASSP (2021), pp. 369\u2013372","DOI":"10.1109\/ICASSP39728.2021.9414050"},{"key":"3278_CR59","doi-asserted-by":"crossref","unstructured":"H. Su, H. Zhang, X. Zhang, G. Gao, Convolutional neural network for robust pitch determination. ICASSP pp. 579\u2013583 (2016)","DOI":"10.1109\/ICASSP.2016.7471741"},{"key":"3278_CR60","unstructured":"D. Talkin, A robust algorithm for pitch tracking (rapt). Speech Coding and Synthesis pp. 497\u2013518 (1995)"},{"issue":"3","key":"3278_CR61","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","volume":"12","author":"A Varga","year":"1993","unstructured":"A. Varga, H.J. Steeneken, Assessment for automatic speech recognition: Noisex-92: A database and an experiment to study the effect of additive noise on speech recognition systems. Speech Commun. 12(3), 247\u2013251 (1993)","journal-title":"Speech Commun."},{"key":"3278_CR62","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1109\/TASL.2008.2012194","volume":"17","author":"B Yegnanarayana","year":"2009","unstructured":"B. Yegnanarayana, K.S.R. Murty, Event-based instantaneous fundamental frequency estimation from speech signals. IEEE Trans. Audio Speech Lang. Process. 17, 614\u2013624 (2009)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"3278_CR63","unstructured":"F. Yu, V. Koltun, Multi-scale context aggregation by dilated convolutions, in Proceedings of International Conference on Learning Representations (ICLR) (2016)"}],"container-title":["Circuits, Systems, and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-025-03278-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00034-025-03278-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00034-025-03278-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T05:40:39Z","timestamp":1773466839000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00034-025-03278-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,14]]},"references-count":63,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["3278"],"URL":"https:\/\/doi.org\/10.1007\/s00034-025-03278-4","relation":{},"ISSN":["0278-081X","1531-5878"],"issn-type":[{"value":"0278-081X","type":"print"},{"value":"1531-5878","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,14]]},"assertion":[{"value":"19 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 July 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 August 2025","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 are no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}