{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T00:36:07Z","timestamp":1743122167844,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030377304"},{"type":"electronic","value":"9783030377311"}],"license":[{"start":{"date-parts":[[2019,12,24]],"date-time":"2019-12-24T00:00:00Z","timestamp":1577145600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-37731-1_2","type":"book-chapter","created":{"date-parts":[[2019,12,27]],"date-time":"2019-12-27T06:02:51Z","timestamp":1577426571000},"page":"14-25","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Speaker-Aware Speech Emotion Recognition by Fusing Amplitude and Phase Information"],"prefix":"10.1007","author":[{"given":"Lili","family":"Guo","sequence":"first","affiliation":[]},{"given":"Longbiao","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Jianwu","family":"Dang","sequence":"additional","affiliation":[]},{"given":"Zhilei","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Haotian","family":"Guan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,12,24]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Schuller, B., Steidl, S., Batliner, A., Burkhardt, F., Devillers, L.: The INTERSPEECH 2010 paralinguistic challenge. In: Eleventh Annual Conference of the International Speech Communication Association (INTERSPEECH), pp. 2794\u20132797 (2010)","DOI":"10.21437\/Interspeech.2010-739"},{"issue":"3","key":"2_CR2","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1016\/j.patcog.2010.09.020","volume":"44","author":"M Ayadi El","year":"2011","unstructured":"El Ayadi, M., Kamel, M.S., Karray, F.: Survey on speech emotion recognition: features, classification schemes, and databases. Pattern Recognit. 44(3), 572\u2013587 (2011)","journal-title":"Pattern Recognit."},{"issue":"9\u201310","key":"2_CR3","doi-asserted-by":"publisher","first-page":"1062","DOI":"10.1016\/j.specom.2011.01.011","volume":"53","author":"B Schuller","year":"2011","unstructured":"Schuller, B., Batliner, A., Steidl, S., Seppi, D.: Recognising realistic emotions and affect in speech: state of the art and lessons learnt from the first challenge. Speech Commun. 53(9\u201310), 1062\u20131087 (2011)","journal-title":"Speech Commun."},{"key":"2_CR4","unstructured":"Slaney, M., McRoberts, G.: Baby ears: a recognition system for affective vocalizations. In: 1998 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 2, pp. 985\u2013988 (1998)"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Luengo, I., Navas, E., Hern\u00e1ez, I., S\u00e1nchez, J.: Automatic emotion recognition using prosodic parameters. In: Ninth European Conference on Speech Communication and Technology, pp. 493\u2013496 (2005)","DOI":"10.21437\/Interspeech.2005-324"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Wang, Z., Tashev, I.: Learning utterance-level representations for speech emotion and age\/gender recognition using deep neural networks. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5150\u20135154 (2017)","DOI":"10.1109\/ICASSP.2017.7953138"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Lee, J., Tashev, I.: High-level feature representation using recurrent neural network for speech emotion recognition. In: Sixteenth Annual Conference of the International Speech Communication Association (INTERSPEECH), pp. 1537\u20131540 (2015)","DOI":"10.21437\/Interspeech.2015-336"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Bertero, D., Fung, P.: A first look into a convolutional neural network for speech emotion detection. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5115\u20135119 (2017)","DOI":"10.1109\/ICASSP.2017.7953131"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Satt, A., Rozenberg, S., Hoory, R.: Efficient emotion recognition from speech using deep learning on spectrograms. In: Eighteenth Annual Conference of the International Speech Communication Association (INTERSPEECH), pp. 1089\u20131093 (2017)","DOI":"10.21437\/Interspeech.2017-200"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Keren, G., Schuller, B.: Convolutional RNN: an enhanced model for extracting features from sequential data. In: International Joint Conference on Neural Networks, pp. 3412\u20133419 (2016)","DOI":"10.1109\/IJCNN.2016.7727636"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Guo, L., Wang, L., Dang, J., Zhang, L., Guan, H.: A feature fusion method based on extreme learning machine for speech emotion recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2666\u20132670 (2018)","DOI":"10.1109\/ICASSP.2018.8462219"},{"issue":"1","key":"2_CR12","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/TASL.2006.876858","volume":"15","author":"R Hegde","year":"2007","unstructured":"Hegde, R., Murthy, H., Gadde, V.: Significance of the modified group delay feature in speech recognition. IEEE Trans. Audio Speech Lang. Process. 15(1), 190\u2013202 (2007)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"issue":"4","key":"2_CR13","doi-asserted-by":"publisher","first-page":"1085","DOI":"10.1109\/TASL.2011.2172422","volume":"20","author":"S Nakagawa","year":"2012","unstructured":"Nakagawa, S., Wang, L., Ohtsuka, S.: Speaker identification and verification by combining MFCC and phase information. IEEE Trans. Audio Speech Lang. Process. 20(4), 1085\u20131095 (2012)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Oo, Z., Kawakami, Y., Wang, L., Nakagawa, S., Xiao, X., Iwahashi, M.: DNN-based amplitude and phase feature enhancement for noise robust speaker identification. In: Seventeenth Annual Conference of the International Speech Communication Association (INTERSPEECH), pp. 2204\u20132208 (2016)","DOI":"10.21437\/Interspeech.2016-717"},{"issue":"4","key":"2_CR15","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1109\/JSTSP.2017.2694139","volume":"11","author":"L Wang","year":"2017","unstructured":"Wang, L., Nakagawa, S., Zhang, Z., Yoshida, Y., Kawakami, Y.: Spoofing speech detection using modified relative phase information. IEEE J. Sel. Top. Signal Process. 11(4), 660\u2013670 (2017)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Zhang, B., Provost, E.M., Essi, G.: Cross-corpus acoustic emotion recognition from singing and speaking: a multi-task learning approach. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5805\u20135809 (2016)","DOI":"10.1109\/ICASSP.2016.7472790"},{"key":"2_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1007\/978-3-030-01418-6_76","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2018","author":"L Zhang","year":"2018","unstructured":"Zhang, L., Wang, L., Dang, J., Guo, L., Yu, Q.: Gender-aware CNN-BLSTM for speech emotion recognition. In: K\u016frkov\u00e1, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds.) ICANN 2018. LNCS, vol. 11139, pp. 782\u2013790. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01418-6_76"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Tao, F., Liu, G.: Advanced LSTM: a study about better time dependency modeling in emotion recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2906\u20132910 (2018)","DOI":"10.1109\/ICASSP.2018.8461750"},{"key":"2_CR19","doi-asserted-by":"publisher","first-page":"75798","DOI":"10.1109\/ACCESS.2019.2921390","volume":"7","author":"L Guo","year":"2019","unstructured":"Guo, L., Wang, L., Dang, J., et al.: Exploration of complementary features for speech emotion recognition based on kernel extreme learning machine. IEEE Access 7, 75798\u201375809 (2019)","journal-title":"IEEE Access"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Kua, J., Epps, J., Ambikairajah, E., Choi, E.: LS regularization of group delay features for speaker recognition. In: Tenth Annual Conference of the International Speech Communication Association (INTERSPEECH), pp. 2887\u20132890 (2009)","DOI":"10.21437\/Interspeech.2009-46"},{"key":"2_CR21","unstructured":"Hegde, R., Murthy, H., Rao, G.: Application of the modified group delay function to speaker identification and discrimination. In: 2004 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 1, pp. 517\u2013520 (2004)"},{"key":"2_CR22","unstructured":"Chen, Y., Chen, Y., Wang, X., Tang, X.: Deep learning face representation by joint identification-verification. In: Advances in Neural Information Processing Systems, pp. 1988\u20131996 (2014)"},{"key":"2_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1007\/978-3-319-10599-4_7","volume-title":"Computer Vision \u2013 ECCV 2014","author":"Z Zhang","year":"2014","unstructured":"Zhang, Z., Luo, P., Loy, C.C., Tang, X.: Facial landmark detection by deep multi-task learning. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 94\u2013108. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_7"},{"issue":"5","key":"2_CR24","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1016\/0924-2716(95)90116-V","volume":"50","author":"GM Foody","year":"1995","unstructured":"Foody, G.M.: Cross-entropy for the evaluation of the accuracy of a fuzzy land cover classification with fuzzy ground data. ISPRS J. Photogramm. Remote. Sens. 50(5), 2\u201312 (1995)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"issue":"1","key":"2_CR25","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1016\/j.neucom.2005.12.126","volume":"70","author":"GB Huang","year":"2006","unstructured":"Huang, G.B., Zhu, Q.Y., Siew, C.K.: Extreme learning machine: theory and applications. Neurocomputing 70(1), 489\u2013501 (2006)","journal-title":"Neurocomputing"},{"issue":"10","key":"2_CR26","doi-asserted-by":"publisher","first-page":"1759","DOI":"10.1016\/j.patcog.2005.03.028","volume":"38","author":"QY Zhu","year":"2005","unstructured":"Zhu, Q.Y., Qin, A.K., Suganthan, P.N., Huang, G.B.: Evolutionary extreme learning machine. Pattern Recognit. 38(10), 1759\u20131763 (2005)","journal-title":"Pattern Recognit."},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Han, K., Yu, D., Tashev, I.: Speech emotion recognition using deep neural network and extreme learning machine. In: Fifteenth Annual Conference of the International Speech Communication Association (INTERSPEECH), pp. 223\u2013227 (2014)","DOI":"10.21437\/Interspeech.2014-57"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Burkhardt, F., Paeschke, A., Rolfes, M.: A database of German emotional speech. In: Ninth European Conference on Speech Communication and Technology, pp. 1517\u20131520 (2005)","DOI":"10.21437\/Interspeech.2005-446"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Provost, E.: Identifying salient sub-utterance emotion dynamics using flexible units and estimates of affective flow. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3682\u20133686 (2013)","DOI":"10.1109\/ICASSP.2013.6638345"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Busso, C., Metallinou, A., Narayanan, S.S.: Iterative feature normalization for emotional speech detection. In: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5692\u20135695 (2011)","DOI":"10.1109\/ICASSP.2011.5947652"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-37731-1_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,9]],"date-time":"2022-10-09T11:37:36Z","timestamp":1665315456000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-37731-1_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,24]]},"ISBN":["9783030377304","9783030377311"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-37731-1_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019,12,24]]},"assertion":[{"value":"24 December 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Daejeon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","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":"5 January 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 January 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.mmm2020.kr\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-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":"171","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":"40","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":"23% - 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":"5","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)"}},{"value":"Of the 171 submissions, 46 were accepted as poster papers; of the 49 special session paper submissions, 28 were accepted for oral presentation and 8 for poster presentation; 9 demo papers and 10 VBS papers were also accepted.","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)"}}]}}