{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T20:14:08Z","timestamp":1761596048873,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031216886"},{"type":"electronic","value":"9783031216893"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-21689-3_13","type":"book-chapter","created":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T10:03:56Z","timestamp":1668765836000},"page":"169-180","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Probabilistically-Oriented Analysis of\u00a0the\u00a0Performance of\u00a0ASR Systems for\u00a0Brazilian Radios and\u00a0TVs"],"prefix":"10.1007","author":[{"given":"Diego Marques","family":"de Azevedo","sequence":"first","affiliation":[]},{"given":"Guilherme Souza","family":"Rodrigues","sequence":"additional","affiliation":[]},{"given":"Marcelo","family":"Ladeira","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,19]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Alencar, V., Alcaim, A.: LSF and LPC-derived features for large vocabulary distributed continuous speech recognition in Brazilian Portuguese. In: 2008 42nd Asilomar Conference on Signals, Systems and Computers, pp. 1237\u20131241. IEEE (2008)","DOI":"10.1109\/ACSSC.2008.5074614"},{"key":"13_CR2","unstructured":"Amodei, D., et al.: Deep speech 2: end-to-end speech recognition in English and mandarin. In: International Conference on Machine Learning, pp. 173\u2013182. PMLR (2016)"},{"key":"13_CR3","first-page":"12449","volume":"33","author":"A Baevski","year":"2020","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. Adv. Neural. Inf. Process. Syst. 33, 12449\u201312460 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"1","key":"13_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13634-022-00844-9","volume":"2022","author":"C Batista","year":"2022","unstructured":"Batista, C., Dias, A.L., Neto, N.: Free resources for forced phonetic alignment in Brazilian Portuguese based on Kaldi toolkit. EURASIP J. Adv. Signal Process. 2022(1), 1\u201332 (2022)","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Batista, C.T., Dias, A.L., Neto, N.C.S.: Baseline acoustic models for Brazilian Portuguese using Kaldi tools. In: IberSPEECH, pp. 77\u201381 (2018)","DOI":"10.21437\/IberSPEECH.2018-17"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Chan, W., Jaitly, N., Le, Q., Vinyals, O.: Listen, attend and spell: a neural network for large vocabulary conversational speech recognition. In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4960\u20134964. IEEE (2016)","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Chiu, C.C., et al.: State-of-the-art speech recognition with sequence-to-sequence models. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4774\u20134778. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"13_CR8","doi-asserted-by":"publisher","unstructured":"Conneau, A., et al.: Unsupervised cross-lingual representation learning at scale. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 8440\u20138451. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.747, https:\/\/aclanthology.org\/2020.acl-main.747","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Georgescu, A.L., Cucu, H., Burileanu, C.: Kaldi-based DNN architectures for speech recognition in Romanian. In: 2019 International Conference on Speech Technology and Human-Computer Dialogue (SpeD), pp. 1\u20136. IEEE (2019)","DOI":"10.1109\/SPED.2019.8906555"},{"key":"13_CR10","unstructured":"Junior, A.C., et al.: CORAA: a large corpus of spontaneous and prepared speech manually validated for speech recognition in Brazilian Portuguese (2021)"},{"key":"13_CR11","volume-title":"Speech and Language Processing: An Introduction to Speech Recognition, Computational Linguistics and Natural Language Processing","author":"D Jurafsky","year":"2008","unstructured":"Jurafsky, D., Martin, J.H.: Speech and Language Processing: An Introduction to Speech Recognition, Computational Linguistics and Natural Language Processing. Prentice Hall, Upper Saddle River, NJ (2008)"},{"issue":"4","key":"13_CR12","first-page":"393","volume":"9","author":"S Karpagavalli","year":"2016","unstructured":"Karpagavalli, S., Chandra, E.: A review on automatic speech recognition architecture and approaches. Int. J. Signal Process. Image Process. Pattern Recogn. 9(4), 393\u2013404 (2016)","journal-title":"Int. J. Signal Process. Image Process. Pattern Recogn."},{"key":"13_CR13","unstructured":"Leviathan, Y., Matias, Y.: Google duplex: an AI system for accomplishing real-world tasks over the phone (2018)"},{"key":"13_CR14","doi-asserted-by":"crossref","unstructured":"de Lima, T.A., Da Costa-Abreu, M.: A survey on automatic speech recognition systems for Portuguese language and its variations. Comput. Speech Lang. 62, 101055 (2020)","DOI":"10.1016\/j.csl.2019.101055"},{"key":"13_CR15","unstructured":"Meinedo, H., Abad, A., Pellegrini, T., Trancoso, I., Neto, J.: The l2f broadcast news speech recognition system. Proc. Fala, 93\u201396 (2010)"},{"key":"13_CR16","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/3-540-45011-4_2","volume-title":"Computational Processing of the Portuguese Language","author":"H Meinedo","year":"2003","unstructured":"Meinedo, H., Caseiro, D., Neto, J., Trancoso, I.: AUDIMUS.MEDIA: a broadcast news speech recognition system for the European Portuguese language. In: Mamede, N.J., Trancoso, I., Baptista, J., das Gra\u00e7as Volpe Nunes, M. (eds.) PROPOR 2003. LNCS (LNAI), vol. 2721, pp. 9\u201317. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/3-540-45011-4_2"},{"key":"13_CR17","unstructured":"Meinedo, H., Souto, N., Neto, J.P.: Speech recognition of broadcast news for the European Portuguese language. In: IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU 2001, pp. 319\u2013322. IEEE (2001)"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Neto, J., Meinedo, H., Viveiros, M.: A media monitoring solution. In: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1813\u20131816. IEEE (2011)","DOI":"10.1109\/ICASSP.2011.5946856"},{"key":"13_CR19","unstructured":"Patry, N.: Making automatic speech recognition work on large files with wav2vec2 in transformers (2022). https:\/\/huggingface.co\/blog\/asr-chunking"},{"key":"13_CR20","unstructured":"Povey, D., et al.: The Kaldi speech recognition toolkit. In: IEEE 2011 Workshop on Automatic Speech Recognition and Understanding. No. CONF, IEEE Signal Processing Society (2011)"},{"key":"13_CR21","doi-asserted-by":"publisher","unstructured":"Pratap, V., Xu, Q., Sriram, A., Synnaeve, G., Collobert, R.: MLS: a large-scale multilingual dataset for speech research. In: Interspeech 2020, 21st Annual Conference of the International Speech Communication Association, Virtual Event, Shanghai, China, 25\u201329 October 2020, pp. 2757\u20132761. ISCA (2020). https:\/\/doi.org\/10.21437\/Interspeech. 2020\u20132826","DOI":"10.21437\/Interspeech"},{"issue":"1","key":"13_CR22","first-page":"230","volume":"35","author":"IM Quintanilha","year":"2020","unstructured":"Quintanilha, I.M., Netto, S.L., Biscainho, L.W.P.: An open-source end-to-end ASR system for Brazilian Portuguese using DNNs built from newly assembled corpora. J. Commun. Inf. Syst. 35(1), 230\u2013242 (2020)","journal-title":"J. Commun. Inf. Syst."},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. Readings Speech Recogn. 267\u2013296 (1990)","DOI":"10.1016\/B978-0-08-051584-7.50027-9"},{"key":"13_CR24","doi-asserted-by":"publisher","unstructured":"Salesky, E., et al.: The multilingual TEDX corpus for speech recognition and translation. In: Interspeech 2021, 22nd Annual Conference of the International Speech Communication Association, Brno, Czechia, 30 August - 3 September 2021, pp. 3655\u20133659. ISCA (2021). https:\/\/doi.org\/10.21437\/Interspeech. 2021\u201311","DOI":"10.21437\/Interspeech"},{"key":"13_CR25","doi-asserted-by":"crossref","unstructured":"Sampaio, M.X., et al.: Evaluation of automatic speech recognition systems. In: Anais do XXXVI Simp\u00f3sio Brasileiro de Bancos de Dados, pp. 301\u2013306. SBC (2021)","DOI":"10.5753\/sbbd.2021.17889"},{"key":"13_CR26","unstructured":"Schramm, M., Freitas, L., Zanuz, A., Barone, D.: CSLU: spoltech Brazilian Portuguese version 1.0 ldc2006s16 (2006)"},{"key":"13_CR27","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1007\/978-3-030-98305-5_31","volume-title":"Computational Processing of the Portuguese Language","author":"LR Stefanel Gris","year":"2022","unstructured":"Stefanel Gris, L.R., Casanova, E., de Oliveira, F.S., da Silva Soares, A., Candido Junior, A.: Brazilian Portuguese speech recognition using Wav2vec 2.0. In: Pinheiro, V., et al. (eds.) PROPOR 2022. LNCS (LNAI), vol. 13208, pp. 333\u2013343. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-98305-5_31"},{"key":"13_CR28","unstructured":"Vase, S.: The maturing of automatic speech recognition in healthcare practices. Proceedings (2021). http:\/\/ceur-ws.org. ISSN 1613, 0073"},{"issue":"12","key":"13_CR29","doi-asserted-by":"publisher","first-page":"2410","DOI":"10.1109\/TASLP.2017.2756440","volume":"25","author":"W Xiong","year":"2017","unstructured":"Xiong, W., et al.: Toward human parity in conversational speech recognition. IEEE\/ACM Trans. Audio Speech Lang. Process. 25(12), 2410\u20132423 (2017)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Xiong, W., Wu, L., Alleva, F., Droppo, J., Huang, X., Stolcke, A.: The Microsoft 2017 conversational speech recognition system. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5934\u20135938. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461870"},{"key":"13_CR31","series-title":"Signals and Communication Technology","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-5779-3","volume-title":"Automatic Speech Recognition","author":"D Yu","year":"2015","unstructured":"Yu, D., Deng, L.: Automatic Speech Recognition. SCT, Springer, London (2015). https:\/\/doi.org\/10.1007\/978-1-4471-5779-3"}],"container-title":["Lecture Notes in Computer Science","Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-21689-3_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T00:12:41Z","timestamp":1668989561000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-21689-3_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031216886","9783031216893"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-21689-3_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"19 November 2022","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":"Campinas","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bracis2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www2.sbc.org.br\/bracis2022\/","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":"225","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":"89","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":"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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}