{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:28:00Z","timestamp":1776889680765,"version":"3.51.2"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031483110","type":"print"},{"value":"9783031483127","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\/978-3-031-48312-7_26","type":"book-chapter","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T20:03:21Z","timestamp":1700597001000},"page":"322-334","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A Comparison of\u00a0Learned Representations with\u00a0Jointly Optimized VAE and\u00a0DNN for\u00a0Syllable Stress Detection"],"prefix":"10.1007","author":[{"given":"Jhansi","family":"Mallela","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prasanth Sai","family":"Boyina","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chiranjeevi","family":"Yarra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,22]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Aoyama, K., Guion, S.G.: Prosody in second language acquisition. Language Experience in Second Language Speech Learning: in honor of James Emil Flege. Amsterdam (2007)","DOI":"10.1075\/lllt.17.24aoy"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Arnold, D., Wagner, P., Baayen, R.H.: Using generalized additive models and random forests to model prosodic prominence in German. In: INTERSPEECH, Lyon, France, pp. 272\u2013276. International Speech Communications Association (2017)","DOI":"10.21437\/Interspeech.2013-82"},{"key":"26_CR3","doi-asserted-by":"publisher","unstructured":"Bernhard, V., Schwab, S., Goldman, J.P.: Acoustic Stress Detection in Isolated English Words for Computer-Assisted Pronunciation Training. In: Proceedings of Interspeech 2022, pp. 3143\u20133147 (2022). https:\/\/doi.org\/10.21437\/Interspeech 2022\u2013197","DOI":"10.21437\/Interspeech"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Christodoulides, G., Avanzi, M.: An evaluation of machine learning methods for prominence detection in French. In: INTERSPEECH, pp. 116\u2013119 (2014)","DOI":"10.21437\/Interspeech.2014-24"},{"key":"26_CR5","unstructured":"Couper-Kuhlen, E.: An introduction to english prosody. (No Title) (1986)"},{"issue":"3","key":"26_CR6","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1016\/S0933-3657(00)00065-8","volume":"20","author":"P Cunningham","year":"2000","unstructured":"Cunningham, P., Carney, J., Jacob, S.: Stability problems with artificial neural networks and the ensemble solution. Artif. Intell. Med. 20(3), 217\u2013225 (2000)","journal-title":"Artif. Intell. Med."},{"key":"26_CR7","unstructured":"Cutler, A., Isard, S.D.: The production of prosody (1980)"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Evin, D., Cossio Mercado, C., Torres, H.M., Gurlekian, J., Mixdorff, H.: Automatic prominence detection in Argentinian Spanish, Proceedings of Speech Prosody, Poznan, Poland, pp. 680\u2013684 (2018)","DOI":"10.21437\/SpeechProsody.2018-138"},{"key":"26_CR9","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.specom.2015.02.002","volume":"69","author":"L Ferrer","year":"2015","unstructured":"Ferrer, L., Bratt, H., Richey, C., Franco, H., Abrash, V., Precoda, K.: Classification of lexical stress using spectral and prosodic features for computer-assisted language learning systems. Speech Commun. 69, 31\u201345 (2015)","journal-title":"Speech Commun."},{"issue":"4","key":"26_CR10","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1007\/s10772-015-9299-z","volume":"18","author":"DO Johnson","year":"2015","unstructured":"Johnson, D.O., Kang, O.: Automatic prominent syllable detection with machine learning classifiers. Int. J. Speech Technol. 18(4), 583\u2013592 (2015). https:\/\/doi.org\/10.1007\/s10772-015-9299-z","journal-title":"Int. J. Speech Technol."},{"key":"26_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2021.118423","volume":"241","author":"JH Kim","year":"2021","unstructured":"Kim, J.H., Zhang, Y., Han, K., Wen, Z., Choi, M., Liu, Z.: Representation learning of resting state fMRI with variational autoencoder. Neuroimage 241, 118423 (2021)","journal-title":"Neuroimage"},{"key":"26_CR12","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"26_CR13","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Lewis, C.: The Role of Lexical Stress in English as a Lingua Franca in Southeast Asia. In: Pronunciation in Second Language Learning and Teaching Proceedings, vol. 12(1) (2022)","DOI":"10.31274\/psllt.13338"},{"issue":"2","key":"26_CR15","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1017\/S0272263113000752","volume":"36","author":"A Li","year":"2014","unstructured":"Li, A., Post, B.: L2 acquisition of prosodic properties of speech rhythm: evidence from l1 mandarin and German learners of English. Stud. Second. Lang. Acquis. 36(2), 223\u2013255 (2014)","journal-title":"Stud. Second. Lang. Acquis."},{"key":"26_CR16","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.specom.2017.11.003","volume":"96","author":"K Li","year":"2018","unstructured":"Li, K., Mao, S., Li, X., Wu, Z., Meng, H.: Automatic lexical stress and pitch accent detection for L2 English speech using multi-distribution deep neural networks. Speech Commun. 96, 28\u201336 (2018)","journal-title":"Speech Commun."},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Lin, C.C., Hung, Y., Feris, R., He, L.: Video instance segmentation tracking with a modified vae architecture. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13147\u201313157 (2020)","DOI":"10.1109\/CVPR42600.2020.01316"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Lin, S., Clark, R., Birke, R., Sch\u00f6nborn, S., Trigoni, N., Roberts, S.: Anomaly detection for time series using VAE-LSTM hybrid model. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4322\u20134326. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053558"},{"key":"26_CR19","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008)"},{"key":"26_CR20","unstructured":"Menzel, W., et al.: The ISLE corpus of non-native spoken English. In: Proceedings of LREC: Language Resources and Evaluation Conference, vol. 2, pp. 957\u2013964. European Language Resources Association (2000)"},{"key":"26_CR21","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: ICML (2010)"},{"key":"26_CR22","unstructured":"Ruan, Y., et al.: An end-to-end approach for lexical stress detection based on transformer. arXiv preprint arXiv:1911.04862 (2019)"},{"issue":"6088","key":"26_CR23","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"DE Rumelhart","year":"1986","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(6088), 533\u2013536 (1986)","journal-title":"Nature"},{"issue":"1","key":"26_CR24","first-page":"127","volume":"23","author":"PH Su","year":"2014","unstructured":"Su, P.H., Wu, C.H., Lee, L.S.: A recursive dialogue game for personalized computer-aided pronunciation training. IEEE\/ACM Trans. Audio Speech Lang. Process. 23(1), 127\u2013141 (2014)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Sun, G., et al.: Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and autoregressive prosody prior. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6699\u20136703. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053436"},{"key":"26_CR26","unstructured":"Tauberer, J.: P2tk automated syllabifier (2008)"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Tepperman, J., Narayanan, S.: Automatic syllable stress detection using prosodic features for pronunciation evaluation of language learners. In: Proceedings (ICASSP) IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 1, pp. I-937. IEEE (2005)","DOI":"10.1109\/ICASSP.2005.1415269"},{"key":"26_CR28","unstructured":"Tschannen, M., Bachem, O., Lucic, M.: Recent advances in autoencoder-based representation learning. arXiv preprint arXiv:1812.05069 (2018)"},{"issue":"2","key":"26_CR29","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1121\/1.380688","volume":"58","author":"N Umeda","year":"1975","unstructured":"Umeda, N.: Vowel duration in American English. J. Acoustical Soc. Am. 58(2), 434\u2013445 (1975)","journal-title":"J. Acoustical Soc. Am."},{"key":"26_CR30","doi-asserted-by":"crossref","unstructured":"Xia, T., Rui, X., Huang, C.L., Chu, I.H., Wang, S., Han, M.: An Attention Based Deep Neural Network for Automatic Lexical Stress Detection. In: Global Conference on Signal and Information Processing (GlobalSIP), pp. 1\u20135. IEEE (2019)","DOI":"10.1109\/GlobalSIP45357.2019.8969232"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Yarra, C., Deshmukh, O.D., Ghosh, P.K.: Automatic detection of syllable stress using sonority based prominence features for pronunciation evaluation. In: International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5845\u20135849. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7953277"},{"key":"26_CR32","doi-asserted-by":"crossref","unstructured":"Yarra, C., Ramanathi, M.K., Ghosh, P.K.: Comparison of automatic syllable stress detection quality with time-aligned boundaries and context dependencies. In: SLaTE, pp. 79\u201383 (2019)","DOI":"10.21437\/SLaTE.2019-15"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-48312-7_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T14:46:56Z","timestamp":1730558816000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-48312-7_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031483110","9783031483127"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-48312-7_26","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)"}}]}}