{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:57:58Z","timestamp":1740099478914,"version":"3.37.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030238612"},{"type":"electronic","value":"9783030238629"}],"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\/978-3-030-23862-9_12","type":"book-chapter","created":{"date-parts":[[2019,7,4]],"date-time":"2019-07-04T14:39:21Z","timestamp":1562251161000},"page":"162-175","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating the Performance of ASR Systems for TV Interactions in Several Domestic Noise Scenarios"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7332-4901","authenticated-orcid":false,"given":"Pedro","family":"Be\u00e7a","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0492-2307","authenticated-orcid":false,"given":"Jorge","family":"Abreu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9741-6210","authenticated-orcid":false,"given":"Rita","family":"Santos","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9485-1727","authenticated-orcid":false,"given":"Ana","family":"Rodrigues","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,7,5]]},"reference":[{"key":"12_CR1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-49127-9","volume-title":"Handbook of Speech Processing","author":"J Benesty","year":"2008","unstructured":"Benesty, J.: Handbook of Speech Processing. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-49127-9"},{"doi-asserted-by":"crossref","unstructured":"Bernhaupt, R., Boutonnnet, M., Gatellier, B., Gimenez, Y., Pouchepanadin, C., Souiba, L.: A set of recommendations for the control of IPTV-systems via smartphones based on the understanding of users practices and needs (2012)","key":"12_CR2","DOI":"10.1145\/2325616.2325645"},{"unstructured":"Bernhaupt, R., Drouet, D., Manciet, F., Pirker, M., Pottier, G.: Using speech to search comparing built-in and ambient speech search in terms of privacy and user experience (2017)","key":"12_CR3"},{"issue":"3","key":"12_CR4","doi-asserted-by":"publisher","first-page":"1758","DOI":"10.1121\/1.5035758","volume":"143","author":"G Bohouta","year":"2018","unstructured":"Bohouta, G., K\u00ebpuska, V.: Performance of WUW and general ASR speech recognition systems in different acoustic environments. J. Acoust. Soc. Am. 143(3), 1758 (2018)","journal-title":"J. Acoust. Soc. Am."},{"unstructured":"Cordeiro, J.P.R.: Conversa\u00e7\u00e3o Homem-m\u00e1quina. Caracteriza\u00e7\u00e3o e Avalia\u00e7\u00e3o do Estado Actual das Solu\u00e7\u00f5es de Speech Recognition, Speech Synthesis e Sistemas de conversa\u00e7\u00e3o Homem-m\u00e1quina (2016)","key":"12_CR5"},{"unstructured":"Cultofmac. Nuance Beats Apple to Voice-Controlled Television with New Dragon TV Platform. https:\/\/www.cultofmac.com\/139335\/nuance-beats-apple-to-voice-controlled-television-with-new-dragon-tv-platform\/CultofMac . Accessed 20 Sept 2018","key":"12_CR6"},{"unstructured":"Gomes, R.: Teste de interfaces de Voz (2007)","key":"12_CR7"},{"doi-asserted-by":"crossref","unstructured":"Goto, J., Kim, Y.-B., Strl, N., Miyazaki, M., Komine, K., Uratani, N.: A spoken dialogue interface for TV operations based on data collected by using WOZ method (2004)","key":"12_CR8","DOI":"10.3115\/1075178.1075191"},{"issue":"2","key":"12_CR9","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1109\/TASLP.2014.2387414","volume":"23","author":"N Hirayama","year":"2015","unstructured":"Hirayama, N., Yoshino, K., Itoyama, K., Mori, S., Okuno, H.G.: Automatic speech recognition for mixed dialect utterances by mixing dialect language models. IEEE\/ACM Trans. Audio Speech Lang. Process. 23(2), 373\u2013382 (2015)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"12_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1007\/3-540-36572-9_17","volume-title":"Universal Access Theoretical Perspectives, Practice, and Experience","author":"A Ibrahim","year":"2003","unstructured":"Ibrahim, A., Johansson, P.: Multimodal dialogue systems: a case study for interactive TV. In: Carbonell, N., Stephanidis, C. (eds.) UI4ALL 2002. LNCS, vol. 2615, pp. 209\u2013218. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/3-540-36572-9_17"},{"issue":"03","key":"12_CR11","first-page":"20","volume":"07","author":"V K\u00ebpuska","year":"2017","unstructured":"K\u00ebpuska, V.: Comparing speech recognition systems (Microsoft API, Google API And CMU Sphinx). Int. J. Eng. Res. Appl. 07(03), 20\u201324 (2017)","journal-title":"Int. J. Eng. Res. Appl."},{"unstructured":"Zajechowski, M.: Automatic Speech Recognition (ASR) Software - An Introduction - Usability Geek. https:\/\/usabilitygeek.com\/automatic-speech-recognition-asr-software-an-introduction\/ . Accessed 30 Jan 2019","key":"12_CR12"},{"unstructured":"Morbini, F., Audhkhasi, K., Sagae, K., Artstein, R.: Which ASR should I choose for my dialogue system? In: Sigdial, pp. 394\u2013403, August 2013","key":"12_CR13"},{"issue":"3","key":"12_CR14","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1250\/ast.28.165","volume":"28","author":"Y Nakatoh","year":"2007","unstructured":"Nakatoh, Y., Kuwano, H., Kanamori, T., Hoshimi, M.: Speech recognition interface system for digital TV control. Acoust. Sci. Technol. 28(3), 165\u2013171 (2007)","journal-title":"Acoust. Sci. Technol."},{"key":"12_CR15","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1016\/j.neucom.2013.09.040","volume":"129","author":"SR Shahamiri","year":"2014","unstructured":"Shahamiri, S.R., Binti Salim, S.S.: Real-time frequency-based noise-robust automatic speech recognition using multi-nets artificial neural networks: a multi-views multi-learners\u2019 approach. Neurocomputing 129, 199\u2013207 (2014)","journal-title":"Neurocomputing"},{"key":"12_CR16","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1007\/978-3-642-10308-7_36","volume-title":"HCI and Usability for e-Inclusion","author":"Dimitris Spiliotopoulos","year":"2009","unstructured":"Spiliotopoulos, D., Stavropoulou, P., Kouroupetroglou, G.: Spoken dialogue interfaces: integrating usability. In: Holzinger, A., Miesenberger, K. (eds.) HCI and Usability for e-Inclusion. USAB 2009. LNCS, vol 5889, pp. 484\u2013499. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-10308-7_36"},{"unstructured":"Stolfi, G.: Perce\u00e7\u00e3o auditiva e compress\u00e3o de \u00e1udio. In Princ\u00edpios de Televis\u00e3o Digital, pp. 1\u201326 (2008)","key":"12_CR17"},{"doi-asserted-by":"crossref","unstructured":"He, L.D., Alex, A.: Why word error rate is not a good metric for speech recognizer training for the speech translation task? In: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5632\u20135635 (2011)","key":"12_CR18","DOI":"10.1109\/ICASSP.2011.5947637"},{"key":"12_CR19","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1007\/s10772-018-9520-y","volume":"21","author":"B Lecouteux","year":"2018","unstructured":"Lecouteux, B., Vacher, M., Portet, F.: Distant speech processing for smart home: comparison of ASR approaches in scattered microphone network for voice command. Int. J. Speech Technol. 21, 601\u2013618 (2018)","journal-title":"Int. J. Speech Technol."},{"doi-asserted-by":"crossref","unstructured":"Turunen, M., et al.: User expectations and user experience with different modalities in a mobile phone-controlled home entertainment system. In: Proceedings of the 11th International Conference on Human-Computer Interaction with Mobile Devices, pp. 1\u20134. ACM, New York (2009)","key":"12_CR20","DOI":"10.1145\/1613858.1613898"},{"unstructured":"Vipperla, R., Bozonnet, S., Wang, D., Evans, N.: Robust speech recognition in multi-source noise environments using convolutive non-negative matrix factorization. In: CHiME: Workshop on Machine Learning in Multisource Environments, pp. 74\u201379 (2011)","key":"12_CR21"},{"unstructured":"Ward, N., Rivera, A., Ward, K., Novick, D.: Some Usability issues and research priorities in spoken dialog applications. Departmental Technical Reports (2005)","key":"12_CR22"},{"key":"12_CR23","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1007\/978-3-319-64680-0_14","volume-title":"New Era for Robust Speech Recognition","author":"JP Barker","year":"2017","unstructured":"Barker, J.P., Marxer, R., Vincent, E., Watanabe, S.: The CHiME challenges: robust speech recognition in everyday environments. In: Watanabe, S., Delcroix, M., Metze, F., Hershey, J.R. (eds.) New Era for Robust Speech Recognition, pp. 327\u2013344. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-64680-0_14"},{"issue":"3","key":"12_CR24","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1007\/s10772-018-9520-y","volume":"21","author":"B Lecouteux","year":"2018","unstructured":"Lecouteux, B., Vacher, B., Portet, F.: Distant speech processing for smart home: comparison of ASR approaches in scattered microphone network for voice command. Int. J. Speech Technol. 21(3), 601\u2013618 (2018)","journal-title":"Int. J. Speech Technol."},{"issue":"02","key":"12_CR25","doi-asserted-by":"publisher","first-page":"1550032","DOI":"10.1142\/S0219843615500322","volume":"13","author":"MA Nematollahi","year":"2016","unstructured":"Nematollahi, M.A., Al-Haddad, S.A.R.: Distant speaker recognition: an overview. Int. J. Humanoid Robot. 13(02), 1550032 (2016)","journal-title":"Int. J. Humanoid Robot."},{"doi-asserted-by":"crossref","unstructured":"Pellegrini, T., et al.: A corpus-based study of elderly and young speakers of European Portuguese: acoustic correlates and their impact on speech recognition performance (2013)","key":"12_CR26","DOI":"10.21437\/Interspeech.2013-241"},{"key":"12_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-319-09761-9_1","volume-title":"Lecture Notes in Computer Science","author":"Annika H\u00e4m\u00e4l\u00e4inen","year":"2014","unstructured":"H\u00e4m\u00e4l\u00e4inen, A.: Automatically Recognising European Portuguese Children\u2019s Speech (2014). https:\/\/doi.org\/10.1007\/978-3-319-09761-9_1"},{"doi-asserted-by":"crossref","unstructured":"Ali, A., Magdy, W., Renals, S.: Multi-Reference Evaluation for Dialectal Speech Recognition System: A Study for Egyptian ASR (2015)","key":"12_CR28","DOI":"10.18653\/v1\/W15-3213"},{"unstructured":"Garner, P.N., Imseng, D., Meyer, T.: Automatic Speech Recognition and Translation of a Swiss German Dialect: Walliserdeutsch (2014). http:\/\/www.swissinfo.ch\/ . Accessed 12 Mar 2019","key":"12_CR29"},{"unstructured":"deMauro, T.: Lingu\u00edstica Elementar. Editorial Estampa, Lisboa (2000)","key":"12_CR30"}],"container-title":["Communications in Computer and Information Science","Applications and Usability of Interactive TV"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-23862-9_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,22]],"date-time":"2022-09-22T23:03:21Z","timestamp":1663887801000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-23862-9_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030238612","9783030238629"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-23862-9_12","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"5 July 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"jAUTI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Iberoamerican Conference on Applications and Usability of Interactive TV","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bernal","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Argentina","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 October 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2018","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":"jatui2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/jauti2018.web.unq.edu.ar\/jauti-2018\/","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":"OSC","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"45","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":"13","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":"29% - 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":"1,5","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}