{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T08:37:04Z","timestamp":1711442224037},"reference-count":44,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2021,4,9]],"date-time":"2021-04-09T00:00:00Z","timestamp":1617926400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,4,9]],"date-time":"2021-04-09T00:00:00Z","timestamp":1617926400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-021-10771-w","type":"journal-article","created":{"date-parts":[[2021,4,9]],"date-time":"2021-04-09T07:03:16Z","timestamp":1617951796000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["An efficient adaptive artificial neural network based text to speech synthesizer for Hindi language"],"prefix":"10.1007","author":[{"given":"Ruchika","family":"Kumari","sequence":"first","affiliation":[]},{"given":"Amita","family":"Dev","sequence":"additional","affiliation":[]},{"given":"Ashwani","family":"Kumar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,4,9]]},"reference":[{"key":"10771_CR1","unstructured":"Abhash D, Sarmah P, Samudravijaya K, Prasanna SRM (2019) Development of Assamese text-to-speech system using deep neural network. In 2019 National Conference on Communications (NCC), pp. 1\u20135. IEEE"},{"key":"10771_CR2","doi-asserted-by":"publisher","first-page":"43157","DOI":"10.1109\/ACCESS.2018.2859631","volume":"6","author":"AH Absa","year":"2018","unstructured":"Absa AH, Deriche M, Elshafei-Ahmed M, Elhadj YM, Juang BH (2018) A hybrid unsupervised segmentation algorithm for Arabic speech using feature fusion and a genetic algorithm (July 2018). IEEE Access 6:43157\u201343169","journal-title":"IEEE Access"},{"key":"10771_CR3","unstructured":"Afzal H Md, Memon S, Gregory MA (2010) A novel approach for MFCC features extraction, In 2010 4th International Conference on Signal Processing and Communication Systems, pp. 1\u20135. IEEE, 2010."},{"issue":"2","key":"10771_CR4","doi-asserted-by":"publisher","first-page":"1171","DOI":"10.1007\/s00500-019-03952-1","volume":"24","author":"V Ansal","year":"2020","unstructured":"Ansal V (2020) ALO-optimized artificial neural network-controlled dynamic voltage restorer for compensation of voltage issues in distribution system. Soft Comput 24(2):1171\u20131184","journal-title":"Soft Comput"},{"issue":"2","key":"10771_CR5","first-page":"146","volume":"62ript to speec","author":"B Archana","year":"2016","unstructured":"Archana B, Dev A, Kumari R, Agrawal SS (2016) Labelling of Hindi speech. IETE J Res 62ript to speech conversion for Hindi la(2):146\u2013153","journal-title":"IETE J Res"},{"key":"10771_CR6","unstructured":"Athiyaa N, Grasha Jacob (2019) Spoken language identification system using MFCC features and Gaussian mixture model for tamil and telugu languages 06(04): 4243\u20134248"},{"key":"10771_CR7","doi-asserted-by":"crossref","unstructured":"Baby A, Prakash JJ, Vignesh SR, Murthy HA (2017) Deep learning techniques in tandem with signal processing cues for phonetic segmentation for text to speech synthesis in indian languages. In INTERSPEECH (pp. 3817\u20133821)","DOI":"10.21437\/Interspeech.2017-666"},{"key":"10771_CR8","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1007\/978-981-13-0224-4_27","volume-title":"Progress in advanced computing and intelligent engineering","author":"A Begum","year":"2019","unstructured":"Begum A, Askari SM, Sharma U (2019) Text-to-speech synthesis system for Mymensinghiya dialect of Bangla language. In: Progress in advanced computing and intelligent engineering. Springer, Singapore, pp 291\u2013303"},{"issue":"6","key":"10771_CR9","doi-asserted-by":"publisher","first-page":"4255","DOI":"10.1121\/1.5134781","volume":"146","author":"AC Gilbert","year":"2019","unstructured":"Gilbert AC, Wolpert M, Saito H, Kousaie S, Itzhak I, Baum SR (2019) Adaptive and selective production of syllable duration and fundamental frequency as word segmentation cues by French-English bilinguals. J Acoustical Soc America 146(6):4255\u20134272","journal-title":"J Acoustical Soc America"},{"key":"10771_CR10","doi-asserted-by":"crossref","unstructured":"Gowthul Alam MM, Baulkani S (2019) Geometric structure information based multi-objective function to increase fuzzy clustering performance with artificial and real-life data. Soft Computing 23(4):1079\u20131098","DOI":"10.1007\/s00500-018-3124-y"},{"key":"10771_CR11","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1016\/j.measurement.2019.02.053","volume":"138","author":"T Han","year":"2019","unstructured":"Han T, Liu Q, Zhang L, Tan ACC (2019) Fault feature extraction of low speed roller bearing based on Teager energy operator and CEEMD. Measurement 138:400\u2013408","journal-title":"Measurement"},{"key":"10771_CR12","volume-title":"2017 IEEE International Conference on Circuits and Systems (ICCS), pp. 447\u2013451. IEEE","author":"AF Jalin","year":"2017","unstructured":"Jalin AF, Jayakumari J (2017) Text to speech synthesis system for tamil using HMM. In: 2017 IEEE International Conference on Circuits and Systems (ICCS), pp. 447\u2013451. IEEE"},{"key":"10771_CR13","unstructured":"Javed M, Baig MM, Qazi SA (2019) Unsupervised phonetic segmentation of classical Arabic speech using forward and inverse characteristics of the vocal tract. Arab J Sci Eng:1\u20137"},{"issue":"04","key":"10771_CR14","first-page":"630","volume":"06","author":"MM Joshi","year":"2019","unstructured":"Joshi MM, Agarwal S, Shaikh S, Pitale P (2019) Text to speech synthesis for Hindi language using festival framework. International Research Journal of Engineering and Technology (IRJET) 06(04):630\u2013632","journal-title":"International Research Journal of Engineering and Technology (IRJET)"},{"key":"10771_CR15","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.specom.2015.05.003","volume":"72","author":"Y Li","year":"2015","unstructured":"Li Y, Tao J, Hirose K, Xu X, Lai W (2015) Hierarchical stress modeling and generation in mandarin for expressive text-to-speech. Speech Comm 72:59\u201373","journal-title":"Speech Comm"},{"key":"10771_CR16","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1016\/j.advengsoft.2015.01.010","volume":"83","author":"S Mirjalili","year":"2015","unstructured":"Mirjalili S (2015) The ant lion optimizer. Adv Eng Softw 83:80\u201398","journal-title":"Adv Eng Softw"},{"issue":"1","key":"10771_CR17","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/s10772-015-9320-6","volume":"19","author":"SP Panda","year":"2016","unstructured":"Panda SP, Nayak AK (2016) Automatic speech segmentation in syllable centric speech recognition system. Int J Speech Technol 19(1):9\u201318","journal-title":"Int J Speech Technol"},{"issue":"4","key":"10771_CR18","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/s10772-011-9110-8","volume":"14","author":"HA Patil","year":"2011","unstructured":"Patil HA, Viswanath S (2011) Effectiveness of Teager energy operator for epoch detection from speech signals. Int J Speech Technol 14(4):321","journal-title":"Int J Speech Technol"},{"issue":"5","key":"10771_CR19","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1080\/03772063.2018.1452642","volume":"65","author":"V Rajendran","year":"2019","unstructured":"Rajendran V, Kumar GB (2019) A robust syllable centric pronunciation model for Tamil text to speech synthesizer. IETE J Res 65(5):601\u2013612","journal-title":"IETE J Res"},{"key":"10771_CR20","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1016\/j.protcy.2016.05.242","volume":"24","author":"TM Rajisha","year":"2016","unstructured":"Rajisha TM, Sunija AP, Riyas KS (2016) Performance analysis of Malayalam language speech emotion recognition system using ANN\/SVM. Procedia Technology 24:1097\u20131104","journal-title":"Procedia Technology"},{"issue":"4","key":"10771_CR21","doi-asserted-by":"publisher","first-page":"1283","DOI":"10.1007\/s00034-015-0118-1","volume":"35","author":"B Ramani","year":"2016","unstructured":"Ramani B, Actlin Jeeva MP, Vijayalakshmi P, Nagarajan T (2016) A multi-level GMM-based cross-lingual voice conversion using language-specific mixture weights for polyglot synthesis. Circuits, Systems, and Signal Processing 35(4):1283\u20131311","journal-title":"Circuits, Systems, and Signal Processing"},{"issue":"3","key":"10771_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5815\/ijigsp.2017.03.01","volume":"9","author":"GD Ramteke","year":"2017","unstructured":"Ramteke GD, Ramteke RJ (2017) Efficient model for numerical text-to-speech synthesis system in Marathi, Hindi and English languages. International Journal of Image, Graphics & Signal Processing 9(3):1\u201313","journal-title":"International Journal of Image, Graphics & Signal Processing"},{"key":"10771_CR23","doi-asserted-by":"crossref","unstructured":"Rathod Prajakta S (2011) Script to speech conversion for Hindi language by using artificial neural network. In 2011 Nirma University International Conference on Engineering, pp. 1\u20135. IEEE","DOI":"10.1109\/NUiConE.2011.6153241"},{"issue":"1","key":"10771_CR24","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.csl.2015.04.002","volume":"34","author":"I Rebai","year":"2015","unstructured":"Rebai I, Ben Ayed Y (2015) Text-to-speech synthesis system with Arabic diacritic recognition system. Comput Speech Lang 34(1):43\u201360","journal-title":"Comput Speech Lang"},{"issue":"5","key":"10771_CR25","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1016\/j.csl.2013.02.003","volume":"27","author":"VR Reddy","year":"2013","unstructured":"Reddy VR, Rao KS (2013) Two-stage intonation modeling using feed forward neural networks for syllable based text-to-speech synthesis. Comput Speech Lang 27(5):1105\u20131126","journal-title":"Comput Speech Lang"},{"key":"10771_CR26","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1016\/j.neucom.2015.07.053","volume":"171","author":"VR Reddy","year":"2016","unstructured":"Reddy VR, Rao KS (2016) Prosody modeling for syllable based text-to-speech synthesis using feed forward neural networks. Neurocomputing. 171:1323\u20131334","journal-title":"Neurocomputing."},{"key":"10771_CR27","doi-asserted-by":"crossref","unstructured":"Rejeesh MR (2019) Interest point based face recognition using adaptive neuro fuzzy inference system. Multimedia Tools and Applications 78(16):22691\u201322710","DOI":"10.1007\/s11042-019-7577-5"},{"key":"10771_CR28","unstructured":"Rejeesh MR, Thejaswini P (2020) MOTF: Multi-objective Optimal Trilateral Filtering based partial moving frame algorithm for image denoising. Multimedia Tools and Applications 79(37-38):28411\u201328430"},{"key":"10771_CR29","doi-asserted-by":"publisher","first-page":"3186","DOI":"10.21437\/Interspeech.2016-1034","volume-title":"INTERSPEECH","author":"MS Ribeiro","year":"2016","unstructured":"Ribeiro MS, Watts O, Yamagishi J (2016) Syllable-level representations of Suprasegmental features for DNN-based text-to-speech synthesis. In: INTERSPEECH, pp 3186\u20133190"},{"key":"10771_CR30","unstructured":"Sangramsing K, Gawali B (2015) The Marathi text-to-speech synthesizer based on artificial neural networks. Int Res J Eng Technol (IRJET), 02 (08): 948\u2013953, 2015"},{"key":"10771_CR31","unstructured":"Shahzada SK, Habib T, Mumtaz B, Adeeba F, Haq E u (2016) Subjective testing of Urdu text-to-speech (TTS) system. Language & Technology:101\u2013108"},{"key":"10771_CR32","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1016\/j.csl.2018.05.003","volume":"52","author":"P Sharma","year":"2018","unstructured":"Sharma P, Abrol V, Sao AK (2018) Reducing footprint of unit selection based text-to-speech system using compressed sensing and sparse representation. Comput Speech Lang 52:191\u2013208","journal-title":"Comput Speech Lang"},{"issue":"6","key":"10771_CR33","doi-asserted-by":"publisher","first-page":"1179","DOI":"10.1109\/TMM.2006.884618","volume":"8","author":"J Shen","year":"2006","unstructured":"Shen J, Shepherd J, Ngu AHH (2006) Towards effective content-based music retrieval with multiple acoustic feature combination. IEEE Transactions on Multimedia 8(6):1179\u20131189","journal-title":"IEEE Transactions on Multimedia"},{"key":"10771_CR34","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.procs.2015.01.056","volume":"46","author":"T Shreekanth","year":"2015","unstructured":"Shreekanth T, Udayashankara V, Chandrika M (2015) Duration modelling using neural networks for hindi TTS system considering position of syllable in a word. Procedia Computer Science 46:60\u201367","journal-title":"Procedia Computer Science"},{"issue":"4","key":"10771_CR35","doi-asserted-by":"publisher","first-page":"2105","DOI":"10.1007\/s11277-019-06374-2","volume":"107","author":"J Subhashini","year":"2019","unstructured":"Subhashini J, Kumar CM (2019) An algorithm to identify syllable from a visual speech recognition system. Wirel Pers Commun 107(4):2105\u20132121","journal-title":"Wirel Pers Commun"},{"issue":"1","key":"10771_CR36","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1007\/s11277-018-6014-9","volume":"104","author":"V Sundararaj","year":"2019","unstructured":"Sundararaj V (2019) Optimal task assignment in mobile cloud computing by queue based ant-bee algorithm. Wirel Pers Commun 104(1):173\u2013197","journal-title":"Wirel Pers Commun"},{"issue":"4","key":"10771_CR37","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1504\/IJBET.2019.103242","volume":"31","author":"V Sundararaj","year":"2019","unstructured":"Sundararaj V (2019) Optimised denoising scheme via opposition-based self-adaptive learning PSO algorithm for wavelet-based ECG signal noise reduction. Int J Biomed Eng Technol 31(4):325","journal-title":"Int J Biomed Eng Technol"},{"issue":"11","key":"10771_CR38","doi-asserted-by":"publisher","first-page":"1128","DOI":"10.1002\/pip.3315","volume":"28","author":"V Sundararaj","year":"2020","unstructured":"Sundararaj V, Anoop V, Dixit P, Arjaria A, Chourasia U, Bhambri P, MR R, Sundararaj R (2020) CCGPA-MPPT: Cauchy preferential crossover-based global pollination algorithm for MPPT in photovoltaic system. Prog Photovolt Res Appl 28(11):1128\u20131145","journal-title":"Prog Photovolt Res Appl"},{"key":"10771_CR39","unstructured":"Tripathi K, Sarkar P, Sreenivasa Rao K (2016) Sentence based discourse classification for hindi story text-to-speech (TTS) system. In Proceedings of the 13th International Conference on Natural Language Processing, pp. 46\u201354."},{"issue":"3","key":"10771_CR40","first-page":"117","volume":"9","author":"S Vinu","year":"2016","unstructured":"Vinu S (2016) An efficient threshold prediction scheme for wavelet based ECG signal noise reduction using variable step size firefly algorithm. Int J Intell Eng Syst 9(3):117\u2013126","journal-title":"Int J Intell Eng Syst"},{"key":"10771_CR41","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1016\/j.cose.2018.04.009","volume":"77","author":"S Vinu","year":"2018","unstructured":"Vinu S, Muthukumar S, Kumar RS (2018) An optimal cluster formation based energy efficient dynamic scheduling hybrid MAC protocol for heavy traffic load in wireless sensor networks. Comput Secur 77:277\u2013288","journal-title":"Comput Secur"},{"key":"10771_CR42","doi-asserted-by":"crossref","unstructured":"Zhao Xufang, Douglas O'Shaughnessy (2008) A new hybrid approach for automatic speech signal segmentation using silence signal detection, energy convex hull, and spectral variation. In 2008 Canadian Conference on Electrical and Computer Engineering, pp. 000145\u2013000148. IEEE, 2008.","DOI":"10.1109\/CCECE.2008.4564512"},{"issue":"1","key":"10771_CR43","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/s00034-015-0051-3","volume":"35","author":"J Yadav","year":"2016","unstructured":"Yadav J, Sreenivasa Rao K (2016) Prosodic mapping using neural networks for emotion conversion in Hindi language. Circuits, Systems, and Signal Processing 35(1):139\u2013162","journal-title":"Circuits, Systems, and Signal Processing"},{"key":"10771_CR44","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1007\/978-3-030-37734-2_5","volume-title":"International conference on multimedia modeling","author":"S Zhou","year":"2020","unstructured":"Zhou S, Jia J, Zhang L, Wang Y, Chen W, Meng F, Fei Y, Shen J (2020) Inferring emphasis for real voice data: an attentive multimodal neural network approach. In: International conference on multimedia modeling. Springer, Cham, pp 52\u201362"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-10771-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-021-10771-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-10771-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,9]],"date-time":"2021-04-09T07:16:20Z","timestamp":1617952580000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-021-10771-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,9]]},"references-count":44,"alternative-id":["10771"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-10771-w","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,9]]},"assertion":[{"value":"25 March 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 December 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 February 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 April 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}