{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T13:41:39Z","timestamp":1754487699220,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"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_34","type":"book-chapter","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:03:21Z","timestamp":1700597001000},"page":"421-433","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Robustness of\u00a0Whisper Features for\u00a0Infant Cry Classification"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5145-8378","authenticated-orcid":false,"given":"Monil","family":"Charola","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2176-4413","authenticated-orcid":false,"given":"Siddharth","family":"Rathod","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4068-2005","authenticated-orcid":false,"given":"Hemant A.","family":"Patil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,22]]},"reference":[{"key":"34_CR1","unstructured":"Agarap, A.F.: Deep learning using rectified linear units (relu). CoRR abs\/1803.08375 (2018). http:\/\/arxiv.org\/abs\/1803.08375. Accessed 6 Feb 2023"},{"key":"34_CR2","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.specom.2015.12.001","volume":"77","author":"HF Alaie","year":"2016","unstructured":"Alaie, H.F., Abou-Abbas, L., Tadj, C.: Cry-based infant pathology classification using GMMs. Speech Commun. 77, 28\u201352 (2016)","journal-title":"Speech Commun."},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Anjali, G., Sanjeev, S., Mounika, A., Suhas, G., Reddy, G.P., Kshiraja, Y.: Infant cry classification using transfer learning. In: TENCON 2022, Seoul, South Korea, pp. 1\u20137. IEEE (2022)","DOI":"10.1109\/TENCON55691.2022.9977793"},{"issue":"5","key":"34_CR4","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1159\/000510622","volume":"73","author":"L Armbr\u00fcster","year":"2021","unstructured":"Armbr\u00fcster, L., Mende, W., Gelbrich, G., Wermke, P., G\u00f6tz, R., Wermke, K.: Musical intervals in infants\u2019 spontaneous crying over the first 4 months of life. Folia Phoniatr. Logop. 73(5), 401\u2013412 (2021)","journal-title":"Folia Phoniatr. Logop."},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Bock, S., Wei\u00df, M.: A proof of local convergence for the Adam optimizer. In: 2019 (IJCNN), pp. 1\u20138 (2019)","DOI":"10.1109\/IJCNN.2019.8852239"},{"key":"34_CR6","unstructured":"Buddha, N., Patil, H.A.: Corpora for analysis of infant cry. Oriental Cocosda, Vietnam (2007)"},{"issue":"2","key":"34_CR7","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1016\/j.jvoice.2016.07.007","volume":"31","author":"A Chittora","year":"2017","unstructured":"Chittora, A., Patil, H.A.: Data collection of infant cries for research and analysis. J. Voice 31(2), 252-e15 (2017)","journal-title":"J. Voice"},{"key":"34_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-59605-7_1","volume-title":"Artificial Intelligence and Mobile Services \u2013 AIMS 2020","author":"C Ji","year":"2020","unstructured":"Ji, C., Basodi, S., Xiao, X., Pan, Y.: Infant sound classification on multi-stage CNNs with hybrid features and prior knowledge. In: Xu, R., De, W., Zhong, W., Tian, L., Bai, Y., Zhang, L.-J. (eds.) AIMS 2020. LNCS, vol. 12401, pp. 3\u201316. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59605-7_1"},{"issue":"1","key":"34_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13636-021-00197-5","volume":"2021","author":"C Ji","year":"2021","unstructured":"Ji, C., Mudiyanselage, T.B., Gao, Y., Pan, Y.: A review of infant cry analysis and classification. EURASIP J. Audio Speech Music Process. 2021(1), 1\u201317 (2021)","journal-title":"EURASIP J. Audio Speech Music Process."},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Ji, C., Xiao, X., Basodi, S., Pan, Y.: Deep learning for asphyxiated infant cry classification based on acoustic features and weighted prosodic features. In: 2019 International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE smart data (SmartData), pp. 1233\u20131240. IEEE (2019)","DOI":"10.1109\/iThings\/GreenCom\/CPSCom\/SmartData.2019.00206"},{"key":"34_CR11","unstructured":"Manickam, K., Li, H.: Complexity analysis of normal and deaf infant cry acoustic waves. In: 4th International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications (2005)"},{"key":"34_CR12","doi-asserted-by":"crossref","unstructured":"Onu, C.C., Lebensold, J., Hamilton, W.L., Precup, D.: Neural transfer learning for cry-based diagnosis of perinatal asphyxia. In: International Conference on Learning Representations (ICLR) Workshop, Graz, Austria (2019)","DOI":"10.21437\/Interspeech.2019-2340"},{"key":"34_CR13","unstructured":"Onu, C.C., et al.: Ubenwa: cry-based diagnosis of birth asphyxia. In: 31st Conference on Neural Information Processing Systems (NIPS), Long Beach, CA (2017)"},{"key":"34_CR14","unstructured":"O\u2019Shea, K., Nash, R.: An introduction to convolutional neural networks. arXiv preprint arXiv:1511.08458 (2015). Accessed 25 Feb 2023"},{"key":"34_CR15","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. arXiv preprint arXiv:2212.04356 (2022). Accessed 6 Mar 2023"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Reyes-Galaviz, O.F., Cano-Ortiz, S.D., Reyes-Garc\u00eda, C.A.: Validation of the cry unit as primary element for cry analysis using an evolutionary-neural approach. In: 2008 Mexican International Conference on Computer Science, pp. 261\u2013267. IEEE (2008)","DOI":"10.1109\/ENC.2008.16"},{"key":"34_CR17","doi-asserted-by":"crossref","unstructured":"Rezaee, K., Ghayoumi Zadeh, H., Qi, L., Rabiee, H., Khosravi, M.R.: Can you understand why i am crying? a decision-making system for classifying infants\u2019 cry languages based on deepsvm model. ACM Transactions on Asian and Low-Resource Language Information Processing (2023)","DOI":"10.1145\/3579032"},{"key":"34_CR18","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.bspc.2014.10.002","volume":"17","author":"A Rosales-P\u00e9rez","year":"2015","unstructured":"Rosales-P\u00e9rez, A., Reyes-Garc\u00eda, C.A., Gonzalez, J.A., Reyes-Galaviz, O.F., Escalante, H.J., Orlandi, S.: Classifying infant cry patterns by the genetic selection of a fuzzy model. Biomed. Signal Process. Control 17, 38\u201346 (2015)","journal-title":"Biomed. Signal Process. Control"},{"key":"34_CR19","doi-asserted-by":"crossref","unstructured":"Sahak, R., Mansor, W., Lee, Y., Yassin, A., Zabidi, A.: Performance of combined support vector machine and principal component analysis in recognizing infant cry with asphyxia. In: 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology, pp. 6292\u20136295. IEEE (2010)","DOI":"10.1109\/IEMBS.2010.5628084"},{"issue":"11","key":"34_CR20","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45(11), 2673\u20132681 (1997)","journal-title":"IEEE Trans. Signal Process."},{"key":"34_CR21","unstructured":"Strand, O.M., Egeberg, A.: Cepstral mean and variance normalization in the model domain. In: COST278 and ITRW on Robustness Issues in Conversational Interaction, Norwich, United Kingdom, 30\u201331 August 2004 (2004)"},{"key":"34_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118064","volume":"208","author":"HN Ting","year":"2022","unstructured":"Ting, H.N., Choo, Y.M., Kamar, A.A.: Classification of asphyxia infant cry using hybrid speech features and deep learning models. Expert Syst. Appl. 208, 118064 (2022)","journal-title":"Expert Syst. Appl."},{"key":"34_CR23","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in NIPS, Long Beach California, United States of America 30 (2017)"},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Xu, H.t., Zhang, J., Dai, L.r.: Differential time-frequency log-mel spectrogram features for vision transformer based infant cry recognition. In: Proceedings of the INTERSPEECH, Incheon Songdo ConvensiA, Korea, pp. 1963\u20131967 (2022)","DOI":"10.21437\/Interspeech.2022-18"},{"key":"34_CR25","unstructured":"Zhang, Z., Sabuncu, M.: Generalized cross entropy loss for training deep neural networks with noisy labels. In: Advances in NIPS, vol. 31, 2018, Montreal Canada (2018)"}],"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_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:07:35Z","timestamp":1700597255000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-48312-7_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031483110","9783031483127"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-48312-7_34","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)"}}]}}