{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:48:47Z","timestamp":1740098927120,"version":"3.37.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319664286"},{"type":"electronic","value":"9783319664293"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-66429-3_44","type":"book-chapter","created":{"date-parts":[[2017,8,12]],"date-time":"2017-08-12T02:02:55Z","timestamp":1502503375000},"page":"445-455","source":"Crossref","is-referenced-by-count":4,"title":["Improving Speech-Based Emotion Recognition by Using Psychoacoustic Modeling and Analysis-by-Synthesis"],"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":"Andreas","family":"Wendemuth","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,8,13]]},"reference":[{"issue":"1","key":"44_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. IJSPS 4(1), 55\u201361 (2016)","journal-title":"IJSPS"},{"issue":"1","key":"44_CR2","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1007\/s13218-015-0414-8","volume":"30","author":"S Biundo","year":"2016","unstructured":"Biundo, S., Wendemuth, A.: Companion-technology for cognitive technical systems. KI - K\u00fcnstliche Intelligenz 30(1), 71\u201375 (2016)","journal-title":"KI - K\u00fcnstliche Intelligenz"},{"key":"44_CR3","unstructured":"Brandenburg, K.: MP3 and AAC explained. In: 17th AES International Conference: High-Quality Audio Coding, Florence, Italy, September 1999"},{"key":"44_CR4","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, pp. 1517\u20131520, Lisbon, Portugal (2005)","DOI":"10.21437\/Interspeech.2005-446"},{"issue":"1","key":"44_CR5","doi-asserted-by":"crossref","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":"44_CR6","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1007\/s12193-016-0213-z","volume":"10","author":"A Dhall","year":"2016","unstructured":"Dhall, A., Goecke, R., Gedeon, T., Sebe, N.: Emotion recognition in the wild. J. Multimodal User Interfaces 10, 95\u201397 (2016)","journal-title":"J. Multimodal User Interfaces"},{"key":"44_CR7","doi-asserted-by":"crossref","unstructured":"Engberg, I.S., Hansen, A.V.: Documentation of the danish emotional speech database (DES), Tech. rep. Aalborg University, Denmark (1996)","DOI":"10.21437\/Eurospeech.1997-482"},{"key":"44_CR8","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, Firenze, Italy (2010)","DOI":"10.1145\/1873951.1874246"},{"key":"44_CR9","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: Proceedings of STSIVA 2016, pp. 1\u20137 (2015)","DOI":"10.1109\/STSIVA.2015.7330399"},{"issue":"1","key":"44_CR10","doi-asserted-by":"crossref","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":"44_CR11","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)"},{"key":"44_CR12","unstructured":"IBM Corporation and Microsoft Corporation: Multimedia programming interface and data specifications 1.0. Tech. rep., August 1991"},{"key":"44_CR13","unstructured":"ITU-T: Methods for subjective determination of transmission quality. REC P.800 (1996), https:\/\/www.itu.int\/rec\/T-REC-P.800-199608-I\/en"},{"key":"44_CR14","unstructured":"ITU-T: Wideband Coding of Speech at around 16 kbit\/s using adaptive multi-rate wideband (AMR-WB). REC G.722.2 (2003), https:\/\/www.itu.int\/rec\/T-REC-G.722.2-200307-I\/en"},{"key":"44_CR15","unstructured":"ITU-T: Methods for objective and subjective assessment of speech quality (POLQA): Perceptual Objective Listening Quality Assessment. REC P.863, September 2014, http:\/\/www.itu.int\/rec\/T-REC-P.863-201409-I\/en"},{"key":"44_CR16","unstructured":"Jokisch, O., Maruschke, M., Meszaros, M., Iaroshenko, V.: Audio and speech quality survey of the opus codec in web real-time communication. In: Elektronische Sprachsignalverarbeitung 2016, vol. 81, Leipzig, Germany, pp. 254\u2013262 (2016)"},{"key":"44_CR17","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, vol. 86, Saarbr\u00fccken, Germany, pp. 1\u20138 (2017)"},{"key":"44_CR18","unstructured":"Paulsen, S.: QoS\/QoE-Modelle f\u00fcr den Dienst Voice over IP (VoIP). Ph.D. thesis, Universit\u00e4t Hamburg (2015)"},{"key":"44_CR19","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). doi: 10.1007\/978-3-642-14715-9_15"},{"key":"44_CR20","doi-asserted-by":"crossref","unstructured":"R\u00e4m\u00f6, A., Toukomaa, H.: Voice quality characterization of IETF opus codec. In: Proceedings of the INTERSPEECH-2011, pp. 2541\u20132544, Florence, Italy (2011)","DOI":"10.21437\/Interspeech.2011-650"},{"key":"44_CR21","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":"44_CR22","unstructured":"Siegert, I., Lotz, A.F., l. Duong, L., Wendemuth, A.: Measuring the impact of audio compression on the spectral quality of speech data. In: Elektronische Sprachsignalverarbeitung 2016, vol. 81, pp. 229\u2013236. Leipzig, Germany (2016)"},{"key":"44_CR23","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 5\u20137. Oktober 2016 in Paderborn, pp. 215\u2013219. VDE Verlag (2016)"},{"key":"44_CR24","unstructured":"Steininger, S., Schiel, F., Dioubina, O., Raubold, S.: Development of user-state conventions for the multimodal corpus in smartkom. In: Workshop on Multimodal Resources and Multimodal Systems Evaluation, Las Palmas, pp. 33\u201337 (2002)"},{"key":"44_CR25","doi-asserted-by":"crossref","unstructured":"Tickle, A., Raghu, S., Elshaw, M.: Emotional recognition from the speech signal for a virtual education agent. J. Phys.: Conf. Ser., vol. 450, p. 012053 (2013)","DOI":"10.1088\/1742-6596\/450\/1\/012053"},{"key":"44_CR26","unstructured":"Valin, J.M., Vos, K., Terriberry, T.: Definition of the opus audio codec. RFC 6716, http:\/\/tools.ietf.org\/html\/rfc6716"},{"key":"44_CR27","unstructured":"Valin, J.M., Maxwell, G., Terriberry, T.B., Vos, K.: The opus codec. In: 135th AES International Convention, New York, USA, October 2013"},{"key":"44_CR28","doi-asserted-by":"crossref","first-page":"1162","DOI":"10.1016\/j.specom.2006.04.003","volume":"48","author":"D Ververidis","year":"2006","unstructured":"Ververidis, D., Kotropoulos, C.: Emotional speech recognition: resources, features, and methods. Speech Commun. 48, 1162\u20131181 (2006)","journal-title":"Speech Commun."},{"key":"44_CR29","doi-asserted-by":"crossref","unstructured":"V\u00e1squez-Correa, J.C., Garc\u00eda, N., Vargas-Bonilla, J.F., Orozco-Arroyave, J.R., Arias-Londo\u00f1o, J.D., Quintero, M.O.L.: Evaluation of wavelet measures on automatic detection of emotion in noisy and telephony speech signals. In: International Carnahan Conference on Security Technology, pp. 1\u20136 (2014)","DOI":"10.1109\/CCST.2014.6986981"},{"key":"44_CR30","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1109\/TPAMI.2008.52","volume":"31","author":"Z Zeng","year":"2009","unstructured":"Zeng, Z., Pantic, M., Roisman, G.I., Huang, T.S.: A survey of affect recognition methods: audio, visual, and spontaneous expressions. IEEE Trans. Pattern Anal. Mach. Intell. 31, 39\u201358 (2009)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"44_CR31","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\/978-3-319-66429-3_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T00:51:34Z","timestamp":1692924694000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-66429-3_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319664286","9783319664293"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-66429-3_44","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}