{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,29]],"date-time":"2025-03-29T19:32:19Z","timestamp":1743276739724,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030878016"},{"type":"electronic","value":"9783030878023"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-87802-3_50","type":"book-chapter","created":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T23:36:52Z","timestamp":1632267412000},"page":"553-564","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Recognition of Heavily Accented and Emotional Speech of English and Czech Holocaust Survivors Using Various DNN\u00a0Architectures"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4761-1645","authenticated-orcid":false,"given":"Josef V.","family":"Psutka","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9453-0034","authenticated-orcid":false,"given":"Ale\u0161","family":"Pra\u017e\u00e1k","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2639-6731","authenticated-orcid":false,"given":"Jan","family":"Van\u011bk","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,22]]},"reference":[{"issue":"10","key":"50_CR1","doi-asserted-by":"publisher","first-page":"1533","DOI":"10.1109\/TASLP.2014.2339736","volume":"22","author":"O Abdel-Hamid","year":"2014","unstructured":"Abdel-Hamid, O., Mohamed, A., Jiang, H., Deng, L., Penn, G., Yu, D.: Convolutional neural networks for speech recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 22(10), 1533\u20131545 (2014). https:\/\/doi.org\/10.1109\/TASLP.2014.2339736","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"4","key":"50_CR2","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1109\/TSA.2004.828702","volume":"12","author":"W Byrne","year":"2004","unstructured":"Byrne, W., et al.: Automatic recognition of spontaneous speech for access to multilingual oral history archives. IEEE Trans. Speech Audio Process. 12(4), 420\u2013435 (2004). https:\/\/doi.org\/10.1109\/TSA.2004.828702","journal-title":"IEEE Trans. Speech Audio Process."},{"issue":"4","key":"50_CR3","doi-asserted-by":"publisher","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2011","unstructured":"Dehak, N., Kenny, P.J., Dehak, R., Dumouchel, P., Ouellet, P.: Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19(4), 788\u2013798 (2011). https:\/\/doi.org\/10.1109\/TASL.2010.2064307","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"50_CR4","doi-asserted-by":"publisher","unstructured":"Ghahremani, P., Manohar, V., Povey, D., Khudanpur, S.: Acoustic modelling from the signal domain using CNNs. In: Interspeech 2016, pp. 3434\u20133438 (2016). https:\/\/doi.org\/10.21437\/Interspeech.2016-1495","DOI":"10.21437\/Interspeech.2016-1495"},{"key":"50_CR5","doi-asserted-by":"publisher","unstructured":"Hadian, H., Sameti, H., Povey, D., Khudanpur, S.: Flat-start single-stage discriminatively trained HMM-based models for ASR. IEEE ACM Trans. Audio Speech Lang. Process. 26(11), 1949\u20131961 (2018). https:\/\/doi.org\/10.1109\/TASLP.2018.2848701","DOI":"10.1109\/TASLP.2018.2848701"},{"key":"50_CR6","unstructured":"MALACH project (2006). https:\/\/malach.umiacs.umd.edu\/"},{"key":"50_CR7","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1007\/978-3-540-74628-7_45","volume-title":"Text, Speech and Dialogue","author":"P Mihajlik","year":"2007","unstructured":"Mihajlik, P., Fegy\u00f3, T., N\u00e9meth, B., T\u00fcske, Z., Tr\u00f3n, V.: Towards automatic transcription of large spoken archives in agglutinating languages \u2013 Hungarian ASR for the MALACH project. In: Matou\u0161ek, V., Mautner, P. (eds.) TSD 2007. LNCS (LNAI), vol. 4629, pp. 342\u2013349. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-74628-7_45"},{"key":"50_CR8","doi-asserted-by":"publisher","unstructured":"Novak, J.R., Nobuaki, M., Keikichi, H.: Phonetisaurus: Exploring grapheme-to-phoneme conversion with joint n-gram models in the WFST framework. Nat. Lang. Eng. 22(6), 907\u2013938 (2016). https:\/\/doi.org\/10.1017\/S1351324915000315","DOI":"10.1017\/S1351324915000315"},{"key":"50_CR9","doi-asserted-by":"crossref","unstructured":"Peddinti, V., Povey, D., Khudanpur, S.: A time delay neural network architecture for efficient modeling of long temporal contexts. In: Interspeech 2015, pp. 3214\u20133218 (2015)","DOI":"10.21437\/Interspeech.2015-647"},{"key":"50_CR10","doi-asserted-by":"publisher","unstructured":"Picheny, M., T\u00fcske, Z., Kingsbury, B., Audhkhasi, K., Cui, X., Saon, G.: Challenging the boundaries of speech recognition: the MALACH corpus. In: Interspeech 2019, pp. 326\u2013330 (2019). https:\/\/doi.org\/10.21437\/Interspeech.2019-1907","DOI":"10.21437\/Interspeech.2019-1907"},{"key":"50_CR11","doi-asserted-by":"publisher","unstructured":"Povey, D., et al.: Semi-orthogonal low-rank matrix factorization for deep neural networks. In: Interspeech 2018, pp. 3743\u20133747 (2018). https:\/\/doi.org\/10.21437\/Interspeech.2018-1417","DOI":"10.21437\/Interspeech.2018-1417"},{"key":"50_CR12","unstructured":"Povey, D., et al.: The Kaldi speech recognition toolkit. In: IEEE 2011 Workshop on Automatic Speech Recognition and Understanding 01 (2011)"},{"key":"50_CR13","doi-asserted-by":"publisher","unstructured":"Povey, D., et al.: Purely sequence-trained neural networks for ASR based on lattice-free MMI. In: Interspeech 2016, pp. 2751\u20132755 (2016). https:\/\/doi.org\/10.21437\/Interspeech.2016-595","DOI":"10.21437\/Interspeech.2016-595"},{"key":"50_CR14","unstructured":"Psutka, J., Hoidekr, J., Ircing, P., Psutka, J.V.: Recognition of spontaneous speech - some problems and their solutions. In: CITSA 2006, pp. 169\u2013172. IIIS (2006)"},{"key":"50_CR15","doi-asserted-by":"crossref","unstructured":"Psutka, J., Ircing, P., Psutka, J.V., Haji\u010d, J., Byrne, W., M\u00edrovsk\u00fd, J.: Automatic transcription of Czech, Russian and Slovak spontaneous speech in the MALACH project. In: Eurospeech 2005, pp. 1349\u20131352. ISCA (2005)","DOI":"10.21437\/Interspeech.2005-489"},{"key":"50_CR16","doi-asserted-by":"crossref","unstructured":"Psutka, J., et al.: Large vocabulary ASR for spontaneous Czech in the MALACH project. In: Eurospeech 2003, pp. 1821\u20131824. ISCA (2003)","DOI":"10.21437\/Eurospeech.2003-551"},{"key":"50_CR17","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1007\/978-3-642-15760-8_49","volume-title":"Text, Speech and Dialogue","author":"J Psutka","year":"2010","unstructured":"Psutka, J., \u0160vec, J., Psutka, J.V., Van\u011bk, J., Pra\u017e\u00e1k, A., \u0160m\u00eddl, L.: Fast Phonetic\/Lexical searching in\u00a0the archives of the Czech holocaust testimonies: advancing towards the MALACH project visions. In: Sojka, P., Hor\u00e1k, A., Kope\u010dek, I., Pala, K. (eds.) TSD 2010. LNCS (LNAI), vol. 6231, pp. 385\u2013391. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15760-8_49"},{"issue":"1","key":"50_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1687-4722-2011-10","volume":"2011","author":"J Psutka","year":"2011","unstructured":"Psutka, J., et al.: System for fast lexical and phonetic spoken term detection in a Czech cultural heritage archive. EURASIP J. Audio Speech Music Process. 2011(1), 1\u201310 (2011). https:\/\/doi.org\/10.1186\/1687-4722-2011-10","journal-title":"EURASIP J. Audio Speech Music Process."},{"key":"50_CR19","unstructured":"Psutka, J.V., et al.: USC-SFI MALACH interviews and transcripts Czech (2014). https:\/\/catalog.ldc.upenn.edu\/LDC2014S04"},{"key":"50_CR20","doi-asserted-by":"publisher","unstructured":"Ramabhadran, B., Huang, J., Picheny, M.: Towards automatic transcription of large spoken archives - English ASR for the MALACH project. In: ICASSP 2003, p. I (2003). https:\/\/doi.org\/10.1109\/ICASSP.2003.1198756","DOI":"10.1109\/ICASSP.2003.1198756"},{"key":"50_CR21","unstructured":"Ramabhadran, B., et al.: USC-SFI MALACH interviews and transcripts English (2012). https:\/\/catalog.ldc.upenn.edu\/LDC2012S05"},{"key":"50_CR22","unstructured":"Stanislav, P., \u0160vec, J., Ircing, P.: An engine for online video search in large archives of the holocaust testimonies. In: Interspeech 2016, pp. 2352\u20132353 (2016)"},{"key":"50_CR23","doi-asserted-by":"publisher","unstructured":"\u0160vec, J., Psutka, J., Trmal, J., \u0160m\u00eddl, L., Ircing, P., Sedmidubsk\u00fd, J.: On the use of grapheme models for searching in large spoken archives. In: ICASSP 2018, pp. 6259\u20136263 (2018). https:\/\/doi.org\/10.1109\/ICASSP.2018.8461774","DOI":"10.1109\/ICASSP.2018.8461774"},{"issue":"6","key":"50_CR24","doi-asserted-by":"publisher","first-page":"1818","DOI":"10.1109\/TASL.2012.2190928","volume":"20","author":"J Van\u011bk","year":"2012","unstructured":"Van\u011bk, J., Trmal, J., Psutka, J.V., Psutka, J.: Optimized acoustic likelihoods computation for NVIDIA and ATI\/AMD graphics processors. IEEE Trans. Audio Speech Lang. Process. 20(6), 1818\u20131828 (2012). https:\/\/doi.org\/10.1109\/TASL.2012.2190928","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"50_CR25","doi-asserted-by":"crossref","unstructured":"Vesel\u00fd, K., Ghoshal, A., Burget, L., Povey, D.: Sequence-discriminative training of deep neural networks. In: Interspeech 2013, pp. 2345\u20132349 (2013)","DOI":"10.21437\/Interspeech.2013-548"},{"issue":"3","key":"50_CR26","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1109\/29.21701","volume":"37","author":"A Waibel","year":"1989","unstructured":"Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., Lang, K.J.: Phoneme recognition using time-delay neural networks. IEEE Trans. Acoust. Speech Signal Process. 37(3), 328\u2013339 (1989). https:\/\/doi.org\/10.1109\/29.21701","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"50_CR27","doi-asserted-by":"publisher","unstructured":"Wang, D., Wang, X., LV, S.: An overview of end-to-end automatic speech recognition. Symmetry 11(8) (2019). https:\/\/doi.org\/10.3390\/sym11081018","DOI":"10.3390\/sym11081018"},{"key":"50_CR28","unstructured":"Young, S.: The HTK hidden Markov model toolkit: design and philosophy, vol. 2, pp. 2\u201344. Entropic Cambridge Research Laboratory, Ltd. (1994)"},{"key":"50_CR29","doi-asserted-by":"publisher","unstructured":"Zhang, X., Trmal, J., Povey, D., Khudanpur, S.: Improving deep neural network acoustic models using generalized maxout networks. In: ICASSP 2014, pp. 215\u2013219 (2014). https:\/\/doi.org\/10.1109\/ICASSP.2014.6853589","DOI":"10.1109\/ICASSP.2014.6853589"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-87802-3_50","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T22:01:11Z","timestamp":1673301671000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87802-3_50"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030878016","9783030878023"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87802-3_50","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"22 September 2021","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":"St Petersburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/specom.nw.ru\/2021\/","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":"163","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":"74","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":"45% - 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":"3.5","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":"5.5","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held online due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}