{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:14:59Z","timestamp":1775067299913,"version":"3.50.1"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030613761","type":"print"},{"value":"9783030613778","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","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":[[2020]]},"DOI":"10.1007\/978-3-030-61377-8_44","type":"book-chapter","created":{"date-parts":[[2020,10,15]],"date-time":"2020-10-15T19:04:06Z","timestamp":1602788646000},"page":"621-635","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Towards a Free, Forced Phonetic Aligner for Brazilian Portuguese Using Kaldi Tools"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2470-6345","authenticated-orcid":false,"given":"Ana Larissa","family":"Dias","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6799-6058","authenticated-orcid":false,"given":"Cassio","family":"Batista","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3259-3739","authenticated-orcid":false,"given":"Daniel","family":"Santana","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0408-4187","authenticated-orcid":false,"given":"Nelson","family":"Neto","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,10,13]]},"reference":[{"key":"44_CR1","doi-asserted-by":"crossref","unstructured":"Anastasakos, T., McDonough, J., Makhoul, J.: Speaker adaptive training: a maximum likelihood approach to speaker normalization. In: 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 2, pp. 1043\u20131046 (1997)","DOI":"10.1109\/ICASSP.1997.596119"},{"key":"44_CR2","doi-asserted-by":"crossref","unstructured":"Anastasakos, T., Mcdonough, J., Schwartz, R., Makhoul, J.: A compact model for speaker-adaptive training. In: Proceedings of the ICSLP, pp. 1137\u20131140 (1996)","DOI":"10.21437\/ICSLP.1996-253"},{"key":"44_CR3","doi-asserted-by":"publisher","unstructured":"Batista, C., Cunha, R., Batista, P., Klautau, A., Neto, N.: Utterance copy in formant-based speech synthesizers using LSTM neural networks. In: 2019 8th Brazilian Conference on Intelligent Systems (BRACIS), pp. 90\u201395, October 2019. https:\/\/doi.org\/10.1109\/BRACIS.2019.00025","DOI":"10.1109\/BRACIS.2019.00025"},{"key":"44_CR4","doi-asserted-by":"publisher","unstructured":"Batista, C., Dias, A.L., Sampaio Neto, N.: Baseline acoustic models for Brazilian Portuguese using Kaldi tools. In: Proceedings of IberSPEECH, pp. 77\u201381 (2018). https:\/\/doi.org\/10.21437\/IberSPEECH.2018-17","DOI":"10.21437\/IberSPEECH.2018-17"},{"key":"44_CR5","doi-asserted-by":"crossref","unstructured":"Bigi, B., Hirst, D.: Speech phonetization alignment and syllabification (SPPAS): a tool for the automatic analysis of speech prosody. In: Proceedings of Speech Prosody, pp. 1\u20134, May 2012. https:\/\/www.isca-speech.org\/archive\/sp2012\/papers\/sp12_019.pdf","DOI":"10.21437\/SpeechProsody.2012-8"},{"key":"44_CR6","unstructured":"Boersma, P., Weenink, D.: Praat: doing phonetics by computer (version 6.1.15) [computer program] (2020). https:\/\/www.fon.hum.uva.nl\/praat\/"},{"key":"44_CR7","doi-asserted-by":"publisher","unstructured":"Brognaux, S., Roekhaut, S., Drugman, T., Beaufort, R.: Train&align: a new online tool for automatic phonetic alignment. In: IEEE Workshop on Spoken Language Technology, pp. 416\u2013421 (2012). https:\/\/doi.org\/10.1109\/SLT.2012.6424260","DOI":"10.1109\/SLT.2012.6424260"},{"issue":"4","key":"44_CR8","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"S Davis","year":"1980","unstructured":"Davis, S., Mermelstein, P.: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust. Speech Signal Process. 28(4), 357\u2013366 (1980). https:\/\/doi.org\/10.1109\/TASSP.1980.1163420","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"44_CR9","volume-title":"Pattern Classification","author":"RO Duda","year":"2000","unstructured":"Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, 2nd edn. Wiley Interscience, Hoboken (2000)","edition":"2"},{"issue":"2","key":"44_CR10","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1006\/csla.1998.0043","volume":"12","author":"MJF Gales","year":"1998","unstructured":"Gales, M.J.F.: Maximum likelihood linear transformations for hmm-based speech recognition. Comput. Speech Lang. 12(2), 75\u201398 (1998). https:\/\/doi.org\/10.1006\/csla.1998.0043","journal-title":"Comput. Speech Lang."},{"key":"44_CR11","unstructured":"GitHub: Kaldi speech recognition toolkit (2018). https:\/\/github.com\/kaldi-asr\/kaldi"},{"key":"44_CR12","unstructured":"GitHub: Frequencywords (2020). https:\/\/github.com\/hermitdave\/FrequencyWords"},{"key":"44_CR13","unstructured":"GitHub: GNU Aspell (2020). https:\/\/github.com\/GNUAspell\/aspell"},{"key":"44_CR14","unstructured":"Goldman, J.P.: EasyAlign: an automatic phonetic alignment tool under Praat. In: Proceedings of Interspeech, pp. 3233\u20133236 (2011). https:\/\/archive-ouverte.unige.ch\/unige:18188"},{"key":"44_CR15","doi-asserted-by":"publisher","unstructured":"Gopinath, R.A.: Maximum likelihood modeling with Gaussian distributions for classification. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, vol. 2, pp. 661\u2013664, May 1998. https:\/\/doi.org\/10.1109\/ICASSP.1998.675351","DOI":"10.1109\/ICASSP.1998.675351"},{"issue":"3","key":"44_CR16","first-page":"192","volume":"39","author":"K Gorman","year":"2011","unstructured":"Gorman, K., Howell, J., Wagner, M.: Prosodylab-aligner: a tool for forced alignment of laboratory speech. Can. Acoust. 39(3), 192\u2013193 (2011). https:\/\/jcaa.caa-aca.ca\/index.php\/jcaa\/article\/view\/2476","journal-title":"Can. Acoust."},{"key":"44_CR17","unstructured":"Grupo FalaBrasil: Ferramentas para alinhamento fon\u00e9tico em portugu\u00eas brasileiro (2020). https:\/\/gitlab.com\/fb-align\/"},{"key":"44_CR18","unstructured":"Grupo FalaBrasil: NLP: Gerador de ferramentas para processamento de linguagem natural (2020). https:\/\/gitlab.com\/fb-nlp\/nlp-generator"},{"key":"44_CR19","unstructured":"Grupo FalaBrasil: Recursos prontos para processamento de linguagem natural em portugu\u00eas brasileiro (2020). https:\/\/gitlab.com\/fb-nlp\/nlp-resources"},{"key":"44_CR20","unstructured":"Guiroy, S., Cordoba, R., Villegas, A.: Application of the Kaldi toolkit for continuous speech recognition using hidden-Markov models and deep neural networks. In: Proceedings of IberSPEECH 2016, pp. 187\u2013196 (2016). https:\/\/iberspeech2016.inesc-id.pt\/wp-content\/uploads\/2017\/01\/OnlineProceedings_IberSPEECH2016.pdf"},{"key":"44_CR21","volume-title":"Spoken Language Processing: A Guide to Theory, Algorithm, and System Development","author":"X Huang","year":"2001","unstructured":"Huang, X., Acero, A., Hon, H.W.: Spoken Language Processing: A Guide to Theory, Algorithm, and System Development, 1st edn. Prentice Hall PTR, Upper Saddle River (2001)","edition":"1"},{"key":"#cr-split#-44_CR22.1","unstructured":"Jiampojamarn, S., Kondrak, G., Sherif, T.: Applying many-to-many alignments and hidden Markov models to letter-to-phoneme conversion. In: Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics"},{"key":"#cr-split#-44_CR22.2","unstructured":"Proceedings of the Main Conference, Rochester, New York, pp. 372-379. Association for Computational Linguistics, April 2007. http:\/\/www.aclweb.org\/anthology\/N\/N07\/N07-1047"},{"key":"44_CR23","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1007\/978-3-319-43958-7_29","volume-title":"Speech and Computer","author":"I Kipyatkova","year":"2016","unstructured":"Kipyatkova, I., Karpov, A.: DNN-based acoustic modeling for Russian speech recognition using Kaldi. In: Ronzhin, A., Potapova, R., N\u00e9meth, G. (eds.) SPECOM 2016. LNCS (LNAI), vol. 9811, pp. 246\u2013253. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-43958-7_29"},{"key":"44_CR24","unstructured":"LDC: CSLU: Spoltech Brazilian Portuguese version 1.0 (2018). https:\/\/catalog.ldc.upenn.edu\/LDC2006S16"},{"key":"44_CR25","unstructured":"LDC: West point Brazilian Portuguese speech (2018). https:\/\/catalog.ldc.upenn.edu\/LDC2008S04"},{"key":"44_CR26","doi-asserted-by":"publisher","unstructured":"McAuliffe, M., Socolof, M., Mihuc, S., Wagner, M., Sonderegger, M.: Montreal forced aligner: trainable text-speech alignment using Kaldi. In: Proceedings of Interspeech, pp. 498\u2013502, August 2017. https:\/\/doi.org\/10.21437\/Interspeech.2017-1386","DOI":"10.21437\/Interspeech.2017-1386"},{"issue":"11","key":"44_CR27","doi-asserted-by":"publisher","first-page":"1938","DOI":"10.1109\/TASLP.2015.2457612","volume":"23","author":"Y Miao","year":"2015","unstructured":"Miao, Y., Zhang, H., Metze, F.: Speaker adaptive training of deep neural network acoustic models using I-vectors. IEEE\/ACM Trans. Audio Speech Lang. Process. 23(11), 1938\u20131949 (2015)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"issue":"1","key":"44_CR28","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/s13173-010-0023-1","volume":"17","author":"N Neto","year":"2010","unstructured":"Neto, N., Patrick, C., Klautau, A., Trancoso, I.: Free tools and resources for Brazilian Portuguese speech recognition. J. Braz. Comput. Soc. 17(1), 53\u201368 (2010). https:\/\/doi.org\/10.1007\/s13173-010-0023-1","journal-title":"J. Braz. Comput. Soc."},{"key":"44_CR29","unstructured":"Ochshorn, R.M., Hawkins, M.: Gentle forced aligner [computer program] (2020). https:\/\/github.com\/lowerquality\/gentle"},{"key":"44_CR30","unstructured":"opensubtitles.org: Opensubtitles (2020). https:\/\/www.opensubtitles.org\/"},{"key":"44_CR31","unstructured":"PCD Legal: PCD legal: Acess\u00edvel para todos (2018). http:\/\/www.pcdlegal.com.br\/"},{"key":"44_CR32","unstructured":"Povey, D.: Chain models (2020). https:\/\/kaldi-asr.org\/doc\/chain.html"},{"key":"44_CR33","unstructured":"Povey, D.: Kaldi documentations (2020). https:\/\/kaldi-asr.org\/doc\/index.html"},{"key":"44_CR34","unstructured":"Povey, D., et al.: The Kaldi speech recognition toolkit. In: IEEE 2011 Workshop (2011)"},{"key":"44_CR35","unstructured":"PUC-Rio: Centro de estudos em telecomunica\u00e7\u00f5es (CETUC) (2018). http:\/\/www.cetuc.puc-rio.br\/"},{"key":"44_CR36","unstructured":"Siravenha, A., Neto, N., Macedo, V., Klautau, A.: Uso de regras fonol\u00f3gicas com determina\u00e7\u00e3o de vogal t\u00f4nica para convers\u00e3o grafema-fone em Portugu\u00eas Brasileiro. In: 7th International Information and Telecommunication Technologies Symposium (2008)"},{"key":"44_CR37","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1007\/978-3-319-41552-9_38","volume-title":"Computational Processing of the Portuguese Language","author":"G Souza","year":"2016","unstructured":"Souza, G., Neto, N.: An automatic phonetic aligner for Brazilian Portuguese with a Praat interface. In: Silva, J., Ribeiro, R., Quaresma, P., Adami, A., Branco, A. (eds.) PROPOR 2016. LNCS (LNAI), vol. 9727, pp. 374\u2013384. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-41552-9_38"},{"issue":"2","key":"44_CR38","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1109\/TIT.1967.1054010","volume":"13","author":"A Viterbi","year":"1967","unstructured":"Viterbi, A.: Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. IEEE Trans. Inf. Theory 13(2), 260\u2013269 (1967). https:\/\/doi.org\/10.1109\/TIT.1967.1054010","journal-title":"IEEE Trans. Inf. Theory"},{"key":"44_CR39","unstructured":"Young, S., Ollason, D., Valtchev, V., Woodland, P.: The HTK Book. Cambridge University Engineering Department, Version 3.4 (2006)"},{"issue":"5","key":"44_CR40","doi-asserted-by":"publisher","first-page":"3878","DOI":"10.1121\/1.2935783","volume":"123","author":"J Yuan","year":"2008","unstructured":"Yuan, J., Liberman, M.: Speaker identification on the SCOTUS corpus. J. Acoust. Soc. Am. 123(5), 3878\u20133881 (2008). https:\/\/doi.org\/10.1121\/1.2935783","journal-title":"J. Acoust. Soc. Am."}],"container-title":["Lecture Notes in Computer Science","Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-61377-8_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T23:45:26Z","timestamp":1723765526000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-61377-8_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030613761","9783030613778"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-61377-8_44","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"13 October 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BRACIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazilian Conference on Intelligent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Rio Grande","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazil","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2020","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":"bracis2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www2.sbc.org.br\/bracis2020\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"JEMS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"228","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":"91","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":"40% - 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":"3,5","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":"Due to the Corona pandemic BRACIS 2020 was held as a virtual event.","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)"}}]}}