{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T16:17:11Z","timestamp":1743092231918,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030602758"},{"type":"electronic","value":"9783030602765"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/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":"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\/978-3-030-60276-5_6","type":"book-chapter","created":{"date-parts":[[2020,10,4]],"date-time":"2020-10-04T07:02:44Z","timestamp":1601794964000},"page":"57-67","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Speech Emotion Recognition Using Spectrogram Patterns as Features"],"prefix":"10.1007","author":[{"given":"Umut","family":"Avci","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,9,29]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Bhavan, A., Chauhan, P., Hitkul, Shah, R.R.: Bagged support vector machines for emotion recognition from speech. Knowl. Based Syst. 184, 104886 (2019)","key":"6_CR1","DOI":"10.1016\/j.knosys.2019.104886"},{"issue":"6","key":"6_CR2","doi-asserted-by":"publisher","first-page":"1154","DOI":"10.1016\/j.dsp.2012.05.007","volume":"22","author":"L Chen","year":"2012","unstructured":"Chen, L., Mao, X., Xue, Y., Cheng, L.L.: Speech emotion recognition: features and classification models. Digit. Signal Proc. 22(6), 1154\u20131160 (2012)","journal-title":"Digit. Signal Proc."},{"key":"6_CR3","doi-asserted-by":"publisher","first-page":"7","DOI":"10.12700\/APH.17.6.2020.6.1","volume":"17","author":"G Gosztolya","year":"2020","unstructured":"Gosztolya, G.: Using the Fisher vector representation for audio-based emotion recognition. Acta Polytechnica Hungarica 17, 7\u201323 (2020)","journal-title":"Acta Polytechnica Hungarica"},{"doi-asserted-by":"crossref","unstructured":"Huang, K., Wu, C., Hong, Q., Su, M., Zeng, Y.: Speech emotion recognition using convolutional neural network with audio word-based embedding. In: ISCSLP, pp. 265\u2013269 (2018)","key":"6_CR4","DOI":"10.1109\/ISCSLP.2018.8706610"},{"doi-asserted-by":"crossref","unstructured":"Ishi, C.T., Kanda, T.: Prosodic and voice quality analyses of loud speech: differences of hot anger and far-directed speech. In: SMM, pp. 1\u20135 (2019)","key":"6_CR5","DOI":"10.21437\/SMM.2019-1"},{"doi-asserted-by":"crossref","unstructured":"Kaya, H., Fedotov, D., Ye\u015filkanat, A., Verkholyak, O., Zhang, Y., Karpov, A.: LSTM based cross-corpus and cross-task acoustic emotion recognition. In: INTERSPEECH, pp. 521\u2013525 (2018)","key":"6_CR6","DOI":"10.21437\/Interspeech.2018-2298"},{"key":"6_CR7","doi-asserted-by":"publisher","first-page":"117327","DOI":"10.1109\/ACCESS.2019.2936124","volume":"7","author":"RA Khalil","year":"2019","unstructured":"Khalil, R.A., Jones, E., Babar, M.I., Jan, T., Zafar, M.H., Alhussain, T.: Speech emotion recognition using deep learning techniques: a review. IEEE Access 7, 117327\u2013117345 (2019)","journal-title":"IEEE Access"},{"doi-asserted-by":"crossref","unstructured":"Lin, J., Wu, C., Wei, W.: Emotion recognition of conversational affective speech using temporal course modeling. In: INTERSPEECH, pp. 1336\u20131340 (2013)","key":"6_CR8","DOI":"10.1109\/APSIPA.2014.7041621"},{"doi-asserted-by":"crossref","unstructured":"Liu, Y., Zheng, Y.F.: One-against-all multi-class SVM classification using reliability measures. In: IJCNN, vol. 2, pp. 849\u2013854 (2005)","key":"6_CR9","DOI":"10.1109\/IJCNN.2005.1555963"},{"issue":"5","key":"6_CR10","doi-asserted-by":"publisher","first-page":"e0196391","DOI":"10.1371\/journal.pone.0196391","volume":"13","author":"SR Livingstone","year":"2018","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), e0196391 (2018)","journal-title":"PLoS ONE"},{"doi-asserted-by":"crossref","unstructured":"Mao, S., Tao, D., Zhang, G., Ching, P.C., Lee, T.: Revisiting hidden Markov models for speech emotion recognition. In: ICASSP, pp. 6715\u20136719 (2019)","key":"6_CR11","DOI":"10.1109\/ICASSP.2019.8683172"},{"unstructured":"Milgram, J., Cheriet, M., Sabourin, R.: \u201cOne against one\u201d or \u201cOne against all\u201d: which one is better for handwriting recognition with SVMs? In: IWFHR (2006)","key":"6_CR12"},{"unstructured":"Platt, J.C., Cristianini, N., Shawe-Taylor, J.: Large margin DAGs for multiclass classification. In: ANIPS, pp. 547\u2013553 (2000)","key":"6_CR13"},{"doi-asserted-by":"crossref","unstructured":"Satt, A., Rozenberg, S., Hoory, R.: Efficient emotion recognition from speech using deep learning on spectrograms. In: INTERSPEECH, pp. 1089\u20131093 (2017)","key":"6_CR14","DOI":"10.21437\/Interspeech.2017-200"},{"issue":"1","key":"6_CR15","doi-asserted-by":"publisher","first-page":"20","DOI":"10.3390\/technologies7010020","volume":"7","author":"E Spyrou","year":"2019","unstructured":"Spyrou, E., Nikopoulou, R., Vernikos, I., Mylonas, P.: Emotion recognition from speech using the bag-of-visual words on audio segment spectrograms. Technologies 7(1), 20 (2019)","journal-title":"Technologies"},{"doi-asserted-by":"crossref","unstructured":"Trigeorgis, G., et al.: Adieu features? End-to-end speech emotion recognition using a deep convolutional recurrent network. In: ICASSP, pp. 5200\u20135204 (2016)","key":"6_CR16","DOI":"10.1109\/ICASSP.2016.7472669"},{"unstructured":"Tripathi, S., Beigi, H.S.M.: Multi-modal emotion recognition on IEMOCAP dataset using deep learning. arXiv abs\/1804.05788 (2018)","key":"6_CR17"},{"unstructured":"Tripathi, S., Kumar, A., Ramesh, A., Singh, C., Yenigalla, P.: Deep learning-based emotion recognition system using speech features and transcriptions. arXiv abs\/1906.05681 (2019)","key":"6_CR18"},{"doi-asserted-by":"crossref","unstructured":"Tzirakis, P., Zhang, J., Schuller, B.W.: End-to-end speech emotion recognition using deep neural networks. In: ICASSP, pp. 5089\u20135093 (2018)","key":"6_CR19","DOI":"10.1109\/ICASSP.2018.8462677"},{"doi-asserted-by":"crossref","unstructured":"Wang, Y., Hu, W.: Speech emotion recognition based on improved MFCC. In: CSAE, pp. 1\u20137 (2018)","key":"6_CR20","DOI":"10.1145\/3207677.3278037"},{"issue":"11","key":"6_CR21","first-page":"2994","volume":"26","author":"H Yang","year":"2015","unstructured":"Yang, H., Duan, L., Hu, B., Deng, S., Wang, W., Qin, P.: Mining top-k distinguishing sequential patterns with gap constraint. J. Softw. 26(11), 2994\u20133009 (2015)","journal-title":"J. Softw."},{"doi-asserted-by":"crossref","unstructured":"Yang, Z., Hirschberg, J.: Predicting arousal and valence from waveforms and spectrograms using deep neural networks. In: INTERSPEECH, pp. 3092\u20133096 (2018)","key":"6_CR22","DOI":"10.21437\/Interspeech.2018-2397"},{"doi-asserted-by":"crossref","unstructured":"Zhang, B., Essl, G., Provost, E.M.: Recognizing emotion from singing and speaking using shared models. In: ACII, pp. 139\u2013145 (2015)","key":"6_CR23","DOI":"10.1109\/ACII.2015.7344563"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-60276-5_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T12:50:23Z","timestamp":1723726223000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-60276-5_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030602758","9783030602765"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-60276-5_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"29 September 2020","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":"St. Petersburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","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":"7 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 October 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/specom.nw.ru\/2020\/","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":"160","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":"65","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":"41% - 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":"Due to the Corona pandemic SPECOM 2020 was held as a virtual event","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)"}}]}}