{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T17:59:26Z","timestamp":1742925566878,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"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_39","type":"book-chapter","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:03:21Z","timestamp":1700597001000},"page":"483-493","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Effect of\u00a0Linear Prediction Order to\u00a0Modify Formant Locations for\u00a0Children Speech Recognition"],"prefix":"10.1007","author":[{"given":"Udara Laxman","family":"Kumar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mikko","family":"Kurimo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hemant Kumar","family":"Kathania","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,22]]},"reference":[{"key":"39_CR1","doi-asserted-by":"publisher","unstructured":"Ahmad, W., Shahnawazuddin, S., Kathania, H., Pradhan, G., Samaddar, A.: Improving children\u2019s speech recognition through explicit pitch scaling based on iterative spectrogram inversion. In: Proceedings of INTERSPEECH 2017, pp. 2391\u20132395 (2017). https:\/\/doi.org\/10.21437\/INTERSPEECH.2017-302","DOI":"10.21437\/INTERSPEECH.2017-302"},{"key":"39_CR2","doi-asserted-by":"crossref","unstructured":"Batliner, A., et al.: The PF_STAR children\u2019s speech corpus. In: Proceedings of INTERSPEECH, pp. 2761\u20132764 (2005)","DOI":"10.21437\/Interspeech.2005-705"},{"issue":"9","key":"39_CR3","doi-asserted-by":"publisher","first-page":"4419","DOI":"10.3390\/app12094419","volume":"12","author":"V Bhardwaj","year":"2022","unstructured":"Bhardwaj, V., et al.: Automatic speech recognition (ASR) systems for children: a systematic literature review. Appl. Sci. 12(9), 4419 (2022)","journal-title":"Appl. Sci."},{"issue":"6","key":"39_CR4","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1109\/89.725321","volume":"6","author":"T Claes","year":"1998","unstructured":"Claes, T., Dologlou, I., ten Bosch, L., van Compernolle, D.: A novel feature transformation for vocal tract length normalization in automatic speech recognition. IEEE Trans. Speech Audio Process. 6(6), 549\u2013557 (1998)","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"1","key":"39_CR5","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/TASL.2011.2134090","volume":"20","author":"G Dahl","year":"2012","unstructured":"Dahl, G., Yu, D., Deng, L., Acero, A.: Context-dependent pre-trained deep neural networks for large vocabulary speech recognition. IEEE Trans. Speech Audio Process. 20(1), 30\u201342 (2012)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"39_CR6","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1109\/89.466659","volume":"3","author":"V Digalakis","year":"1995","unstructured":"Digalakis, V., Rtischev, D., Neumeyer, L.: Speaker adaptation using constrained estimation of Gaussian mixtures. IEEE Trans. Speech Audio Process. 3, 357\u2013366 (1995)","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"39_CR7","doi-asserted-by":"publisher","unstructured":"Fainberg, J., Bell, P., Lincoln, M., Renals, S.: Improving children\u2019s speech recognition through out-of-domain data augmentation. In: INTERSPEECH 2016, pp. 1598\u20131602 (2016). https:\/\/doi.org\/10.21437\/INTERSPEECH.2016-1348","DOI":"10.21437\/INTERSPEECH.2016-1348"},{"key":"39_CR8","doi-asserted-by":"publisher","first-page":"1532","DOI":"10.1121\/1.427150","volume":"106","author":"J Huber","year":"1999","unstructured":"Huber, J., Stathopoulos, E., Curione, G., Ash, T., Johnson, K.: Formants of children, women, and men: the effects of vocal intensity variation. J. Acoust. Soc. Am. 106, 1532\u201342 (1999). https:\/\/doi.org\/10.1121\/1.427150","journal-title":"J. Acoust. Soc. Am."},{"key":"39_CR9","doi-asserted-by":"publisher","unstructured":"Johnson, A., Fan, R., Morris, R., Alwan, A.: LPC augment: an LPC-based ASR data augmentation algorithm for low and zero-resource children\u2019s dialects. In: ICASSP 2022\u20132022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8577\u20138581 (2022). https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746281","DOI":"10.1109\/ICASSP43922.2022.9746281"},{"key":"39_CR10","doi-asserted-by":"publisher","first-page":"2021","DOI":"10.1007\/s00034-017-0652-0","volume":"32","author":"HK Kathania","year":"2018","unstructured":"Kathania, H.K., Ahmad, W., Shahnawazuddin, S., Samaddar, A.B.: Explicit pitch mapping for improved children\u2019s speech recognition. Circ. Syst. Signal Process. 32, 2021\u20132044 (2018)","journal-title":"Circ. Syst. Signal Process."},{"key":"39_CR11","doi-asserted-by":"crossref","unstructured":"Kathania, H.K., Ghai, S., Sinha, R.: Soft-weighting technique for robust children speech recognition under mismatched condition. In: 2013 Annual IEEE India Conference (INDICON), pp. 1\u20136 (2013)","DOI":"10.1109\/INDCON.2013.6726063"},{"key":"39_CR12","doi-asserted-by":"crossref","unstructured":"Kathania, H.K., Shahnawazuddin, S., Adiga, N., Ahmad, W.: Role of prosodic features on children\u2019s speech recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5519\u20135523 (2018)","DOI":"10.1109\/ICASSP.2018.8461668"},{"key":"39_CR13","doi-asserted-by":"crossref","unstructured":"Kathania, H.K., Shahnawazuddin, S., Ahmad, W., Adiga, N., Jana, S.K., Samaddar, A.B.: Improving children\u2019s speech recognition through time scale modification based speaking rate adaptation. In: 2018 International Conference on Signal Processing and Communications (SPCOM) (2018)","DOI":"10.1109\/SPCOM.2018.8724465"},{"key":"39_CR14","doi-asserted-by":"crossref","unstructured":"Kathania, H.K., Shahnawazuddin, S., Sinha, R.: Exploring HLDA based transformation for reducing acoustic mismatch in context of children speech recognition. In: 2014 International Conference on Signal Processing and Communications (SPCOM), pp. 1\u20135 (2014)","DOI":"10.1109\/SPCOM.2014.6983999"},{"key":"39_CR15","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/j.specom.2021.11.003","volume":"136","author":"HK Kathania","year":"2022","unstructured":"Kathania, H.K., Kadiri, S.R., Alku, P., Kurimo, M.: A formant modification method for improved ASR of children\u2019s speech. Speech Commun. 136, 98\u2013106 (2022)","journal-title":"Speech Commun."},{"key":"39_CR16","doi-asserted-by":"publisher","unstructured":"Kumar Kathania, H., Reddy Kadiri, S., Alku, P., Kurimo, M.: Study of formant modification for children ASR. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7429\u20137433 (2020). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053334","DOI":"10.1109\/ICASSP40776.2020.9053334"},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"Laine, U.K., Karjalainen, M., Altosaar, T.: Warped linear prediction (WLP) in speech and audio processing. In: Proceedings of ICASSP 1994, IEEE International Conference on Acoustics, Speech and Signal Processing, vol. 3, pp. III-349. IEEE (1994)","DOI":"10.1109\/ICASSP.1994.390018"},{"issue":"1","key":"39_CR18","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":"39_CR19","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. Soci. Am. 105(3), 1455\u20131468 (1999)","journal-title":"J. Acoust. Soci. Am."},{"issue":"4","key":"39_CR20","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1109\/PROC.1975.9792","volume":"63","author":"J Makhoul","year":"1975","unstructured":"Makhoul, J.: Linear prediction: a tutorial review. Proc. IEEE 63(4), 561\u2013580 (1975)","journal-title":"Proc. IEEE"},{"key":"39_CR21","doi-asserted-by":"crossref","unstructured":"Povey, D., et al.: Semi-orthogonal low-rank matrix factorization for deep neural networks. In: Proceedings of INTERSPEECH 2018, ISCA, pp. 3743\u20133747 (2018)","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"39_CR22","unstructured":"Povey, D., et al.: The Kaldi Speech recognition toolkit. In: Proceedings of ASRU (2011)"},{"key":"39_CR23","doi-asserted-by":"crossref","unstructured":"Rath, S.P., Povey, D., Vesel\u00fd, K., \u010cernock\u00fd, J.: Improved feature processing for deep neural networks. In: Proceedings of INTERSPEECH (2013)","DOI":"10.21437\/Interspeech.2013-48"},{"key":"39_CR24","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 ICASSP, vol. 1, pp. 81\u201384 (1995)","DOI":"10.1109\/ICASSP.1995.479278"},{"key":"39_CR25","doi-asserted-by":"crossref","unstructured":"Saon, G., Soltau, H., Nahamoo, D., Picheny, M.: Speaker adaptation of neural network acoustic models using i-vectors. In: 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, Olomouc, Czech Republic, 8\u201312 December 2013, pp. 55\u201359. IEEE (2013)","DOI":"10.1109\/ASRU.2013.6707705"},{"key":"39_CR26","doi-asserted-by":"crossref","unstructured":"Schalkwyk, J., et al.: Your word is my command: google search by voice: a case study. In: Advances in Speech Recognition: Mobile Environments, Call Centers and Clinics, vol. 4, pp. 61\u201390 (2010)","DOI":"10.1007\/978-1-4419-5951-5_4"},{"issue":"1","key":"39_CR27","doi-asserted-by":"publisher","first-page":"203","DOI":"10.2466\/pms.1991.73.1.203","volume":"73","author":"GP Scukanec","year":"1991","unstructured":"Scukanec, G.P., Petrosino, L., Squibb, K.: Formant frequency characteristics of children, young adult, and aged female speakers. Percept. Mot. Skills 73(1), 203\u2013208 (1991)","journal-title":"Percept. Mot. Skills"},{"key":"39_CR28","doi-asserted-by":"crossref","unstructured":"Serizel, R., Giuliani, D.: Vocal tract length normalisation approaches to DNN-based children\u2019s and adults\u2019 speech recognition. In: 2014 IEEE Spoken Language Technology Workshop (SLT), pp. 135\u2013140 (2014)","DOI":"10.1109\/SLT.2014.7078563"},{"issue":"11","key":"39_CR29","doi-asserted-by":"publisher","first-page":"1749","DOI":"10.1109\/LSP.2017.2756347","volume":"24","author":"S Shahnawazuddin","year":"2017","unstructured":"Shahnawazuddin, S., Adiga, N., Kathania, H.K.: Effect of prosody modification on children\u2019s ASR. IEEE Signal Process. Lett. 24(11), 1749\u20131753 (2017)","journal-title":"IEEE Signal Process. Lett."},{"key":"39_CR30","doi-asserted-by":"crossref","unstructured":"Shahnawazuddin, S., Dey, A., Sinha, R.: Pitch-adaptive front-end features for robust children\u2019s ASR. In: INTERSPEECH (2016)","DOI":"10.21437\/Interspeech.2016-1020"},{"key":"39_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101077","volume":"63","author":"PG Shivakumar","year":"2020","unstructured":"Shivakumar, P.G., Georgiou, P.: Transfer learning from adult to children for speech recognition: evaluation, analysis and recommendations. Comput. Speech Lang. 63, 101077 (2020). https:\/\/doi.org\/10.1016\/j.csl.2020.101077","journal-title":"Comput. Speech Lang."},{"issue":"4","key":"39_CR32","doi-asserted-by":"publisher","first-page":"1071","DOI":"10.1121\/1.384992","volume":"68","author":"HW Strube","year":"1980","unstructured":"Strube, H.W.: Linear prediction on a warped frequency scale. J. Acoust. Soc. Am. 68(4), 1071\u20131076 (1980)","journal-title":"J. Acoust. Soc. Am."},{"key":"39_CR33","doi-asserted-by":"crossref","unstructured":"Yadav, I.C., Shahnawazuddin, S., Govind, D., Pradhan, G.: Spectral smoothing by variational mode decomposition and its effect on noise and pitch robustness of ASR system. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5629\u20135633 (2018)","DOI":"10.1109\/ICASSP.2018.8462133"},{"key":"39_CR34","unstructured":"Yildirim, S., Narayanan, S., Byrd, D., Khurana, S.: Acoustic analysis of preschool children\u2019s speech. In: In ICPhS-2015, pp. 949\u2013952 (2003)"},{"issue":"5","key":"39_CR35","doi-asserted-by":"publisher","first-page":"1645","DOI":"10.1109\/TASL.2007.899236","volume":"15","author":"X Zhu","year":"2007","unstructured":"Zhu, X., Beauregard, G.T., Wyse, L.L.: Real-time signal estimation from modified short-time fourier transform magnitude spectra. IEEE Trans. Audio Speech Lang. Process. 15(5), 1645\u20131653 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. 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_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T14:50:12Z","timestamp":1730559012000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-48309-7_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031483080","9783031483097"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-48309-7_39","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)"}}]}}