{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T01:51:50Z","timestamp":1742953910630,"version":"3.40.3"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030895785"},{"type":"electronic","value":"9783030895792"}],"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\/978-3-030-89579-2_8","type":"book-chapter","created":{"date-parts":[[2021,10,16]],"date-time":"2021-10-16T17:08:32Z","timestamp":1634404112000},"page":"85-96","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Various DNN-HMM Architectures Used in Acoustic Modeling with Single-Speaker and Single-Channel"],"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\/0000-0002-2639-6731","authenticated-orcid":false,"given":"Jan","family":"Van\u011bk","sequence":"additional","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"}]}],"member":"297","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"issue":"10","key":"8_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)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"8_CR2","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/TASL.2011.2172153","volume":"20","author":"L Deng","year":"2012","unstructured":"Deng, L., Acero, A., Dahl, G., Yu, D.: Context-dependent pre-trained deep neural networks for large vocabulary speech recognition. IEEE Trans. Audio Speech Lang. Process. 20, 30\u201342 (2012)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: In Proceedings of the International Conference on Machine Learning, ICML 2006, pp. 369\u2013376 (2006)","key":"8_CR3","DOI":"10.1145\/1143844.1143891"},{"doi-asserted-by":"crossref","unstructured":"Han, K.J., Hahm, S., Kim, B., Kim, J., Lane, I.R.: Deep learning-based telephony speech recognition in the wild. In: Interspeech 2017, pp. 1323\u20131327 (2017)","key":"8_CR4","DOI":"10.21437\/Interspeech.2017-1695"},{"issue":"6","key":"8_CR5","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton, G., et al.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process. Mag. 29(6), 82\u201397 (2012)","journal-title":"IEEE Signal Process. Mag."},{"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)","key":"8_CR6","DOI":"10.21437\/Interspeech.2015-647"},{"doi-asserted-by":"crossref","unstructured":"Povey, D., et al.: Semi-orthogonal low-rank matrix factorization for deep neural networks. In: Interspeech 2018, pp. 3743\u20133747 (2018)","key":"8_CR7","DOI":"10.21437\/Interspeech.2018-1417"},{"unstructured":"Povey, D., et al.: The Kaldi speech recognition toolkit. IEEE 2011 Workshop on Automatic Speech Recognition and Understanding (2011)","key":"8_CR8"},{"doi-asserted-by":"crossref","unstructured":"Povey, D., et al.: Purely sequence-trained neural networks for ASR based on lattice-free MMI. In: Interspeech 2016, pp. 2751\u20132755 (2016)","key":"8_CR9","DOI":"10.21437\/Interspeech.2016-595"},{"key":"8_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"678","DOI":"10.1007\/978-3-319-23192-1_57","volume-title":"Computer Analysis of Images and Patterns","author":"JV Psutka","year":"2015","unstructured":"Psutka, J.V.: Gaussian mixture model selection using multiple random subsampling with initialization. In: Azzopardi, G., Petkov, N. (eds.) CAIP 2015. LNCS, vol. 9256, pp. 678\u2013689. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-23192-1_57"},{"key":"8_CR11","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/j.patcog.2019.01.046","volume":"91","author":"JV Psutka","year":"2019","unstructured":"Psutka, J.V., Psutka, J.: Sample size for maximum-likelihood estimates of gaussian model depending on dimensionality of pattern space. Pattern Recogn. 91, 25\u201333 (2019)","journal-title":"Pattern Recogn."},{"key":"8_CR12","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1007\/978-3-642-23538-2_45","volume-title":"Text, Speech and Dialogue","author":"J \u0160vec","year":"2011","unstructured":"\u0160vec, J., Hoidekr, J., Soutner, D., Vavru\u0161ka, J.: Web text data mining for building large scale language modelling corpus. In: Habernal, I., Matou\u0161ek, V. (eds.) TSD 2011. LNCS (LNAI), vol. 6836, pp. 356\u2013363. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-23538-2_45"},{"issue":"6","key":"8_CR13","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)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"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)","key":"8_CR14","DOI":"10.21437\/Interspeech.2013-548"},{"issue":"3","key":"8_CR15","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)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"issue":"8","key":"8_CR16","doi-asserted-by":"publisher","first-page":"1018","DOI":"10.3390\/sym11081018","volume":"11","author":"D Wang","year":"2019","unstructured":"Wang, D., Wang, X., Lv, S.: An overview of end-to-end automatic speech recognition. Symmetry 11(8), 1018 (2019)","journal-title":"Symmetry"},{"key":"8_CR17","first-page":"2","volume":"2","author":"S Young","year":"1994","unstructured":"Young, S.: The HTK hidden Markov model toolkit: design and philosophy. Entrop. Camb. Res. Lab. Ltd. 2, 2\u201344 (1994)","journal-title":"Entrop. Camb. Res. Lab. Ltd."}],"container-title":["Lecture Notes in Computer Science","Statistical Language and Speech Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-89579-2_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T08:38:50Z","timestamp":1710232730000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-89579-2_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030895785","9783030895792"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-89579-2_8","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":"17 October 2021","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":"Cardiff","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","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":"22 November 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"slsp2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/irdta.eu\/slsp2020-2021\/","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":"21","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":"9","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":"43% - 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":"2","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)"}}]}}