{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:18:14Z","timestamp":1773965894383,"version":"3.50.1"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031235030","type":"print"},{"value":"9783031235047","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-23504-7_10","type":"book-chapter","created":{"date-parts":[[2022,12,15]],"date-time":"2022-12-15T08:03:53Z","timestamp":1671091433000},"page":"126-134","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Infant Cry Classification Based-On Feature Fusion and Mel-Spectrogram Decomposition with CNNs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1538-9875","authenticated-orcid":false,"given":"Chunyan","family":"Ji","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2787-8927","authenticated-orcid":false,"given":"Yang","family":"Jiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1494-901X","authenticated-orcid":false,"given":"Ming","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2766-3096","authenticated-orcid":false,"given":"Yi","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,12,16]]},"reference":[{"key":"10_CR1","doi-asserted-by":"publisher","unstructured":"Lavner, Y., Cohen, R., Ruinskiy, D., Ijzerman, H.: Baby cry detection in domestic environment using deep learning. In: 2016 IEEE International Conference on the Science of Electrical Engineering (ICSEE) (2017). https:\/\/doi.org\/10.1109\/ICSEE.2016.7806117","DOI":"10.1109\/ICSEE.2016.7806117"},{"key":"10_CR2","doi-asserted-by":"publisher","unstructured":"Liu, L., Li, Y., Kuo, K.: Infant cry signal detection, pattern extraction and recognition. In: 2018 International Conference on Information and Computer Technologies (ICICT), pp. 159\u2013163. IEEE (2018 ). https:\/\/doi.org\/10.1109\/INFOCT.2018.8356861","DOI":"10.1109\/INFOCT.2018.8356861"},{"key":"10_CR3","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). https:\/\/doi.org\/10.1016\/j.bspc.2014.10.002","journal-title":"Biomed. Signal Process. Control"},{"key":"10_CR4","doi-asserted-by":"publisher","unstructured":"Franti, E., Ispas, I., Dascalu, M.: Testing the universal baby language hypothesis-automatic infant speech recognition with cnns. In: 2018 41st International Conference on Telecommunications and Signal Processing (TSP), pp. 1\u20134. IEEE (2018). https:\/\/doi.org\/10.1109\/TSP.2018.8441412","DOI":"10.1109\/TSP.2018.8441412"},{"key":"10_CR5","doi-asserted-by":"publisher","unstructured":"Sachin, M.U., Nagaraj, R., Samiksha, M., Rao, S., Moharir, M.: GPU based deep learning to detect asphyxia in neonates. Indian J. Sci. Technol. 10(3) (2017). https:\/\/doi.org\/10.17485\/ijst\/2017\/v10i3\/110617","DOI":"10.17485\/ijst\/2017\/v10i3\/110617"},{"key":"10_CR6","unstructured":"Lim, H., Park, J., Lee, K., Han, Y.: Rare sound event detection using 1D convolutional recurrent neural networks. In: Dcase 2017 Proceeding, pp. 2\u20136 (2017)"},{"key":"10_CR7","doi-asserted-by":"publisher","unstructured":"Gong, Y., Chung, Y.A., Glass, J.: AST: Audio Spectrogram Transformer (2021). https:\/\/doi.org\/10.21437\/interspeech.2021-698","DOI":"10.21437\/interspeech.2021-698"},{"issue":"12","key":"10_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/APP10124176","volume":"10","author":"L Nanni","year":"2020","unstructured":"Nanni, L., Rigo, A., Lumini, A., Brahnam, S.: Spectrogram classification using dissimilarity space. Appl. Sci. 10(12), 1\u201317 (2020). https:\/\/doi.org\/10.3390\/APP10124176","journal-title":"Appl. Sci."},{"key":"10_CR9","unstructured":"Palanisamy, K., Singhania, D., Yao, A.: Rethinking CNN Models for Audio Classification (2020). http:\/\/arxiv.org\/abs\/2007.11154"},{"key":"10_CR10","series-title":"Advances in Intelligent Systems and Computing","doi-asserted-by":"publisher","first-page":"786","DOI":"10.1007\/978-3-030-15035-8_76","volume-title":"Web, Artificial Intelligence and Network Applications","author":"C-Y Chang","year":"2019","unstructured":"Chang, C.-Y., Tsai, L.-Y.: A CNN-based method for infant cry detection and recognition. In: Barolli, L., Takizawa, M., Xhafa, F., Enokido, T. (eds.) WAINA 2019. AISC, vol. 927, pp. 786\u2013792. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-15035-8_76"},{"key":"10_CR11","unstructured":"Hwang, Y., Cho, H., Yang, H., Won, D.O., Oh, I., Lee, S.W.: Mel-spectrogram augmentation for sequence-to-sequence voice conversion (2020). http:\/\/arxiv.org\/abs\/2001.01401"},{"key":"10_CR12","doi-asserted-by":"publisher","unstructured":"Juvela, L., Bollepalli, B., Yamagishi, J., Alku, P.: Gelp: GAN-excited linear prediction for speech synthesis from mel-spectrogram. In: Proceedings Annual Conference International Speech Communication Association. Interspeech, pp. 694\u2013698 (2019). https:\/\/doi.org\/10.21437\/Interspeech.2019-2008","DOI":"10.21437\/Interspeech.2019-2008"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Phaye, S.S.R., Benetos, E., Wang, Y.: Subspectralnet \u2013 Using Sub-Spectrogram Based Convolutional Neural Networks for Acoustic Scene ClassificatioN School of Computing , National University of Singapore, Singapore School of EECS , Queen Mary University of London , UK 3 The Alan Turing Institu, pp. 825\u2013829 (2019)","DOI":"10.1109\/ICASSP.2019.8683288"},{"key":"10_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2021.108258","volume":"182","author":"T Zhang","year":"2021","unstructured":"Zhang, T., Feng, G., Liang, J., An, T.: Acoustic scene classification based on Mel spectrogram decomposition and model merging. Appl. Acoust. 182, 108258 (2021). https:\/\/doi.org\/10.1016\/j.apacoust.2021.108258","journal-title":"Appl. Acoust."},{"key":"10_CR15","doi-asserted-by":"publisher","unstructured":"Dai, Y., Gieseke, F., Oehmcke, S., Wu, Y., Barnard, K.: Attentional Feature Fusion, pp. 3559\u20133568 (2021). https:\/\/doi.org\/10.1109\/wacv48630.2021.00360","DOI":"10.1109\/wacv48630.2021.00360"},{"key":"10_CR16","doi-asserted-by":"publisher","unstructured":"Chen Y, et al.: Research of improving semantic image segmentation based on a feature fusion model. J. Ambient Intell. Hum. Comput. 9, 1\u20133 (2020). https:\/\/doi.org\/10.1007\/s12652-020-02066-z","DOI":"10.1007\/s12652-020-02066-z"},{"key":"10_CR17","unstructured":"Xu, X., et al.: AMFFCN: Attentional Multi-layer Feature Fusion Convolution Network for Audio-visual Speech Enhancement (2021). http:\/\/arxiv.org\/abs\/2101.06268"},{"issue":"3","key":"10_CR18","doi-asserted-by":"publisher","first-page":"1672","DOI":"10.1007\/s00034-019-01203-0","volume":"39","author":"I McLoughlin","year":"2019","unstructured":"McLoughlin, I., Xie, Z., Song, Y., Phan, H., Palaniappan, R.: Time\u2013frequency feature fusion for noise robust audio event classification. Circuits Syst. Signal Process. 39(3), 1672\u20131687 (2019). https:\/\/doi.org\/10.1007\/s00034-019-01203-0","journal-title":"Circuits Syst. Signal Process."},{"key":"10_CR19","doi-asserted-by":"publisher","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: Proceedings 2019 IEEE International Congress Cybermatics 12th IEEE International Conference Internet Things, 15th IEEE International Conference Green Computing Communication 12th IEEE International Confernce Cybermatics Phys. So (2019). https:\/\/doi.org\/10.1109\/iThings\/GreenCom\/CPSCom\/SmartData.2019.00206","DOI":"10.1109\/iThings\/GreenCom\/CPSCom\/SmartData.2019.00206"},{"key":"10_CR20","unstructured":"Chang, C.M., Chen, H.Y., Chen, H.C., Lee, C.C.: Sensing with contexts: crying reason classification for infant care center with environmental fusion. In: 2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 314\u2013318 (2020)"},{"key":"10_CR21","unstructured":"Sox Homepage. https:\/\/en.wikipedia.org\/wiki\/SoX"},{"key":"10_CR22","doi-asserted-by":"publisher","unstructured":"McFee, B., et al.: librosa: Audio and Music Signal Analysis in Python (2015). https:\/\/doi.org\/10.25080\/majora-7b98e3ed-003","DOI":"10.25080\/majora-7b98e3ed-003"},{"key":"10_CR23","doi-asserted-by":"publisher","unstructured":"Reyes-Galaviz, O.F., Cano-Ortiz, S.D., Reyes-Garc\u00eda, C.A.: Evolutionary-neural system to classify infant cry units for pathologies identification in recently born babies. In: 2008 Seventh Mexican International Conference on Artificial Intelligence, pp. 330-335. IEEE (2008). https:\/\/doi.org\/10.1109\/MICAI.2008.73","DOI":"10.1109\/MICAI.2008.73"},{"key":"10_CR24","unstructured":"Ma, R., Wang, Y., Wei, Y., Pan, Y.: Meta-data Study in Autism Spectrum Disorder Classification Based on Structural MRI (2022). arXiv preprint arXiv:2206.05052"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence and Mobile Services \u2013 AIMS 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-23504-7_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,21]],"date-time":"2022-12-21T00:30:51Z","timestamp":1671582651000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-23504-7_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031235030","9783031235047"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-23504-7_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"16 December 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIMS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on AI and Mobile Services","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Honolulu, HI","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aimse2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.servicessociety.org\/aims","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":"EDAS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"22","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":"10","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":"45% - 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":"2","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":"6","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)"}}]}}