{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T23:29:26Z","timestamp":1785540566971,"version":"3.56.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031483080","type":"print"},{"value":"9783031483097","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-48309-7_16","type":"book-chapter","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:03:21Z","timestamp":1700597001000},"page":"189-199","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Driver Speech Detection in\u00a0Real Driving Scenario"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5348-9378","authenticated-orcid":false,"given":"Mrinmoy","family":"Bhattacharjee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9425-978X","authenticated-orcid":false,"given":"Shikha","family":"Baghel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8135-7938","authenticated-orcid":false,"given":"S. R. Mahadeva","family":"Prasanna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,11,22]]},"reference":[{"key":"16_CR1","doi-asserted-by":"publisher","unstructured":"Ahmed, S.F., Jaffari, R., Jawaid, M., Ahmed, S.S., Talpur, S.: An MFCC-based secure framework for voice assistant systems. In: International Conference on Cyber Warfare and Security (ICCWS), pp. 57\u201361 (2022). https:\/\/doi.org\/10.1109\/ICCWS56285.2022.9998446","DOI":"10.1109\/ICCWS56285.2022.9998446"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Angkititrakul, P., Petracca, M., Sathyanarayana, A., Hansen, J.H.: UTDrive: driver behavior and speech interactive systems for in-vehicle environments. In: 2007 IEEE Intelligent Vehicles Symposium, pp. 566\u2013569 (2007)","DOI":"10.1109\/IVS.2007.4290175"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Ashok, A., Pawlak, J., Paplu, S., Zafar, Z., Berns, K.: Paralinguistic cues in speech to adapt robot behavior in human-robot interaction. In: 9th IEEE RAS\/EMBS International Conference for Biomedical Robotics and Biomechatronics (BioRob), pp. 1\u20136 (2022)","DOI":"10.1109\/BioRob52689.2022.9925505"},{"key":"16_CR4","first-page":"12449","volume":"33","author":"A Baevski","year":"2020","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. Adv. Neural Inf. Process. Syst. 33, 12449\u201312460 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Bo\u0159il, H., Sadjadi, S.O., Kleinschmidt, T., Hansen, J.H.L.: Analysis and detection of cognitive load and frustration in drivers\u2019 speech. In: Interspeech, pp. 502\u2013505 (2010)","DOI":"10.21437\/Interspeech.2010-208"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Devi, C.A., Renuka, D.K.: Multimodal emotion recognition framework using a decision-level fusion and feature-level fusion approach. IETE J. Res. 1\u201312 (2023)","DOI":"10.1080\/03772063.2023.2173668"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Eyben, F., W\u00f6llmer, M., Schuller, B.: Opensmile: the munich versatile and fast open-source audio feature extractor. In: ACM International Conference on Multimedia, pp. 1459\u20131462 (2010)","DOI":"10.1145\/1873951.1874246"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Fan, Z., Li, M., Zhou, S., Xu, B.: Exploring wav2vec 2.0 on speaker verification and language identification. arXiv preprint arXiv:2012.06185 (2020)","DOI":"10.21437\/Interspeech.2021-1280"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Grosche, P., M\u00fcller, M., Kurth, F.: Cyclic tempogram-a mid-level tempo representation for music signals. In: IEEE International Conference on Acoustics, Speech and Signal Process (ICASSP), pp. 5522\u20135525. IEEE (2010)","DOI":"10.1109\/ICASSP.2010.5495219"},{"issue":"4","key":"16_CR10","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1109\/MSP.2017.2699039","volume":"34","author":"JH Hansen","year":"2017","unstructured":"Hansen, J.H., Busso, C., Zheng, Y., Sathyanarayana, A.: Driver modeling for detection and assessment of driver distraction: examples from the UTDrive test bed. IEEE Signal Process. Maga. 34(4), 130\u2013142 (2017)","journal-title":"IEEE Signal Process. Maga."},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Kristjansson, T., Deligne, S., Olsen, P.: Voicing features for robust speech detection. In: Interspeech, pp. 369\u2013372 (2005)","DOI":"10.21437\/Interspeech.2005-186"},{"key":"16_CR12","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1007\/978-3-031-20980-2_35","volume-title":"Speech and Computer","author":"D Kumar","year":"2022","unstructured":"Kumar, D., Patil, P.K.V., Agarwal, A., Prasanna, S.R.M.: Fake speech detection using OpenSMILE features. In: Prasanna, S.R.M., Karpov, A., Samudravijaya, K., Agrawal, S.S. (eds.) SPECOM 2022. LNCS, vol. 13721, pp. 404\u2013415. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20980-2_35"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Lin, B., Wang, L.: Exploiting information from native data for non-native automatic pronunciation assessment. In: IEEE Spoken Language Technology Workshop (SLT), pp. 708\u2013714 (2023)","DOI":"10.1109\/SLT54892.2023.10022486"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: The empathetic car: exploring emotion inference via driver behaviour and traffic context. In: Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, vol. 5, no. 3, pp. 1\u201334 (2021)","DOI":"10.1145\/3478078"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Martelaro, N., Teevan, J., Iqbal, S.T.: An exploration of speech-based productivity support in the car. In: CHI Conference on Human Factors in Computing Systems, CHI 2019, pp. 1\u201312. Association for Computing Machinery, New York (2019)","DOI":"10.1145\/3290605.3300494"},{"key":"16_CR16","unstructured":"Moreno, A., et al.: SPEECHDAT-CAR: a large speech database for automotive environments. In: 2nd International Conference on Language Resources and Evaluation (LREC), pp. 1\u20136 (2000)"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Moro-Velazquez, L., Villalba, J., Dehak, N.: Using X-vectors to automatically detect Parkinson\u2019s disease from speech. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1155\u20131159 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053770"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Murugaiyan, S., Uyyala, S.R.: Aspect-based sentiment analysis of customer speech data using deep convolutional neural network and BiLSTM. Cogn. Comput. 1\u201318 (2023)","DOI":"10.1007\/s12559-023-10127-6"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Pappagari, R., Wang, T., Villalba, J., Chen, N., Dehak, N.: X-vectors meet emotions: a study on dependencies between emotion and speaker recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7169\u20137173 (2020)","DOI":"10.1109\/ICASSP40776.2020.9054317"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Pepino, L., Riera, P., Ferrer, L.: Emotion recognition from speech using wav2vec 2.0 embeddings. In: Interspeech, pp. 3400\u20133404 (2021)","DOI":"10.21437\/Interspeech.2021-703"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Raj, D., Snyder, D., Povey, D., Khudanpur, S.: Probing the information encoded in X-vectors. In: IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 726\u2013733 (2019)","DOI":"10.1109\/ASRU46091.2019.9003979"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Sathyanarayana, A., Sadjadi, S.O., Hansen, J.H.L.: Leveraging speech-active regions towards active safety in vehicles. In: IEEE International Conference on Emerging Signal Processing Applications, pp. 48\u201351 (2012)","DOI":"10.1109\/ESPA.2012.6152443"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Shokouhi, N., Sathyanarayana, A., Sadjadi, S.O., Hansen, J.H.: Overlapped-speech detection with applications to driver assessment for in-vehicle active safety systems. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2834\u20132838 (2013)","DOI":"10.1109\/ICASSP.2013.6638174"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Snyder, D., Garcia-Romero, D., Sell, G., Povey, D., Khudanpur, S.: X-Vectors: robust DNN embeddings for speaker recognition. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5329\u20135333 (2018)","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"16_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2023.3252631","volume":"72","author":"J Svatos","year":"2023","unstructured":"Svatos, J., Holub, J.: Impulse acoustic event detection, classification, and localization system. IEEE Trans. Instrument. Meas. 72, 1\u201315 (2023). https:\/\/doi.org\/10.1109\/TIM.2023.3252631","journal-title":"IEEE Trans. Instrument. Meas."},{"key":"16_CR26","unstructured":"Wood, C., Torkkola, K., Kundalkar, S.: Using driver\u2019s speech to detect cognitive workload. In: SPECOM, pp. 215\u2013222 (2004)"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Yin, B., Ruiz, N., Chen, F., Khawaja, M.A.: Automatic cognitive load detection from speech features. In: 19th Australasian Conference on Computer-Human Interaction: Entertaining User Interfaces, OZCHI 2007, pp. 249\u2013255. Association for Computing Machinery, New York (2007)","DOI":"10.1145\/1324892.1324946"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-48309-7_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:11:49Z","timestamp":1700597509000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-48309-7_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031483080","9783031483097"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-48309-7_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 November 2023","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":"Dharwad","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iitdh.ac.in\/specom-2023\/","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":"174","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":"94","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":"54% - 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)"}}]}}