{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T05:15:40Z","timestamp":1743138940643,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031483110"},{"type":"electronic","value":"9783031483127"}],"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\/978-3-031-48312-7_31","type":"book-chapter","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:03:21Z","timestamp":1700597001000},"page":"380-394","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Children\u2019s Short Utterance Based ASV Using Data Augmentation Techniques and\u00a0Feature Concatenation Approach"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5415-8864","authenticated-orcid":false,"given":"Shahid","family":"Aziz","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3916-9693","authenticated-orcid":false,"given":"Syed","family":"Shahnawazuddin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,22]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Badillo-Urquiola, K., Smriti, D., McNally, B., Golub, E., Bonsignore, E., Wisniewski, P.J.: Stranger danger! social media app features co-designed with children to keep them safe online. In: Proceedings of the 18th ACM International Conference on Interaction Design and Children, pp. 394\u2013406 (2019)","DOI":"10.1145\/3311927.3323133"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"D\u2019Arcy, S., Russell, M.: A comparison of human and computer recognition accuracy for children\u2019s speech. In: Ninth European Conference on Speech Communication and Technology (2005)","DOI":"10.21437\/Interspeech.2005-697"},{"issue":"4","key":"31_CR3","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"S Davis","year":"1980","unstructured":"Davis, S., Mermelstein, P.: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust. Speech Signal Process. 28(4), 357\u2013366 (1980). https:\/\/doi.org\/10.1109\/TASSP.1980.1163420","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"31_CR4","unstructured":"Eskenazi, M., Mostow, J., Graff, D.: The CMU Kids Corpus LDC97S63 (1997). https:\/\/catalog.ldc.upenn.edu\/LDC97S63"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Gerosa, M., Giuliani, D., Narayanan, S., Potamianos, A.: A review of ASR technologies for children\u2019s speech. In: Proceedings of the Workshop on Child, Computer and Interaction, pp. 7:1\u20137:8 (2009)","DOI":"10.1145\/1640377.1640384"},{"key":"31_CR6","doi-asserted-by":"publisher","first-page":"107005","DOI":"10.1016\/j.compeleceng.2021.107005","volume":"90","author":"RM Hanifa","year":"2021","unstructured":"Hanifa, R.M., Isa, K., Mohamad, S.: A review on speaker recognition: technology and challenges. Comput. Electr. Eng. 90, 107005 (2021)","journal-title":"Comput. Electr. Eng."},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Kaneko, T., Kameoka, H.: Parallel-data-free voice conversion using cycle-consistent adversarial networks. arXiv preprint arXiv:1711.11293 (2017)","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Kathania, H.K., Kadiri, S.R., 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. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053334"},{"issue":"10","key":"31_CR9","doi-asserted-by":"publisher","first-page":"4667","DOI":"10.1007\/s00034-019-01072-7","volume":"38","author":"HK Kathania","year":"2019","unstructured":"Kathania, H.K., Shahnawazuddin, S., Ahmad, W., Adiga, N.: Role of linear, mel and inverse-mel filterbanks in automatic recognition of speech from high-pitched speakers. Circuits Syst. Sig. Process. 38(10), 4667\u20134682 (2019)","journal-title":"Circuits Syst. Sig. Process."},{"issue":"4","key":"31_CR10","doi-asserted-by":"publisher","first-page":"2205","DOI":"10.1007\/s00034-021-01885-5","volume":"41","author":"V Kumar","year":"2022","unstructured":"Kumar, V., Kumar, A., Shahnawazuddin, S.: Creating robust children\u2019s ASR system in zero-resource condition through out-of-domain data augmentation. Circuits Syst. Signal Process. 41(4), 2205\u20132220 (2022)","journal-title":"Circuits Syst. Signal Process."},{"issue":"3","key":"31_CR11","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."},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Peddinti, V., Povey, D., Khudanpur, S.: A time delay neural network architecture for efficient modeling of long temporal contexts. In: Proceedings of the INTERSPEECH (2015)","DOI":"10.21437\/Interspeech.2015-647"},{"issue":"2","key":"31_CR13","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1049\/iet-bmt.2017.0065","volume":"7","author":"A Poddar","year":"2018","unstructured":"Poddar, A., Sahidullah, M., Saha, G.: Speaker verification with short utterances: a review of challenges, trends and opportunities. IET Biometrics 7(2), 91\u2013101 (2018)","journal-title":"IET Biometrics"},{"key":"31_CR14","unstructured":"Povey, D., et al.: The kaldi speech recognition toolkit. In: Proceedings of the ASRU (2011)"},{"key":"31_CR15","unstructured":"Povey, D., Zhang, X., Khudanpur, S.: Parallel training of deep neural networks with natural gradient and parameter averaging. In: Proceedings of the ICLR (2015)"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Prasanna, S.R.M., Govind, D., Rao, K.S., Yegnanarayana, B.: Fast prosody modification using instants of significant excitation. In: Proceedings of the International Conference on Speech Prosody (2010)","DOI":"10.21437\/SpeechProsody.2010-126"},{"key":"31_CR17","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 the ICASSP, vol. 1, pp. 81\u201384 (1995)","DOI":"10.1109\/ICASSP.1995.479278"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Russell, M., D\u2019Arcy, S.: Challenges for computer recognition of children\u2019s speech. In: Proceedings of the Speech and Language Technologies in Education (SLaTE) (2007)","DOI":"10.21437\/SLaTE.2007-26"},{"issue":"12","key":"31_CR19","doi-asserted-by":"publisher","first-page":"1044","DOI":"10.1109\/LSP.2007.906213","volume":"14","author":"M Russell","year":"2007","unstructured":"Russell, M., D\u2019Arcy, S., Qun, L.: The effects of bandwidth reduction on human and computer recognition of children\u2019s speech. IEEE Sig. Process. Lett. 14(12), 1044\u20131046 (2007)","journal-title":"IEEE Sig. Process. Lett."},{"key":"31_CR20","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1016\/j.csl.2018.01.001","volume":"50","author":"S Safavi","year":"2018","unstructured":"Safavi, S., Russell, M., Jancovic, P.: Automatic speaker, age-group and gender identification from children\u2019s speech. Comput. Speech Lang. 50, 141\u2013156 (2018)","journal-title":"Comput. Speech Lang."},{"key":"31_CR21","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1016\/j.patrec.2019.12.019","volume":"131","author":"S Shahnawazuddin","year":"2020","unstructured":"Shahnawazuddin, S., Adiga, N., Kathania, H.K., Sai, B.T.: Creating speaker independent ASR system through prosody modification based data augmentation. Pattern Recogn. Lett. 131, 213\u2013218 (2020). https:\/\/doi.org\/10.1016\/j.patrec.2019.12.019","journal-title":"Pattern Recogn. Lett."},{"key":"31_CR22","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/j.dsp.2019.06.015","volume":"93","author":"S Shahnawazuddin","year":"2019","unstructured":"Shahnawazuddin, S., Adiga, N., Sai, B.T., Ahmad, W., Kathania, H.K.: Developing speaker independent ASR system using limited data through prosody modification based on fuzzy classification of spectral bins. Digit. Sig. Process. 93, 34\u201342 (2019)","journal-title":"Digit. Sig. Process."},{"key":"31_CR23","doi-asserted-by":"crossref","unstructured":"Shahnawazuddin, S., Ahmad, W., Adiga, N., Kumar, A.: In-domain and out-of-domain data augmentation to improve children\u2019s speaker verification system in limited data scenario. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7554\u20137558 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053891"},{"key":"31_CR24","unstructured":"Shobaki, K., Hosom, J.P., Cole, R.: CSLU: kids\u2019 speech version 1.1. Linguistic Data Consortium (2007)"},{"key":"31_CR25","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Povey, D., Khudanpur, S.: Deep neural network embeddings for text-independent speaker verification. In: Proceedings of the INTERSPEECH, pp. 999\u20131003 (2017)","DOI":"10.21437\/Interspeech.2017-620"},{"key":"31_CR26","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Sell, G., Povey, D., Khudanpur, S.: X-Vectors: Robust DNN embeddings for speaker recognition. In: Proceedings of the ICASSP, pp. 5329\u20135333 (2018)","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"31_CR27","doi-asserted-by":"crossref","unstructured":"Yeung, G., Alwan, A.: On the difficulties of automatic speech recognition for kindergarten-aged children. In: Interspeech 2018 (2018)","DOI":"10.21437\/Interspeech.2018-2297"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-48312-7_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T14:46:50Z","timestamp":1730558810000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-48312-7_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031483110","9783031483127"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-48312-7_31","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)"}}]}}