{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:52:37Z","timestamp":1740099157616,"version":"3.37.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319995786"},{"type":"electronic","value":"9783319995793"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","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":[[2018]]},"DOI":"10.1007\/978-3-319-99579-3_64","type":"book-chapter","created":{"date-parts":[[2018,8,24]],"date-time":"2018-08-24T07:36:09Z","timestamp":1535096169000},"page":"625-635","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Utilizing Psychoacoustic Modeling to Improve Speech-Based Emotion Recognition"],"prefix":"10.1007","author":[{"given":"Ingo","family":"Siegert","sequence":"first","affiliation":[]},{"given":"Alicia Flores","family":"Lotz","sequence":"additional","affiliation":[]},{"given":"Olga","family":"Egorow","sequence":"additional","affiliation":[]},{"given":"Susann","family":"Wolff","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,8,25]]},"reference":[{"issue":"1","key":"64_CR1","first-page":"55","volume":"4","author":"A Albahri","year":"2016","unstructured":"Albahri, A., Lech, M., Cheng, E.: Effect of speech compression on the automatic recognition of emotions. Int. J. Signal Process. Syst. 4(1), 55\u201361 (2016)","journal-title":"Int. J. Signal Process. Syst."},{"key":"64_CR2","doi-asserted-by":"crossref","unstructured":"Burkhardt, F., Paeschke, A., Rolfes, M., Sendlmeier, W., Weiss, B.: A database of German emotional speech. In: Proceedings of the INTERSPEECH 2005, Lisbon, Portugal, pp. 1517\u20131520 (2005)","DOI":"10.21437\/Interspeech.2005-446"},{"issue":"1","key":"64_CR3","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1558\/sll.2004.11.1.83","volume":"11","author":"C Byrne","year":"2004","unstructured":"Byrne, C., Foulkes, P.: The \u2018mobile phone effect\u2019 on vowel formants. Int. J. Speech Lang. Law 11(1), 83\u2013102 (2004)","journal-title":"Int. J. Speech Lang. Law"},{"key":"64_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1007\/978-3-319-72038-8_15","volume-title":"Intelligent Human Computer Interaction","author":"R B\u00f6ck","year":"2017","unstructured":"B\u00f6ck, R., Egorow, O., Siegert, I., Wendemuth, A.: Comparative study on normalisation in emotion recognition from speech. In: Horain, P., Achard, C., Mallem, M. (eds.) IHCI 2017. LNCS, vol. 10688, pp. 189\u2013201. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-72038-8_15"},{"key":"64_CR5","doi-asserted-by":"crossref","unstructured":"Eyben, F., W\u00f6llmer, M., Schuller, B.: openSMILE - the Munich versatile and fast open-source audio feature extractor. In: Proceedings of the ACM MM 2010. p. s.p., Firenze, Italy (2010)","DOI":"10.1145\/1873951.1874246"},{"key":"64_CR6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-68888-4","volume-title":"Psychoacoustics. Facts and Models","author":"H Fastl","year":"2007","unstructured":"Fastl, H., Zwicker, E.: Psychoacoustics. Facts and Models. Springer, Berlin (2007). https:\/\/doi.org\/10.1007\/978-3-540-68888-4"},{"key":"64_CR7","doi-asserted-by":"crossref","unstructured":"Garc\u00eda, N., V\u00e1squez-Correa, J.C., Arias-Londo\u00f1o, J.D., V\u00e1rgas-Bonilla, J.F., Orozco-Arroyave, J.R.: Automatic emotion recognition in compressed speech using acoustic and non-linear features. In: 20th Symposium on Signal Processing, Images and Computer Vision (STSIVA), Bogota, Colombia, pp. 1\u20137 (2015)","DOI":"10.1109\/STSIVA.2015.7330399"},{"issue":"1","key":"64_CR8","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1145\/1656274.1656278","volume":"11","author":"M Hall","year":"2009","unstructured":"Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The weka data mining software: an update. SIGKDD Explor. Newsl. 11(1), 10\u201318 (2009)","journal-title":"SIGKDD Explor. Newsl."},{"key":"64_CR9","doi-asserted-by":"crossref","unstructured":"Hansen, J., Bou-Ghazale, S.: Getting started with SUSAS: a speech under simulated and actual stress database. In: Proceedings of EUROSPEECH 1997, Rhodes, Greece, vol. 4, pp. 1743\u20131746 (1997)","DOI":"10.21437\/Eurospeech.1997-494"},{"key":"64_CR10","unstructured":"Hoene, C., Valin, J.M., Vos, K., Skoglund, J.: Summary of Opus listening test results draft-valin-codec-results-03. Internet-draft, IETF (2013). https:\/\/tools.ietf.org\/html\/draft-ietf-codec-results-03"},{"key":"64_CR11","doi-asserted-by":"crossref","unstructured":"Lefter, I., Nefs, H.T., Jonker, C.M., Rothkrantz, L.: Cross-corpus analysis for acoustic recognition of negative interactions. In: Proceedings of the 6th ACII, Xian, China, pp. 132\u2013138 (2015)","DOI":"10.1109\/ACII.2015.7344562"},{"key":"64_CR12","unstructured":"Lotz, A.F., Siegert, I., Maruschke, M., Wendemuth, A.: Audio compression and its impact on emotion recognition in affective computing. In: Elektronische Sprachsignalverarbeitung 2017. Tagungsband der 28. Konferenz, vol. 86, pp. 1\u20138. TUDpress, Saarbr\u00fccken (2017)"},{"key":"64_CR13","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1007\/978-3-319-43958-7_69","volume-title":"Speech and Computer","author":"M Maruschke","year":"2016","unstructured":"Maruschke, M., Jokisch, O., Meszaros, M., Trojahn, F., Hoffmann, M.: Quality assessment of two fullband audio codecs supporting real-time communication. In: Ronzhin, A., Potapova, R., N\u00e9meth, G. (eds.) SPECOM 2016. LNCS (LNAI), vol. 9811, pp. 571\u2013579. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-43958-7_69"},{"issue":"2","key":"64_CR14","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1109\/93.388209","volume":"2","author":"D Pan","year":"1995","unstructured":"Pan, D.: A tutorial on mpeg\/audio compression. IEEE MultiMed. 2(2), 60\u201374 (1995)","journal-title":"IEEE MultiMed."},{"key":"64_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/978-3-642-14715-9_15","volume-title":"Human Behavior Understanding","author":"T Pfister","year":"2010","unstructured":"Pfister, T., Robinson, P.: Speech emotion classification and public speaking skill assessment. In: Salah, A.A., Gevers, T., Sebe, N., Vinciarelli, A. (eds.) HBU 2010. LNCS, vol. 6219, pp. 151\u2013162. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-14715-9_15"},{"key":"64_CR16","doi-asserted-by":"crossref","unstructured":"Schuller, B., M\u00fcller, R., H\u00f6rnler, B., H\u00f6thker, A., Konosu, H., Rigoll, G.: Audiovisual recognition of spontaneous interest within conversations. In: Proceedings of the 9th ACM ICMI, pp. 30\u201337 (2007)","DOI":"10.1145\/1322192.1322201"},{"key":"64_CR17","doi-asserted-by":"crossref","unstructured":"Schuller, B., Vlasenko, B., Eyben, F., Rigoll, G., Wendemuth, A.: Acoustic emotion recognition: a benchmark comparison of performances. In: Proceedings of the IEEE ASRU 2009, Merano, Italy, pp. 552\u2013557 (2009)","DOI":"10.1109\/ASRU.2009.5372886"},{"key":"64_CR18","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1109\/T-AFFC.2010.8","volume":"1","author":"B Schuller","year":"2010","unstructured":"Schuller, B., Vlasenko, B., Eyben, F., Wollmer, M., Stuhlsatz, A., Wendemuth, A., Rigoll, G.: Cross-corpus acoustic emotion recognition: variances and strategies. IEEE Trans. Affect. Comput. 1, 119\u2013131 (2010)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"64_CR19","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/978-3-319-66429-3_6","volume-title":"Speech and Computer","author":"I Siegert","year":"2017","unstructured":"Siegert, I., Jokisch, O., Lotz, A.F., Trojahn, F., Meszaros, M., Maruschke, M.: Acoustic cues for the perceptual assessment of surround sound. In: Karpov, A., Potapova, R., Mporas, I. (eds.) SPECOM 2017. LNCS (LNAI), vol. 10458, pp. 65\u201375. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-66429-3_6"},{"key":"64_CR20","unstructured":"Siegert, I., Lotz, A.F., Duong, L.L., Wendemuth, A.: Measuring the impact of audio compression on the spectral quality of speech data. In: Elektronische Sprachsignalverarbeitung 2016. Tagungsband der 27. Konferenz, vol. 81, pp. 229\u2013236. TUDpress, Leipzig (2016)"},{"key":"64_CR21","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/978-3-319-66429-3_44","volume-title":"Speech and Computer","author":"I Siegert","year":"2017","unstructured":"Siegert, I., Lotz, A.F., Egorow, O., Wendemuth, A.: Improving speech-based emotion recognition by using psychoacoustic modeling and analysis-by-synthesis. In: Karpov, A., Potapova, R., Mporas, I. (eds.) SPECOM 2017. LNCS (LNAI), vol. 10458, pp. 445\u2013455. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-66429-3_44"},{"key":"64_CR22","unstructured":"Siegert, I., Lotz, A.F., Maruschke, M., Jokisch, O., Wendemuth, A.: Emotion intelligibility within codec-compressed and reduced bandwith speech. In: ITG-Fb. 267: Speech Communication: 12. ITG-Fachtagung Sprachkommunikation, pp. 215\u2013219. VDE Verlag, Paderborn, October 2016"},{"issue":"1","key":"64_CR23","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1109\/TASLP.2015.2487051","volume":"24","author":"M Tahon","year":"2016","unstructured":"Tahon, M., Devillers, L.: Towards a small set of robust acoustic features for emotion recognition: challenges. EEE\/ACM Trans. Audio Speech Lang. Process. 24(1), 16\u201328 (2016)","journal-title":"EEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"64_CR24","doi-asserted-by":"crossref","unstructured":"Tahon, M., Devillers, L.: Acoustic measures characterizing anger across corpora collected in artificial or natural context. In: International Conference on Speech Prosody (SP 2010), Chicago, USA, May 2010","DOI":"10.21437\/SpeechProsody.2010-134"},{"key":"64_CR25","doi-asserted-by":"publisher","first-page":"012053","DOI":"10.1088\/1742-6596\/450\/1\/012053","volume":"450","author":"A Tickle","year":"2013","unstructured":"Tickle, A., Raghu, S., Elshaw, M.: Emotional recognition from the speech signal for a virtual education agent. J. Phys. Conf. Ser. 450, 012053 (2013)","journal-title":"J. Phys. Conf. Ser."},{"issue":"1","key":"64_CR26","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1109\/TASL.2009.2023186","volume":"18","author":"JM Valin","year":"2010","unstructured":"Valin, J.M., Terriberry, T.B., Montgomery, C., Maxwell, G.: A high-quality speech and audio codec with less than 10-ms delay. Trans. Audio Speech Lang. Process. 18(1), 58\u201367 (2010)","journal-title":"Trans. Audio Speech Lang. Process."},{"key":"64_CR27","unstructured":"Valin, J.M., Vos, K., Terriberry, T.B.: Definition of the Opus Audio Codec. RFC 6716, RFC Editor, September 2012. https:\/\/tools.ietf.org\/html\/rfc6716"},{"key":"64_CR28","doi-asserted-by":"crossref","unstructured":"Xu, X., et al.: Survey on discriminative feature selection for speech emotion recognition. In: 9th ISCSLP, pp. 345\u2013349 (2014)","DOI":"10.1109\/ISCSLP.2014.6936641"},{"key":"64_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Weninger, F., W\u00f6llmer, M., Schuller, B.: Unsupervised learning in cross-corpus acoustic emotion recognition. In: Proceedings of the IEEE ASRU 2011, Waikoloa, USA, pp. 523\u2013528 (2011)","DOI":"10.1109\/ASRU.2011.6163986"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-99579-3_64","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,9]],"date-time":"2024-07-09T15:25:32Z","timestamp":1720538732000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-99579-3_64"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319995786","9783319995793"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-99579-3_64","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}