{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T12:20:06Z","timestamp":1743078006889,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319651712"},{"type":"electronic","value":"9783319651729"}],"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\/978-3-319-65172-9_26","type":"book-chapter","created":{"date-parts":[[2017,8,1]],"date-time":"2017-08-01T04:38:54Z","timestamp":1501562334000},"page":"303-313","source":"Crossref","is-referenced-by-count":0,"title":["Emotion Prediction of Sound Events Based on Transfer Learning"],"prefix":"10.1007","author":[{"given":"Stavros","family":"Ntalampiras","sequence":"first","affiliation":[]},{"given":"Ilyas","family":"Potamitis","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,8,2]]},"reference":[{"key":"26_CR1","first-page":"686","volume":"60","author":"S Ntalampiras","year":"2012","unstructured":"Ntalampiras, S., Potamitis, I., Fakotakis, N.: Acoustic detection of human activities in natural environments. J. Audio Eng. Soc. 60, 686\u2013695 (2012)","journal-title":"J. Audio Eng. Soc."},{"key":"26_CR2","doi-asserted-by":"crossref","first-page":"1694","DOI":"10.1121\/1.4977749","volume":"141","author":"S Ntalampiras","year":"2017","unstructured":"Ntalampiras, S.: A transfer learning framework for predicting the emotional content of generalized sound events. J. Acoust. Soc. Am. 141, 1694\u20131701 (2017)","journal-title":"J. Acoust. Soc. Am."},{"key":"26_CR3","doi-asserted-by":"crossref","first-page":"3399","DOI":"10.1121\/1.4970902","volume":"140","author":"S Shigeno","year":"2016","unstructured":"Shigeno, S.: Effects of discrepancy between vocal emotion and the emotional meaning of speech on identifying the speakers emotions. J. Acoust. Soc. Am. 140, 3399\u20133399 (2016)","journal-title":"J. Acoust. Soc. Am."},{"key":"26_CR4","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1016\/S0167-6393(02)00084-5","volume":"40","author":"KR Scherer","year":"2003","unstructured":"Scherer, K.R.: Vocal communication of emotion: a review of research paradigms. Speech Commun. 40, 227\u2013256 (2003)","journal-title":"Speech Commun."},{"key":"26_CR5","doi-asserted-by":"crossref","first-page":"3109","DOI":"10.1121\/1.2188647","volume":"119","author":"V Hozjan","year":"2006","unstructured":"Hozjan, V., Kai, Z.: A rule-based emotion-dependent feature extraction method for emotion analysis from speech. J. Acoust. Soc. Am. 119, 3109\u20133120 (2006)","journal-title":"J. Acoust. Soc. Am."},{"key":"26_CR6","doi-asserted-by":"crossref","first-page":"561","DOI":"10.3758\/BF03193026","volume":"39","author":"M Marcell","year":"2007","unstructured":"Marcell, M., Malatanos, M., Leahy, C., Comeaux, C.: Identifying, rating, and remembering environmental sound events. Behav. Res. Methods 39, 561\u2013569 (2007)","journal-title":"Behav. Res. Methods"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Garner, T., Grimshaw, M.: A climate of fear: considerations for designing a virtual acoustic ecology of fear. In: Proceedings of 6th Audio Mostly Conference: A Conference on Interaction with Sound, pp. 31\u201338 (2011)","DOI":"10.1145\/2095667.2095672"},{"key":"26_CR8","doi-asserted-by":"crossref","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 Recogn. 44, 572\u2013587 (2011)","journal-title":"Pattern Recogn."},{"key":"26_CR9","doi-asserted-by":"crossref","first-page":"2303","DOI":"10.1121\/1.4920410","volume":"137","author":"R Asadi","year":"2015","unstructured":"Asadi, R., Fell, H.: Improving the accuracy of speech emotion recognition using acoustic landmarks and Teager energy operator features. J. Acoust. Soc. Am. 137, 2303\u20132303 (2015)","journal-title":"J. Acoust. Soc. Am."},{"key":"26_CR10","doi-asserted-by":"crossref","first-page":"2422","DOI":"10.1121\/1.4878044","volume":"135","author":"C Lee","year":"2014","unstructured":"Lee, C., Lui, S., So, C.: Visualization of time-varying joint development of pitch and dynamics for speech emotion recognition. J. Acoust. Soc. Am. 135, 2422\u20132422 (2014)","journal-title":"J. Acoust. Soc. Am."},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Fukuyama, S., Goto, M.: Music emotion recognition with adaptive aggregation of Gaussian process regressors. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 71\u201375 (2016)","DOI":"10.1109\/ICASSP.2016.7471639"},{"key":"26_CR12","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1109\/ACCESS.2014.2333095","volume":"2","author":"K Markov","year":"2014","unstructured":"Markov, K., Matsui, T.: Music genre and emotion recognition using Gaussian processes. IEEE Access 2, 688\u2013697 (2014)","journal-title":"IEEE Access"},{"key":"26_CR13","first-page":"40:1","volume":"3","author":"Y Yi-Hsuan","year":"2012","unstructured":"Yi-Hsuan, Y., Chen, H.: Machine recognition of music emotion: a review. ACM Trans. Intell. Syst. Technol. 3, 40:1\u201340:30 (2012)","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"26_CR14","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1111\/j.1469-8986.1975.tb00016.x","volume":"12","author":"M-J Gang","year":"1975","unstructured":"Gang, M.-J., Teft, L.: Individual differences in heart rate responses to affective sound. Psychophysiology 12, 423\u2013426 (1975)","journal-title":"Psychophysiology"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Schuller, B., Hantke, S., Weninger, F., Han, W., Zhang, Z., Narayanan, S.: Automatic recognition of emotion evoked by general sound events. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 341\u2013344 (2012)","DOI":"10.1109\/ICASSP.2012.6287886"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Drossos, K., Floros, A., Kanellopoulos, N.-G.: Affective acoustic ecology: towards emotionally enhanced sound events. In: Proceedings of 7th Audio Mostly Conference: A Conference on Interaction with Sound, pp. 109\u2013116 (2012)","DOI":"10.1145\/2371456.2371474"},{"key":"26_CR17","first-page":"1","volume":"292","author":"F Weninger","year":"2013","unstructured":"Weninger, F., Eyben, F., Schuller, B., Mortillaro, M., Scherer, K.-R.: On the acoustics of emotion in audio: what speech, music and sound have in common. Front. Psychol. 292, 1\u201312 (2013)","journal-title":"Front. Psychol."},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Schuller, B., Steidl, S., Batliner, A., Vinciarelli, A., Scherer, K.-R., Ringeval, F., Chetouani, M., Weninger, F., Eyben, F., Marchi, E., Mortillaro, M., Salamin, H., Polychroniou, A., Valente, F., Kim, S.: The INTERSPEECH 2013 computational paralinguistics challenge: social signals, conflict, emotion, autism. In: INTERSPEECH, pp. 148\u2013152 (2013)","DOI":"10.21437\/Interspeech.2013-56"},{"key":"26_CR19","unstructured":"Bradley, M., Lang, P.-J.: The International Affective Digitized Sounds (2nd edn. IADS-2): Affective Ratings of Sounds and Instruction Manual. Technical report B-3, University of Florida, Gainesville, Fl (2004)"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Soleymani, M., Caro, M.-N., Schmidt, E.-M., Sha, C.-Y., Yang, Y.H.: 1000 songs for emotional analysis of music. In: Proceedings of 2nd ACM International Workshop on Crowdsourcing for Multimedia, pp. 1\u20136 (2013)","DOI":"10.1145\/2506364.2506365"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Ntalampiras, S., Potamitis, I.: On predicting the unpleasantness level of a sound event. In: 15th Annual Conference of International Speech Communication Association (INTERSPEECH), pp. 1782\u20131785 (2014)","DOI":"10.21437\/Interspeech.2014-406"},{"key":"26_CR22","doi-asserted-by":"crossref","first-page":"4323","DOI":"10.1109\/TSP.2009.2025107","volume":"57","author":"P Clark","year":"2009","unstructured":"Clark, P., Atlas, L.: Time-frequency coherent modulation filtering of nonstationary signals. IEEE Trans. Signal Process. 57, 4323\u20134332 (2009)","journal-title":"IEEE Trans. Signal Process."},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Schimmel, S.M., Atlas, L.E., Nie, K.: Feasibility of single channel speaker separation based on modulation frequency analysis. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 605\u2013608 (2007)","DOI":"10.1109\/ICASSP.2007.366985"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Vinton, M.S., Atlas, L.E.: Scalable and progressive audio codec. In: 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing, Proceedings (ICASSP 2001), pp. 3277\u20133280 (2001)","DOI":"10.1109\/ICASSP.2001.940358"},{"key":"26_CR25","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1109\/TASL.2007.908129","volume":"16","author":"A Klapuri","year":"2008","unstructured":"Klapuri, A.: Multipitch analysis of polyphonic music and speech signals using an auditory model. IEEE Trans. Audio Speech Lang. Process. 16, 255\u2013266 (2008)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"26_CR26","unstructured":"Atlas, L., Clark, P., Schimmel, S.: Modulation Toolbox Version 2.1 for MATLAB. http:\/\/isdl.ee.washington.edu\/projects\/modulationtoolbox\/ . Accessed Sept 2010"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Jalalvand, A., Triefenbach, F., Verstraeten, D., Martens, J.: Connected digit recognition by means of reservoir computing. In: Proceedings of 12th Annual Conference of the International Speech Communication Association, pp. 1725\u20131728 (2011)","DOI":"10.21437\/Interspeech.2011-192"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"Verstraeten, D., Schrauwen, B., Stroobandt, D.: Reservoir-based techniques for speech recognition. In: International Joint Conference on Neural Networks, IJCNN 2006, pp. 1050\u20131053 (2006)","DOI":"10.1109\/IJCNN.2006.246804"},{"key":"26_CR29","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1126\/science.1091277","volume":"304","author":"H Jaeger","year":"2004","unstructured":"Jaeger, H., Haas, H.: Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science 304, 78\u201380 (2004)","journal-title":"Science"},{"key":"26_CR30","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.cosrev.2009.03.005","volume":"3","author":"M Luko\u0161evi\u010dius","year":"2009","unstructured":"Luko\u0161evi\u010dius, M., Jaeger, H.: Survey: reservoir computing approaches to recurrent neural network training. Comput. Sci. Rev. 3, 127\u2013149 (2009)","journal-title":"Comput. Sci. Rev."},{"key":"26_CR31","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1016\/j.neunet.2007.04.003","volume":"20","author":"D Verstraeten","year":"2007","unstructured":"Verstraeten, D., Schrauwen, B., d\u2019Haene, M., Stroobandt, D.: An experimental unification of reservoir computing methods. Neural Netw. 20, 391\u2013403 (2007)","journal-title":"Neural Netw."},{"key":"26_CR32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2009\/807162","volume":"2009","author":"S Ntalampiras","year":"2009","unstructured":"Ntalampiras, S., Potamitis, I., Fakotakis, N.: Exploiting temporal feature integration for generalized sound recognition. EURASIP J. Adv. Signal Process. 2009, 1\u201312 (2009)","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"26_CR33","doi-asserted-by":"crossref","first-page":"358","DOI":"10.17743\/jaes.2015.0025","volume":"63","author":"S Ntalampiras","year":"2015","unstructured":"Ntalampiras, S.: Audio pattern recognition of baby crying sound events. J. Audio Eng. Soc 63, 358\u2013369 (2015)","journal-title":"J. Audio Eng. Soc"},{"key":"26_CR34","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1037\/h0049235","volume":"58","author":"B Scharf","year":"1961","unstructured":"Scharf, B.: Complex sounds and critical bands. Psychol. Bull. 58, 205\u2013217 (1961)","journal-title":"Psychol. Bull."},{"key":"26_CR35","doi-asserted-by":"crossref","unstructured":"Yi-Lin, L., Gang, W.: Speech emotion recognition based on HMM and SVM. In: International Conference on Machine Learning and Cybernetics, vol. 8, pp. 4898\u20134901 (2005)","DOI":"10.1109\/ICMLC.2005.1527805"},{"key":"26_CR36","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1023\/B:STCO.0000035301.49549.88","volume":"14","author":"A-J Smola","year":"2004","unstructured":"Smola, A.-J., Sch\u00f6lkopf, B.: A tutorial on support vector regression. Stat. Comput. 14, 199\u2013222 (2004)","journal-title":"Stat. Comput."}],"container-title":["Communications in Computer and Information Science","Engineering Applications of Neural Networks"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-65172-9_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,31]],"date-time":"2022-07-31T17:30:10Z","timestamp":1659288610000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-65172-9_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319651712","9783319651729"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-65172-9_26","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2017]]}}}