{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:59:14Z","timestamp":1740099554436,"version":"3.37.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030313715"},{"type":"electronic","value":"9783030313722"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-31372-2_12","type":"book-chapter","created":{"date-parts":[[2019,9,27]],"date-time":"2019-09-27T00:02:49Z","timestamp":1569542569000},"page":"139-150","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["External Attention LSTM Models for Cognitive Load Classification from Speech"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9322-3128","authenticated-orcid":false,"given":"Ascensi\u00f3n","family":"Gallardo-Antol\u00edn","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7908-5400","authenticated-orcid":false,"given":"Juan M.","family":"Montero","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,9,27]]},"reference":[{"unstructured":"Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems. Software (2015). tensorflow.org","key":"12_CR1"},{"doi-asserted-by":"crossref","unstructured":"Boril, H., Sadjadi, O., Kleinschmidt, T., Hansen, J.: Analysis and detection of cognitive load and frustration in drivers speech. In: Proceedings of INTERSPEECH 2010, pp. 502\u2013505 (2010)","key":"12_CR2","DOI":"10.21437\/Interspeech.2010-208"},{"unstructured":"Chollet, F., et al.: Keras: the python deep learning library. Software (2015). https:\/\/github.com\/fchollet\/keras","key":"12_CR3"},{"unstructured":"Chorowski, J., Bahdanau, D., Serdyuk, D., Cho, K., Bengio, Y.: Attention-based models for speech recognition. In: Proceedings of NIPS 2015, pp. 577\u2013585 (2015)","key":"12_CR4"},{"doi-asserted-by":"crossref","unstructured":"Eyben, F., Huber, B., Marchi, E., Schuller, D., Schuller, B.: Real-time robust recognition of speakers\u2019 emotions and characteristics on mobile platforms. In: Proceedings of ACII 2015, pp. 778\u2013780 (2015)","key":"12_CR5","DOI":"10.1109\/ACII.2015.7344658"},{"doi-asserted-by":"crossref","unstructured":"Eyben, F., Weninger, F., Gro $$\\beta $$ , F., Schuller, B.: Recent developments in openSMILE, the munich open-source multimedia feature extractor. In: Proceedings of MM 2013, pp. 835\u2013838 (2013)","key":"12_CR6","DOI":"10.1145\/2502081.2502224"},{"key":"12_CR7","first-page":"115","volume":"3","author":"FA Gers","year":"2003","unstructured":"Gers, F.A., Schraudolph, N.N., Schmidhuber, J.: Learning precise timing with LSTM recurrent networks. J. Mach. Learn. Res. 3, 115\u2013143 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"12_CR8","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1007\/978-1-4419-1428-6","volume-title":"Encyclopedia of the Sciences of Learning","author":"T Gog van","year":"2012","unstructured":"van Gog, T., Paas, F.: Cognitive load measurement. In: Seel, N.M. (ed.) Encyclopedia of the Sciences of Learning, pp. 599\u2013601. Springer, Boston (2012). https:\/\/doi.org\/10.1007\/978-1-4419-1428-6"},{"key":"12_CR9","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.: The WEKA data mining software: an update. SIGKDD Explor. 11, 10\u201318 (2009)","journal-title":"SIGKDD Explor."},{"doi-asserted-by":"crossref","unstructured":"Huang, C., Narayanan, S.: Attention assisted discovery of sub-utterance structure in speech emotion recognition. In: Proceedings of INTERSPEECH 2016, pp. 1387\u20131391 (2016)","key":"12_CR10","DOI":"10.21437\/Interspeech.2016-448"},{"doi-asserted-by":"crossref","unstructured":"Huang, C., Narayanan, S.: Deep convolutional recurrent neural network with attention mechanism for robust speech emotion recognition. In: Proceedings of ICME 2017, pp. 583\u2013588 (2017)","key":"12_CR11","DOI":"10.1109\/ICME.2017.8019296"},{"issue":"2","key":"12_CR12","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1016\/j.apergo.2010.08.005","volume":"42","author":"K Huttunen","year":"2011","unstructured":"Huttunen, K., Ker\u00e4nen, H., V\u00e4yrynen, E., P\u00e4\u00e4kk\u00f6nen, R., Leino, T.: Effect of cognitive load on speech prosody in aviation: evidence from military simulator flights. Appl. Ergon. 42(2), 348\u2013357 (2011)","journal-title":"Appl. Ergon."},{"doi-asserted-by":"crossref","unstructured":"Kua, J.M.K., Sethu, V., Le, P., Ambikairajah, E.: The UNSW submission to INTERSPEECH 2014 compare cognitive load challenge. In: Proceedings of INTERSPEECH 2014, pp. 746\u2013750 (2014)","key":"12_CR13","DOI":"10.21437\/Interspeech.2014-113"},{"issue":"5","key":"12_CR14","doi-asserted-by":"publisher","first-page":"2962","DOI":"10.1121\/1.405815","volume":"93","author":"SE Lively","year":"1993","unstructured":"Lively, S.E., Pisoni, D.B., Summers, W.V., Bernacki, R.H.: Effects of cognitive workload on speech production: acoustic analyses and perceptual consequences. J. Acoust. Soc. Am. 93(5), 2962\u20132973 (1993)","journal-title":"J. Acoust. Soc. Am."},{"issue":"1","key":"12_CR15","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.csl.2014.04.001","volume":"30","author":"J Lude\u00f1a-Choez","year":"2015","unstructured":"Lude\u00f1a-Choez, J., Gallardo-Antol\u00edn, A.: Feature extraction based on the high-pass filtering of audio signals for acoustic event classification. Comput. Speech Lang. 30(1), 32\u201342 (2015)","journal-title":"Comput. Speech Lang."},{"issue":"1","key":"12_CR16","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1016\/j.eswa.2015.10.018","volume":"46","author":"J Lude\u00f1a-Choez","year":"2016","unstructured":"Lude\u00f1a-Choez, J., Gallardo-Antol\u00edn, A.: Acoustic event classification using spectral band selection and non-negative matrix factorization-based features. Expert. Syst. Appl. 46(1), 77\u201386 (2016)","journal-title":"Expert. Syst. Appl."},{"doi-asserted-by":"crossref","unstructured":"Luong, M.T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025 (2015)","key":"12_CR17","DOI":"10.18653\/v1\/D15-1166"},{"doi-asserted-by":"crossref","unstructured":"McFee, B., et al.: Librosa: audio and music signal analysis in python. In: Proceedings of SCIPY 2015, pp. 18\u201325 (2015)","key":"12_CR18","DOI":"10.25080\/Majora-7b98e3ed-003"},{"doi-asserted-by":"crossref","unstructured":"Mirsamadi, S., Barsoum, E., Zhang, C.: Automatic speech emotion recognition using recurrent neural networks with local attention. In: Proceedings of ICASSP 2017, pp. 2227\u20132231 (2017)","key":"12_CR19","DOI":"10.1109\/ICASSP.2017.7952552"},{"key":"12_CR20","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1007\/3-540-44566-8_3","volume-title":"User Modeling 2001","author":"C M\u00fcller","year":"2001","unstructured":"M\u00fcller, C., Gro\u00dfmann-Hutter, B., Jameson, A., Rummer, R., Wittig, F.: Recognizing time pressure and cognitive load on the basis of speech: an experimental study. In: Bauer, M., Gmytrasiewicz, P.J., Vassileva, J. (eds.) UM 2001. LNCS (LNAI), vol. 2109, pp. 24\u201333. Springer, Heidelberg (2001). https:\/\/doi.org\/10.1007\/3-540-44566-8_3"},{"issue":"12","key":"12_CR21","doi-asserted-by":"publisher","first-page":"2263","DOI":"10.1109\/TASLP.2016.2602884","volume":"24","author":"Y Qian","year":"2016","unstructured":"Qian, Y., Bi, M., Tan, T., Yu, K.: Very deep convolutional neural networks for noise robust speech recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 24(12), 2263\u20132276 (2016)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"doi-asserted-by":"crossref","unstructured":"Rao, K., Peng, F., Sak, H., Beaufays, F.: Grapheme-to-phoneme conversion using long short-term memory recurrent neural networks. In: Proceedings of ICASSP 2015, pp. 4225\u20134229 (2015)","key":"12_CR22","DOI":"10.1109\/ICASSP.2015.7178767"},{"doi-asserted-by":"crossref","unstructured":"Schuller, B., et al.: The INTERSPEECH 2014 computational paralinguistics challenge: cognitive & physical load. In: Proceedings of INTERSPEECH 2014 (2014)","key":"12_CR23","DOI":"10.21437\/Interspeech.2014-104"},{"doi-asserted-by":"crossref","unstructured":"van Segbroeck, M., Travadi, R., Vaz, C., Kim, J., Black, M.P., Potamianos, A., Narayanan, S.S.: Classification of cognitive load from speech using an i-vector framework. In: Proceedings of INTERSPEECH 2014, pp. 751\u2013755 (2014)","key":"12_CR24","DOI":"10.21437\/Interspeech.2014-114"},{"issue":"6","key":"12_CR25","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1037\/h0054651","volume":"18","author":"JR Stroop","year":"1935","unstructured":"Stroop, J.R.: Studies of interference in serial verbal reactions. J. Exp. Psychol. 18(6), 643 (1935)","journal-title":"J. Exp. Psychol."},{"unstructured":"Yap, T.F.: Speech production under cognitive load: effects and classification. Ph.D. dissertation, The University of New South Wales, Sydney, Australia (2012)","key":"12_CR26"},{"issue":"1","key":"12_CR27","doi-asserted-by":"publisher","first-page":"e0146917","DOI":"10.1371\/journal.pone.0146917","volume":"11","author":"R Zazo","year":"2016","unstructured":"Zazo, R., Lozano-D\u00edez, A., Gonz\u00e1lez-Dom\u00ednguez, J., Toledano, D.T., Gonz\u00e1lez-Rodr\u00edguez, J.: Language identification in short utterances using long short-term memory (LSTM) recurrent neural networks. PLoS ONE 11(1), e0146917 (2016)","journal-title":"PLoS ONE"}],"container-title":["Lecture Notes in Computer Science","Statistical Language and Speech Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-31372-2_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T01:26:51Z","timestamp":1664501211000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-31372-2_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030313715","9783030313722"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-31372-2_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"27 September 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SLSP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Statistical Language and Speech Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ljubljana","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovenia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 October 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"slsp2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/slsp2019.irdta.eu\/","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":"48","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":"25","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":"1","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":"52% - 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":"4","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)"}}]}}