{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T03:55:19Z","timestamp":1780372519415,"version":"3.54.1"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030638290","type":"print"},{"value":"9783030638306","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-63830-6_21","type":"book-chapter","created":{"date-parts":[[2020,11,18]],"date-time":"2020-11-18T10:08:18Z","timestamp":1605694098000},"page":"241-252","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Deep Residual Local Feature Learning for Speech Emotion Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7335-7105","authenticated-orcid":false,"given":"Sattaya","family":"Singkul","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thakorn","family":"Chatchaisathaporn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boontawee","family":"Suntisrivaraporn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kuntpong","family":"Woraratpanya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,19]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Singkul, S., Khampingyot, B., Maharattamalai, N., Taerungruang, S., Chalothorn, T.: Parsing thai social data: a new challenge for thai NLP. In: 2019 14th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP), pp. 1\u20137 (2019)","DOI":"10.1109\/iSAI-NLP48611.2019.9045639"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Singkul, S., Woraratpanya, K.: Thai dependency parsing with character embedding. In: 2019 11th International Conference on Information Technology and Electrical Engineering (ICITEE), pp. 1\u20135 (2019)","DOI":"10.1109\/ICITEED.2019.8930002"},{"issue":"3","key":"21_CR3","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1016\/j.patcog.2010.09.020","volume":"44","author":"M El Ayadi","year":"2011","unstructured":"El Ayadi, M., Kamel, M.S., Karray, F.: Survey on speech emotion recognition: features, classification schemes, and databases. Pattern Recogn. 44(3), 572\u2013587 (2011)","journal-title":"Pattern Recogn."},{"issue":"2","key":"21_CR4","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s10462-012-9368-5","volume":"43","author":"C-N Anagnostopoulos","year":"2012","unstructured":"Anagnostopoulos, C.-N., Iliou, T., Giannoukos, I.: Features and classifiers for emotion recognition from speech: a survey from 2000 to 2011. Artif. Intell. Rev. 43(2), 155\u2013177 (2012). https:\/\/doi.org\/10.1007\/s10462-012-9368-5","journal-title":"Artif. Intell. Rev."},{"issue":"1","key":"21_CR5","first-page":"115","volume":"23","author":"Z Zhang","year":"2014","unstructured":"Zhang, Z., Coutinho, E., Deng, J., Schuller, B.: Cooperative learning and its application to emotion recognition from speech. IEEE\/ACM Trans. Audio, Speech Lang. Proces. 23(1), 115\u2013126 (2014)","journal-title":"IEEE\/ACM Trans. Audio, Speech Lang. Proces."},{"key":"21_CR6","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.bspc.2014.10.011","volume":"17","author":"A Guidi","year":"2015","unstructured":"Guidi, A., Vanello, N., Bertschy, G., Gentili, C., Landini, L., Scilingo, E.P.: Automatic analysis of speech f0 contour for the characterization of mood changes in bipolar patients. Biomed. Signal Process. Control 17, 29\u201337 (2015)","journal-title":"Biomed. Signal Process. Control"},{"issue":"4","key":"21_CR7","doi-asserted-by":"publisher","first-page":"1334","DOI":"10.1016\/j.jnca.2006.09.007","volume":"30","author":"H Gunes","year":"2007","unstructured":"Gunes, H., Piccardi, M.: Bi-modal emotion recognition from expressive face and body gestures. J. Netw. Comput. Appl. 30(4), 1334\u20131345 (2007)","journal-title":"J. Netw. Comput. Appl."},{"key":"21_CR8","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1016\/j.bspc.2017.03.016","volume":"36","author":"SZ Bong","year":"2017","unstructured":"Bong, S.Z., Wan, K., Murugappan, M., Ibrahim, N.M., Rajamanickam, Y., Mohamad, K.: Implementation of wavelet packet transform and non linear analysis for emotion classification in stroke patient using brain signals. Biomed. Signal Process. Control 36, 102\u2013112 (2017)","journal-title":"Biomed. Signal Process. Control"},{"key":"21_CR9","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.bspc.2014.07.005","volume":"14","author":"R Yuvaraj","year":"2014","unstructured":"Yuvaraj, R., Murugappan, M., Ibrahim, N.M., Sundaraj, K., Omar, M.I., Mohamad, K., Palaniappan, R.: Detection of emotions in parkinson\u2019s disease using higher order spectral features from brain\u2019s electrical activity. Biomed. Signal Process. Control 14, 108\u2013116 (2014)","journal-title":"Biomed. Signal Process. Control"},{"key":"21_CR10","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1016\/j.bspc.2018.08.035","volume":"47","author":"J Zhao","year":"2019","unstructured":"Zhao, J., Mao, X., Chen, L.: Speech emotion recognition using deep 1d & 2d CNN LSTM networks. Biomed. Signal Process. Control 47, 312\u2013323 (2019)","journal-title":"Biomed. Signal Process. Control"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"5","key":"21_CR12","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1016\/j.specom.2010.08.013","volume":"53","author":"S Wu","year":"2011","unstructured":"Wu, S., Falk, T.H., Chan, W.Y.: Automatic speech emotion recognition using modulation spectral features. Speech Commun. 53(5), 768\u2013785 (2011)","journal-title":"Speech Commun."},{"issue":"2","key":"21_CR13","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/j.bspc.2010.11.001","volume":"6","author":"L He","year":"2011","unstructured":"He, L., Lech, M., Maddage, N.C., Allen, N.B.: Study of empirical mode decomposition and spectral analysis for stress and emotion classification in natural speech. Biomed. Signal Process. Control 6(2), 139\u2013146 (2011)","journal-title":"Biomed. Signal Process. Control"},{"issue":"1","key":"21_CR14","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.bspc.2011.02.008","volume":"7","author":"H P\u00e9rez-Espinosa","year":"2012","unstructured":"P\u00e9rez-Espinosa, H., Reyes-Garcia, C.A., Villase\u00f1or-Pineda, L.: Acoustic feature selection and classification of emotions in speech using a 3d continuous emotion model. Biomed. Signal Process. Control 7(1), 79\u201387 (2012)","journal-title":"Biomed. Signal Process. Control"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Huang, Z., Dong, M., Mao, Q., Zhan, Y.: Speech emotion recognition using CNN. In: Proceedings of the 22nd ACM international conference on Multimedia. pp. 801\u2013804 (2014)","DOI":"10.1145\/2647868.2654984"},{"issue":"4","key":"21_CR16","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1049\/iet-spr.2013.0446","volume":"9","author":"Y Huang","year":"2015","unstructured":"Huang, Y., Wu, A., Zhang, G., Li, Y.: Extraction of adaptive wavelet packet filter-bank-based acoustic feature for speech emotion recognition. IET Signal Proc. 9(4), 341\u2013348 (2015)","journal-title":"IET Signal Proc."},{"issue":"8","key":"21_CR17","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/s00521-016-2712-y","volume":"29","author":"S Demircan","year":"2018","unstructured":"Demircan, S., Kahramanli, H.: Application of fuzzy c-means clustering algorithm to spectral features for emotion classification from speech. Neural Comput. Appl. 29(8), 59\u201366 (2018)","journal-title":"Neural Comput. Appl."},{"key":"21_CR18","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1016\/j.bspc.2014.10.008","volume":"18","author":"Y Sun","year":"2015","unstructured":"Sun, Y., Wen, G., Wang, J.: Weighted spectral features based on local hu moments for speech emotion recognition. Biomed. Signal Process. Control 18, 80\u201390 (2015)","journal-title":"Biomed. Signal Process. Control"},{"key":"21_CR19","unstructured":"Sari, S.W.W.: The influence of using repeated reading strategy towards student\u2019s reading comprehension. In: Proceeding 1st Annual International Conference on Islamic Education and Language: The Education and 4.0 Industrial Era in Islamic Perspective, p. 71 (2019)"},{"key":"21_CR20","unstructured":"Shanahan, T.: Everything you wanted to know about repeated reading. Reading Rockets. https:\/\/www.readingrockets.org\/blogs\/shanahan-literacy\/everything-you-wanted-know-about-repeated-reading (2017)"},{"key":"21_CR21","unstructured":"Venkataramanan, K., Rajamohan, H.R.: Emotion recognition from speech (2019)"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Soekhoe, D., Putten, P., Plaat, A.: On the impact of data set size in transfer learning using deep neural networks, pp. 50\u201360 (2016)","DOI":"10.1007\/978-3-319-46349-0_5"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Park, D.S., et al: Specaugment: a simple data augmentation method for automatic speech recognition. arXiv preprint arXiv:1904.08779 (2019)","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Jagini, N.P., Rao, R.R.: Exploring emotion specific features for emotion recognition system using pca approach. In: 2017 International Conference on Intelligent Computing and Control Systems (ICICCS), pp. 58\u201362 (2017)","DOI":"10.1109\/ICCONS.2017.8250527"},{"key":"21_CR25","unstructured":"Degottex, G.: Glottal source and vocal-tract separation. Ph.D. thesis (2010)"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Doukhan, D., Carrive, J., Vallet, F., Larcher, A., Meignier, S.: An open-source speaker gender detection framework for monitoring gender equality. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). pp. 5214\u20135218. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461471"},{"issue":"6","key":"21_CR27","first-page":"1026","volume":"92","author":"B Doval","year":"2006","unstructured":"Doval, B., d\u2019Alessandro, C., Henrich, N.: The spectrum of glottal flow models. Acta acustica united with acustica 92(6), 1026\u20131046 (2006)","journal-title":"Acta acustica united with acustica"},{"issue":"5","key":"21_CR28","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1109\/TMM.2008.927665","volume":"10","author":"Y Wang","year":"2008","unstructured":"Wang, Y., Guan, L.: Recognizing human emotional state from audiovisual signals. IEEE Trans. Multimedia 10(5), 936\u2013946 (2008)","journal-title":"IEEE Trans. Multimedia"},{"issue":"4","key":"21_CR29","doi-asserted-by":"publisher","first-page":"1858","DOI":"10.1121\/1.414405","volume":"98","author":"K Robinson","year":"1995","unstructured":"Robinson, K., Patterson, R.D.: The stimulus duration required to identify vowels, their octave, and their pitch chroma. J. Acoust. Soc. Am. 98(4), 1858\u20131865 (1995)","journal-title":"J. Acoust. Soc. Am."},{"key":"21_CR30","unstructured":"Wakefield, G.H.: Chromagram visualization of the singing voice. In: International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications (1999)"},{"key":"21_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1007\/978-3-319-46493-0_38","volume-title":"Computer Vision \u2013 ECCV 2016","author":"K He","year":"2016","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630\u2013645. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_38"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Burkhardt, F., Paeschke, A., Rolfes, M., Sendlmeier, W.F., Weiss, B.: A database of german emotional speech. In: Ninth European Conference on Speech Communication and Technology (2005)","DOI":"10.21437\/Interspeech.2005-446"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Livingstone, S.R., Russo, F.A.: The ryerson audio-visual database of emotional speech and song (ravdess): a dynamic, multimodal set of facial and vocal expressions in north american english. PloS one 13(5) (2018)","DOI":"10.1371\/journal.pone.0196391"},{"issue":"1","key":"21_CR34","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1080\/02699930126095","volume":"15","author":"C Breitenstein","year":"2001","unstructured":"Breitenstein, C., Lancker, D.V., Daum, I.: The contribution of speech rate and pitch variation to the perception of vocal emotions in a German and an American sample. Cogn. Emotion 15(1), 57\u201379 (2001)","journal-title":"Cogn. Emotion"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-63830-6_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T14:07:41Z","timestamp":1709820461000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-63830-6_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030638290","9783030638306"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-63830-6_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"19 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bangkok","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thailand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 November 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.apnns.org\/ICONIP2020","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"618","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":"187","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":"189","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":"30% - 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":"3.18","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":"3.68","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to COVID-19 pandemic the conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}