{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T10:06:45Z","timestamp":1764842805504,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031483080"},{"type":"electronic","value":"9783031483097"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-48309-7_42","type":"book-chapter","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:03:21Z","timestamp":1700597001000},"page":"520-534","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Addressing Effects of\u00a0Formant Dispersion and\u00a0Pitch Sensitivity for\u00a0the\u00a0Development of\u00a0Children\u2019s KWS System"],"prefix":"10.1007","author":[{"given":"Jayant Kumar","family":"Rout","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gayadhar","family":"Pradhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,22]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Anastasakos, T., McDonough, J., Schwartz, R., Makhoul, J.: A compact model for speaker-adaptive training. In: Proceedings of International Conference on Spoken Language Processing, vol. 2, pp. 1137\u20131140 (1996)","key":"42_CR1","DOI":"10.21437\/ICSLP.1996-253"},{"doi-asserted-by":"crossref","unstructured":"Batliner, A., et al.: The PF-STAR children\u2019s speech corpus. In: Proceedings of INTERSPEECH, pp. 2761\u20132764 (2005)","key":"42_CR2","DOI":"10.21437\/Interspeech.2005-705"},{"doi-asserted-by":"crossref","unstructured":"Burget, L., et al.: Indexing and search methods for spoken documents. In: Proceedings of 9th International Conference on Text, Speech and Dialogue, pp. 351\u2013358 (2006)","key":"42_CR3","DOI":"10.1007\/11846406_44"},{"issue":"1","key":"42_CR4","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1121\/1.404271","volume":"92","author":"D Byrd","year":"1992","unstructured":"Byrd, D.: Preliminary results on speaker-dependent variation in the TIMIT database. J. Acoust. Soc. Am. 92(1), 593\u2013596 (1992)","journal-title":"J. Acoust. Soc. Am."},{"key":"42_CR5","first-page":"1","volume":"257","author":"S Eguchi","year":"1969","unstructured":"Eguchi, S., Hirsh, I.J.: Development of speech sounds in children. Acta Otolaryngol. Suppl. 257, 1\u201351 (1969)","journal-title":"Acta Otolaryngol. Suppl."},{"doi-asserted-by":"crossref","unstructured":"Fraser, N.M.: Voice-based dialogue in the real world. In: Proceedings of Human Comfort and Security of Information Systems, pp. 75\u201386 (1997)","key":"42_CR6","DOI":"10.1007\/978-3-642-60665-6_9"},{"issue":"4","key":"42_CR7","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1109\/89.848223","volume":"8","author":"MJF Gales","year":"2000","unstructured":"Gales, M.J.F.: Cluster adaptive training of hidden Markov models. IEEE Trans. Speech Audio Process. 8(4), 417\u2013428 (2000)","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"2","key":"42_CR8","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1109\/89.279278","volume":"2","author":"JL Gauvain","year":"1994","unstructured":"Gauvain, J.L., Lee, C.H.: Maximum a-posteriori estimation for multivariate Gaussian mixture observations of Markov chains. IEEE Trans. Speech Audio Process. 2(2), 291\u2013298 (1994)","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"10\u201311","key":"42_CR9","doi-asserted-by":"publisher","first-page":"847","DOI":"10.1016\/j.specom.2007.01.002","volume":"49","author":"M Gerosa","year":"2007","unstructured":"Gerosa, M., Giuliani, D., Brugnara, F.: Acoustic variability and automatic recognition of children\u2019s speech. Speech Commun. 49(10\u201311), 847\u2013860 (2007)","journal-title":"Speech Commun."},{"issue":"1","key":"42_CR10","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1016\/j.csl.2005.05.002","volume":"20","author":"D Giuliani","year":"2006","unstructured":"Giuliani, D., Gerosa, M., Brugnara, F.: Improved automatic speech recognition through speaker normalization. Comput. Speech Lang. 20(1), 107\u2013123 (2006)","journal-title":"Comput. Speech Lang."},{"issue":"5","key":"42_CR11","doi-asserted-by":"publisher","first-page":"1593","DOI":"10.1007\/s00034-015-0129-y","volume":"35","author":"V Joshi","year":"2016","unstructured":"Joshi, V., Prasad, N.V., Umesh, S.: Modified mean and variance normalization: transforming to utterance-specific estimates. Circ. Syst. Signal Process. 35(5), 1593\u20131609 (2016)","journal-title":"Circ. Syst. Signal Process."},{"doi-asserted-by":"crossref","unstructured":"Kumar, A., Shahnawazuddin, S., Pradhan, G.: Non-local estimation of speech signal for vowel onset point detection in varied environments. In: Proceedings of INTERSPEECH, pp. 429\u2013433 (2017)","key":"42_CR12","DOI":"10.21437\/Interspeech.2017-624"},{"issue":"1","key":"42_CR13","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1109\/89.650310","volume":"6","author":"L Lee","year":"1998","unstructured":"Lee, L., Rose, R.: A frequency warping approach to speaker normalization. IEEE Trans. Speech Audio Process. 6(1), 49\u201360 (1998)","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"3","key":"42_CR14","doi-asserted-by":"publisher","first-page":"1455","DOI":"10.1121\/1.426686","volume":"105","author":"S Lee","year":"1999","unstructured":"Lee, S., Potamianos, A., Narayanan, S.S.: Acoustics of children\u2019s speech: developmental changes of temporal and spectral parameters. J. Acoust. Soc. Am. 105(3), 1455\u20131468 (1999)","journal-title":"J. Acoust. Soc. Am."},{"issue":"4","key":"42_CR15","doi-asserted-by":"publisher","first-page":"1892","DOI":"10.1007\/s00034-020-01565-w","volume":"40","author":"K Maity","year":"2021","unstructured":"Maity, K., Pradhan, G., Singh, J.P.: A pitch and noise robust keyword spotting system using SMAC features with prosody modification. Circ. Syst. Signal Process. 40(4), 1892\u20131904 (2021)","journal-title":"Circ. Syst. Signal Process."},{"issue":"8","key":"42_CR16","doi-asserted-by":"publisher","first-page":"1338","DOI":"10.1109\/5.880087","volume":"88","author":"J Makhoul","year":"2000","unstructured":"Makhoul, J., et al.: Speech and language technologies for audio indexing and retrieval. Proc. IEEE 88(8), 1338\u20131353 (2000)","journal-title":"Proc. IEEE"},{"doi-asserted-by":"crossref","unstructured":"Mamou, J., Ramabhadran, B., Siohan, O.: Vocabulary independent spoken term detection. In: Proceedings of the 30th Annual International Conference on Research and Development in Information Retrieval, pp. 615\u2013622 (2007)","key":"42_CR17","DOI":"10.1145\/1277741.1277847"},{"doi-asserted-by":"crossref","unstructured":"Michaely, A.H., Zhang, X., Simko, G., Parada, C., Aleksic, P.: Keyword spotting for google assistant using contextual speech recognition. In: Proceedings of Automatic Speech Recognition and Understanding Workshop, pp. 272\u2013278 (2017)","key":"42_CR18","DOI":"10.1109\/ASRU.2017.8268946"},{"key":"42_CR19","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/j.patrec.2021.07.015","volume":"150","author":"B Pattanayak","year":"2021","unstructured":"Pattanayak, B., Pradhan, G.: Pitch-robust acoustic feature using single frequency filtering for children\u2019s KWS. Pattern Recogn. Lett. 150, 183\u2013188 (2021)","journal-title":"Pattern Recogn. Lett."},{"issue":"5","key":"42_CR20","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1049\/iet-spr.2019.0027","volume":"13","author":"B Pattanayak","year":"2019","unstructured":"Pattanayak, B., Rout, J.K., Pradhan, G.: Adaptive spectral smoothening for development of robust keyword spotting system. IET Signal Process. 13(5), 544\u2013550 (2019)","journal-title":"IET Signal Process."},{"issue":"6","key":"42_CR21","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1109\/TSA.2003.818026","volume":"11","author":"A Potamianos","year":"2003","unstructured":"Potamianos, A., Narayanan, S.: Robust recognition of children\u2019s speech. IEEE Trans. Speech Audio Process. 11(6), 603\u2013616 (2003)","journal-title":"IEEE Trans. Speech Audio Process."},{"doi-asserted-by":"crossref","unstructured":"Potamianos, A., Narayanan, S., Lee, S.: Automatic speech recognition for children. In: Eurospeech, vol. 97, pp. 2371\u20132374 (1997)","key":"42_CR22","DOI":"10.21437\/Eurospeech.1997-623"},{"unstructured":"Povey, D., et al.: The kaldi speech recognition toolkit. In: Proceedings of Workshop on Automatic Speech Recognition and Understanding (2011)","key":"42_CR23"},{"doi-asserted-by":"crossref","unstructured":"Prasanna, S., Govind, D., Rao, K.S., Yegnanarayana, B.: Fast prosody modification using instants of significant excitation. In: Proceedings of Speech Prosody (2010)","key":"42_CR24","DOI":"10.21437\/SpeechProsody.2010-126"},{"doi-asserted-by":"crossref","unstructured":"Rath, S.P., Povey, D., Vesel\u1ef3, K., Cernock\u1ef3, J.: Improved feature processing for deep neural networks. In: Proceedings of INTERSPEECH, pp. 109\u2013113 (2013)","key":"42_CR25","DOI":"10.21437\/Interspeech.2013-48"},{"doi-asserted-by":"crossref","unstructured":"Robinson, T., Fransen, J., Pye, D., Foote, J., Renals, S.: WSJCAM0: a British English speech corpus for large vocabulary continuous speech recognition. In: Proceedings of International Conference on Acoustics, Speech and Signal Processing, vol. 1, pp. 81\u201384 (1995)","key":"42_CR26","DOI":"10.1109\/ICASSP.1995.479278"},{"issue":"5","key":"42_CR27","doi-asserted-by":"publisher","first-page":"3023","DOI":"10.1007\/s00034-021-01923-2","volume":"41","author":"JK Rout","year":"2022","unstructured":"Rout, J.K., Pradhan, G.: Data-adaptive single-pole filtering of magnitude spectra for robust keyword spotting. Circ. Syst. Signal Process. 41(5), 3023\u20133039 (2022)","journal-title":"Circ. Syst. Signal Process."},{"key":"42_CR28","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1016\/j.specom.2022.09.004","volume":"144","author":"JK Rout","year":"2022","unstructured":"Rout, J.K., Pradhan, G.: Enhancement of formant regions in magnitude spectra to develop children\u2019s KWS system in zero resource scenario. Speech Commun. 144, 101\u2013109 (2022)","journal-title":"Speech Commun."},{"doi-asserted-by":"crossref","unstructured":"Russell, M., D\u2019Arcy, S.: Challenges for computer recognition of children\u2019s speech. In: Proceedings of Workshop on Speech and Language Technology in Education (2007)","key":"42_CR29","DOI":"10.21437\/SLaTE.2007-26"},{"key":"42_CR30","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.dsp.2018.12.011","volume":"86","author":"S Shahnawazuddin","year":"2018","unstructured":"Shahnawazuddin, S., Maity, K., Pradhan, G.: Improving the performance of keyword spotting system for children\u2019s speech through prosody modification. Dig. Signal Process. 86, 11\u201318 (2018)","journal-title":"Dig. Signal Process."},{"key":"42_CR31","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.csl.2017.10.007","volume":"48","author":"R Sinha","year":"2018","unstructured":"Sinha, R., Shahnawazuddin, S.: Assessment of pitch-adaptive front-end signal processing for children\u2019s speech recognition. Comput. Speech Lang. 48, 103\u2013121 (2018)","journal-title":"Comput. Speech Lang."},{"unstructured":"Warren, R.L.: Broadcast speech recognition system for keyword monitoring, US Patent 6332120 (2001)","key":"42_CR32"},{"doi-asserted-by":"crossref","unstructured":"Wegmann, S., Faria, A., Janin, A., Riedhammer, K., Morgan, N.: The tao of ATWV: probing the mysteries of keyword search performance. In: Proceedings of Workshop on Automatic Speech Recognition and Understanding, pp. 192\u2013197 (2013)","key":"42_CR33","DOI":"10.1109\/ASRU.2013.6707728"},{"doi-asserted-by":"crossref","unstructured":"Yadav, I.C., Kumar, A., Shahnawazuddin, S., Pradhan, G.: Non-uniform spectral smoothing for robust children\u2019s speech recognition. In: Proceedings of INTERSPEECH, pp. 1601\u20131605 (2018)","key":"42_CR34","DOI":"10.21437\/Interspeech.2018-1828"},{"issue":"12","key":"42_CR35","doi-asserted-by":"publisher","first-page":"1822","DOI":"10.1109\/LSP.2019.2950763","volume":"26","author":"IC Yadav","year":"2019","unstructured":"Yadav, I.C., Pradhan, G.: Significance of pitch-based spectral normalization for children\u2019s speech recognition. IEEE Signal Process. Lett. 26(12), 1822\u20131826 (2019)","journal-title":"IEEE Signal Process. Lett."},{"key":"42_CR36","first-page":"102","volume":"109","author":"IC Yadav","year":"2021","unstructured":"Yadav, I.C., Pradhan, G.: Pitch and noise normalized acoustic feature for children\u2019s ASR. Dig. Signal Process. 109, 102\u2013922 (2021)","journal-title":"Dig. Signal Process."}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-48309-7_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T14:50:24Z","timestamp":1730559024000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-48309-7_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031483080","9783031483097"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-48309-7_42","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Dharwad","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iitdh.ac.in\/specom-2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"174","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"94","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"54% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}