{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T15:52:14Z","timestamp":1783007534127,"version":"3.54.5"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030922696","type":"print"},{"value":"9783030922702","type":"electronic"}],"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\/978-3-030-92270-2_46","type":"book-chapter","created":{"date-parts":[[2021,12,6]],"date-time":"2021-12-06T11:06:00Z","timestamp":1638788760000},"page":"536-547","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Investigation of\u00a0Different G2P Schemes for\u00a0Speech Recognition in\u00a0Sanskrit"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2850-9696","authenticated-orcid":false,"given":"C. S.","family":"Anoop","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3646-1955","authenticated-orcid":false,"given":"A. G.","family":"Ramakrishnan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,12,7]]},"reference":[{"key":"46_CR1","doi-asserted-by":"publisher","unstructured":"Adiga, D., Kumar, R.A.K., Jyothi, P., Ramakrishnan, G., Goyal, P.: Automatic speech recognition in Sanskrit: a new speech corpus and modelling insights. In: 59th Annual Meeting of the Association for Computational Linguistics, ACLFindings (2021), pp. 5039\u20135050. https:\/\/doi.org\/10.18653\/v1\/2021.findings-acl.447","DOI":"10.18653\/v1\/2021.findings-acl.447"},{"key":"46_CR2","unstructured":"Anoop, C.S., Prathosh, A.P., Ramakrishnan, A.G.: Unsupervised domain adaptation schemes for building ASR in low-resource languages. In: Proceedings of Workshop on Automatic Speech Recognition and Understanding, ASRU (2021)"},{"key":"46_CR3","doi-asserted-by":"publisher","unstructured":"Anoop, C.S., Ramakrishnan, A.G.: Automatic speech recognition for Sanskrit. In: 2nd International Conference on Intelligent Computing, Instrumentation and Control Technologies, ICICICT, vol. 1, pp. 1146\u20131151 (2019). https:\/\/doi.org\/10.1109\/ICICICT46008.2019.8993283","DOI":"10.1109\/ICICICT46008.2019.8993283"},{"key":"46_CR4","doi-asserted-by":"publisher","unstructured":"Anoop, C.S., Ramakrishnan, A.G.: CTC-based end-to-end ASR for the low resource Sanskrit language with spectrogram augmentation. 27th National Conference on Communications, NCC (2021). pp. 1\u20136. https:\/\/doi.org\/10.1109\/NCC52529.2021.9530162","DOI":"10.1109\/NCC52529.2021.9530162"},{"key":"46_CR5","doi-asserted-by":"publisher","unstructured":"Arora, A., Gessler, L., Schneider, N.: Supervised grapheme-to-phoneme conversion of orthographic schwas in Hindi and Punjabi. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 7791\u20137795. Association for Computational Linguistics, July 2020. https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.696","DOI":"10.18653\/v1\/2020.acl-main.696"},{"key":"46_CR6","doi-asserted-by":"crossref","unstructured":"Bahl, L.R., Brown, P.F., de Souza, P.V., Mercer, R.L.: Maximum mutual information estimation of hidden Markov model parameters for speech recognition. In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 49\u201352 (1986)","DOI":"10.1109\/ICASSP.1986.1169179"},{"key":"46_CR7","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., Dehak, R., Dumouchel, P., Ouellet, P.: Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19, 788\u2013798 (2011)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"46_CR8","doi-asserted-by":"crossref","unstructured":"Federico, M., Bertoldi, N., Cettolo, M.: IRSTLM: an open source toolkit for handling large scale language models. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH (2008)","DOI":"10.21437\/Interspeech.2008-271"},{"issue":"3","key":"46_CR9","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1109\/89.759034","volume":"7","author":"M Gales","year":"1999","unstructured":"Gales, M.: Semi-tied covariance matrices for hidden Markov models. IEEE Trans. Speech Audio Proces. 7(3), 272\u2013281 (1999). https:\/\/doi.org\/10.1109\/89.759034","journal-title":"IEEE Trans. Speech Audio Proces."},{"key":"46_CR10","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the International Conference on Machine Learning, ICML, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"46_CR11","doi-asserted-by":"publisher","unstructured":"Hadian, H., Sameti, H., Povey, D., Khudanpur, S.: End-to-end speech recognition using lattice-free MMI. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, pp. 12\u201316 (2018). https:\/\/doi.org\/10.21437\/Interspeech","DOI":"10.21437\/Interspeech"},{"issue":"6","key":"46_CR12","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 Sig. Process. Mag. 29(6), 82\u201397 (2012). https:\/\/doi.org\/10.1109\/MSP.2012.2205597","journal-title":"IEEE Sig. Process. Mag."},{"key":"46_CR13","doi-asserted-by":"crossref","unstructured":"Hugo Van, H., Filip Van, A.: An adaptive-beam pruning technique for continuous speech recognition. In: Proceeding of Fourth International Conference on Spoken Language Processing, ICSLP, vol. 4, pp. 2083\u20132086. IEEE (1996)","DOI":"10.21437\/ICSLP.1996-528"},{"key":"46_CR14","unstructured":"Samudravijaya, K., Murthy H.A.: Indian language speech sound label set (ILSL12). In: Indian Language TTS Consortium & ASR Consortium (2012) https:\/\/www.iitm.ac.in\/donlab\/tts\/downloads\/cls\/cls_v2.1.6.pdf"},{"key":"46_CR15","doi-asserted-by":"crossref","unstructured":"Ko, T., Peddinti, V., Povey, D., Khudanpur, S.: Audio augmentation for speech recognition. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. vol. January, pp. 3586\u20133589 (2015)","DOI":"10.21437\/Interspeech.2015-711"},{"issue":"1","key":"46_CR16","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1006\/csla.2001.0184","volume":"16","author":"M Mohri","year":"2002","unstructured":"Mohri, M., Pereira, F., Riley, M.: Weighted finite-state transducers in speech recognition. Comput. Speech Lang. 16(1), 69\u201388 (2002). https:\/\/doi.org\/10.1006\/csla.2001.0184","journal-title":"Comput. Speech Lang."},{"key":"46_CR17","unstructured":"Mortensen, D., Dalmia, S., Littell, P.: Epitran: Precision G2P for many languages. In: 11th International Conference on Language Resources and Evaluation, LREC 2018. pp. 2710\u20132714 (2019)"},{"key":"46_CR18","doi-asserted-by":"crossref","unstructured":"Park, D., Chan, W., Zhang, Y., Chiu, C.C., Zoph, B., Cubuk, E., Le, Q.: Specaugment: A simple data augmentation method for automatic speech recognition. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. vol. September, pp. 2613\u20132617 (2019)","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"46_CR19","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: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. vol. 2015-January, pp. 3214\u20133218 (2015)","DOI":"10.21437\/Interspeech.2015-647"},{"issue":"2","key":"46_CR20","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1016\/j.csl.2010.06.003","volume":"25","author":"D Povey","year":"2011","unstructured":"Povey, D., et al.: The subspace Gaussian mixture model - a structured model for speech recognition. Comput. Speech Lang. 25(2), 404\u2013439 (2011). https:\/\/doi.org\/10.1016\/j.csl.2010.06.003","journal-title":"Comput. Speech Lang."},{"key":"46_CR21","doi-asserted-by":"publisher","unstructured":"Povey, D., Cheng, G., Wang, Y., Li, K., Xu, H., Yarmohamadi, M., Khudanpur, S.: Semi-orthogonal low-rank matrix factorization for deep neural networks. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, vol. 2018-September, pp. 3743\u20133747 (2018). https:\/\/doi.org\/10.21437\/Interspeech","DOI":"10.21437\/Interspeech"},{"key":"46_CR22","doi-asserted-by":"publisher","unstructured":"Povey, D., Peddinti, V., Galvez, D., Ghahremani, P., Manohar, V., Na, X., Wang, Y., Khudanpur, S.: Purely sequence-trained neural networks for ASR based on lattice-free MMI. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, pp. 2751\u20132755 (2016). https:\/\/doi.org\/10.21437\/Interspeech","DOI":"10.21437\/Interspeech"},{"key":"46_CR23","unstructured":"Povey, D., et al.: The Kaldi speech recognition toolkit. In: IEEE Workshop on Automatic Speech Recognition and Understanding, December 2011"},{"issue":"2","key":"46_CR24","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"L Rabiner","year":"1989","unstructured":"Rabiner, L.: A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 77(2), 257\u2013286 (1989). https:\/\/doi.org\/10.1109\/5.18626","journal-title":"Proc. IEEE"},{"key":"46_CR25","unstructured":"Scharf, P.M., Hyman, M.D.: Linguistic Issues in Encoding Sanskrit. The Sanskrit Library, Providence(2012)"},{"issue":"8","key":"46_CR26","doi-asserted-by":"publisher","first-page":"1240","DOI":"10.1109\/JSTSP.2017.2763455","volume":"11","author":"S Watanabe","year":"2017","unstructured":"Watanabe, S., Hori, T., Kim, S., Hershey, J., Hayashi, T.: Hybrid CTC\/attention architecture for end-to-end speech recognition. IEEE J. Select. Topics Sig. Process. 11(8), 1240\u20131253 (2017). https:\/\/doi.org\/10.1109\/JSTSP.2017.2763455","journal-title":"IEEE J. Select. Topics Sig. Process."},{"key":"46_CR27","unstructured":"Wikimedia: Wiki Sanskrit data dump. https:\/\/dumps.wikimedia.org\/sawiki\/"},{"key":"46_CR28","unstructured":"Young, S.J., Kershaw, D., Odell, J., Ollason, D., Valtchev, V., Woodland, P.: The HTK Book Version 3.4. Cambridge University Press, Cambridge (2006)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-92270-2_46","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T21:04:23Z","timestamp":1726261463000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-92270-2_46"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030922696","9783030922702"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-92270-2_46","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"7 December 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sanur, Bali","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Indonesia","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":"8 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2021.apnns.org\/","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":"1093","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":"226","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":"177","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":"21% - 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":"2.57","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":"6","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":"Due to the COVID-19 pandemic the conference was held online.","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)"}}]}}