{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T22:14:26Z","timestamp":1767910466669,"version":"3.49.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T00:00:00Z","timestamp":1721174400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T00:00:00Z","timestamp":1721174400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100017159","name":"ISCTE \u2013 Instituto Universit\u00e1rio","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100017159","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2024,9]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The transcription of parliamentary proceedings is essential for democratic governance. Traditional methods are manual and time-consuming. This work introduces an Automatic Transcription System for the Assembly of the Republic of Portugal (STAAR) that uses an automatic speech recognition model and speaker diarization technologies. STAAR was developed after analyzing existing technologies and the Assembly\u2019s specific needs, leading to an effective solution that integrates with current processes. STAAR stands out for its efficiency in transcribing debates and adapting to parliamentary language nuances. It significantly exceeded expectations by presenting a low transcription error rate, ranging from 1.7 to 11.3%, depending on the context and speech style, reducing the time required to produce the official parliamentary debates journal, and improving overall transcription efficiency. Additionally, STAAR enabled the transcription of previously undocumented parliamentary committee meetings, enhancing the documentation of parliamentary activities. This achievement marks a significant step in modernizing parliamentary processes, increasing transparency and accessibility of political information, and positions the Portuguese Parliament at the forefront of technological innovation in parliamentary debates transcription.<\/jats:p>","DOI":"10.1007\/s10772-024-10126-4","type":"journal-article","created":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T09:01:55Z","timestamp":1721206915000},"page":"613-635","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Automatic transcription system for parliamentary debates in the context of assembly of the republic of Portugal"],"prefix":"10.1007","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0048-9892","authenticated-orcid":false,"given":"Pedro","family":"Nascimento","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6662-0806","authenticated-orcid":false,"given":"Jo\u00e3o C.","family":"Ferreira","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1075-0177","authenticated-orcid":false,"given":"Fernando","family":"Batista","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,7,17]]},"reference":[{"key":"10126_CR1","unstructured":"14:00-17:00 ISO\/IEC 15504-2. (2003). Retrieved 23 Oct 2023, from https:\/\/www.iso.org\/standard\/37458.html"},{"key":"10126_CR2","first-page":"8","volume":"307","author":"T Aluma\u00eb","year":"2018","unstructured":"Aluma\u00eb, T., Tilk, O., & Ullah, A. (2018). Advanced rich transcription system for Estonian speech. Frontiers in Artificial Intelligence and Applications, 307, 8.","journal-title":"Frontiers in Artificial Intelligence and Applications"},{"key":"10126_CR3","unstructured":"Baevski, A., Zhou, H., Mohamed, A., Auli, M. (2020). Wav2vec 2.0: A framework for self-supervised learning of speech representations. In 34th Conference on neural information processing systems (NeurIPS 2020), (Vol. 2020), Vancouver, Canada."},{"key":"10126_CR4","doi-asserted-by":"publisher","unstructured":"Bain, M., Huh, J., Han, T., & Zisserman, A. (2023). WhisperX: Time-accurate speech transcription of long-form audio. https:\/\/doi.org\/10.48550\/arXiv.2303.00747","DOI":"10.48550\/arXiv.2303.00747"},{"key":"10126_CR5","doi-asserted-by":"crossref","unstructured":"Bredin, H., Yin, R., Coria, J. M., Gelly, G., Korshunov, P., Lavechin, M., Fustes, D., Titeux, H., Bouaziz, W., & Gill, M.-P. (2019). Pyannote.Audio: Neural building blocks for speaker diarization.","DOI":"10.1109\/ICASSP40776.2020.9052974"},{"key":"10126_CR6","doi-asserted-by":"crossref","unstructured":"Campr, P., Kune\u0161ov\u00e1, M., Van\u011bk, J., \u010cech, J., Psutka, J. (2014). Audio-video speaker diarization for unsupervised speaker and face model creation. In Proceedings of the lecturer notes on computer sciences (Vol. 8655 LNAI, pp. 465\u2013472). Springer.","DOI":"10.1007\/978-3-319-10816-2_56"},{"key":"10126_CR7","unstructured":"ChatGPT. Retrieved 5 Nov 2023, from https:\/\/chat.openai.com"},{"key":"10126_CR8","unstructured":"DALL\u00b7E 3. Retrieved 5 Nov 2023, from https:\/\/openai.com\/dall-e-3"},{"key":"10126_CR9","doi-asserted-by":"publisher","first-page":"101055","DOI":"10.1016\/j.csl.2019.101055","volume":"62","author":"TA de Lima","year":"2020","unstructured":"de Lima, T. A., & Da Costa-Abreu, M. (2020). A survey on automatic speech recognition systems for Portuguese language and its variations. Computer Speech and Language, 62, 101055. https:\/\/doi.org\/10.1016\/j.csl.2019.101055","journal-title":"Computer Speech and Language"},{"key":"10126_CR10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.08137","author":"H de Vos","year":"2023","unstructured":"de Vos, H., & Verberne, S. (2023). Political corpus creation through automatic speech recognition on EU debates. https:\/\/doi.org\/10.48550\/arXiv.2304.08137","journal-title":"Political Corpus Creation through Automatic Speech Recognition on EU Debates"},{"key":"10126_CR11","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.procs.2016.04.028","volume":"81","author":"F De Wet","year":"2016","unstructured":"De Wet, F., Badenhorst, J., & Modipa, T. (2016). Developing speech resources from parliamentary data for South African English. Procedia Computer Science, 81, 45\u201352.","journal-title":"Procedia Computer Science"},{"key":"10126_CR12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805","author":"J Devlin","year":"2019","unstructured":"Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT:\u00a0Pre-training of deep bidirectional transformers for language understanding. https:\/\/doi.org\/10.48550\/arXiv.1810.04805","journal-title":"Pre-Training of Deep Bidirectional Transformers for Language Understanding"},{"key":"10126_CR13","unstructured":"Di\u00e1z-Muni\u00f3, C. V. G., Silvestre-Cerd\u00e0, J. A., Jorge, J., Gim\u00e9nez, A., Iranzo-S\u00e1nchez, J., Baquero-Arnal, P., Rosell\u00f3, N., P\u00e9rez-Gonz\u00e1lez-de-Martos, A., Civera, J., Sanchis, A. et al. (2021). Europarl-ASR: A large corpus of parliamentary debates for streaming ASR benchmarking and speech data filtering\/verbatimization. In Proceedings of the annual conference on international speech communication association (Vol. 6, pp. 4371\u20134375). International Speech Communication Association (Interspeech)"},{"key":"10126_CR14","doi-asserted-by":"crossref","unstructured":"El Emam, K. (1998, Nov). The internal consistency of the ISO\/IEC 15504 software process capability scale. In Proceedings of the proceedings fifth international software metrics symposium. Metrics (Cat. No.98TB100262) (pp. 72\u201381).","DOI":"10.1109\/METRIC.1998.731228"},{"key":"10126_CR15","unstructured":"Google Forms | Google Workspace. Retrieved 13 June 2023, from https:\/\/www.google.com\/forms\/about\/"},{"key":"10126_CR16","unstructured":"Google Colaboratory. Retrieved 19 Oct 2023, from https:\/\/colab.research.google.com\/"},{"key":"10126_CR17","unstructured":"HTK Speech Recognition Toolkit. Retrieved 29 Oct 2023, from https:\/\/htk.eng.cam.ac.uk\/"},{"key":"10126_CR18","unstructured":"Introducing Whisper. Retrieved 25 Sept 2023, from https:\/\/openai.com\/research\/whisper"},{"key":"10126_CR19","unstructured":"Kaldi: Kaldi. Retrieved 29 Oct 2023, from https:\/\/kaldi-asr.org\/doc\/index.html"},{"key":"10126_CR20","doi-asserted-by":"crossref","unstructured":"Kawahara, T. (2018, Feb) Automatic meeting transcription system for the Japanese Parliament (diet). In Proceedings of the Asia-Pacific signal on information processing association annual summit conference (APSIPA ASC), (Vol. 2018, pp. 1006\u20131010). Institute of Electrical and Electronics Engineers Inc.","DOI":"10.1109\/APSIPA.2017.8282177"},{"key":"10126_CR21","unstructured":"LIBE | Committees | European Parliament. Retrieved 5 Dec 2023, from https:\/\/www.europarl.europa.eu\/committees\/en\/libe\/home\/highlights"},{"key":"10126_CR22","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1080\/00224545.1934.9919450","volume":"5","author":"R Likert","year":"1934","unstructured":"Likert, R., Roslow, S., & Murphy, G. (1934). A simple and reliable method of scoring the thurstone attitude scales. Journal of Social Psychology, 5, 228\u2013238. https:\/\/doi.org\/10.1080\/00224545.1934.9919450","journal-title":"Journal of Social Psychology"},{"key":"10126_CR23","doi-asserted-by":"publisher","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). RoBERTa: A robustly optimized BERT pretraining approach. https:\/\/doi.org\/10.48550\/arXiv.1907.11692","DOI":"10.48550\/arXiv.1907.11692"},{"key":"10126_CR24","unstructured":"LIUM SpkDiarization. Retrieved 29 Oct 2023, from https:\/\/projets-lium.univ-lemans.fr\/spkdiarization\/"},{"key":"10126_CR25","doi-asserted-by":"publisher","first-page":"3267","DOI":"10.21437\/Interspeech.2023-1616","volume":"2023","author":"R Ma","year":"2023","unstructured":"Ma, R., Gales, M. J. F., Knill, K. M., & Qian, M. (2023). N-Best T5: Robust ASR error correction using multiple input hypotheses and constrained decoding space. INTERSPEECH, 2023, 3267\u20133271. https:\/\/doi.org\/10.21437\/Interspeech.2023-1616","journal-title":"INTERSPEECH"},{"key":"10126_CR26","doi-asserted-by":"crossref","unstructured":"Mansikkaniemi, A., Smit, P., & Kurimo, M. (2017, Aug). Automatic construction of the Finnish Parliament speech corpus. In Lacerda F., Strombergsson S., Wlodarczak M., Heldner M., Gustafson J., & House D. (Eds.), Proceedings of the annual conference on international speech communication association (Vol. 2017, pp. 3762\u20133766).  International Speech Communication Association (Interspeech).","DOI":"10.21437\/Interspeech.2017-1115"},{"key":"10126_CR27","unstructured":"Multilingualism in the European Parliament. Retrieved 5 Dec 2023, from https:\/\/www.europarl.europa.eu\/about-parliament\/en\/organisation-and-rules\/multilingualism"},{"key":"10126_CR28","doi-asserted-by":"publisher","unstructured":"OpenAI GPT-4 technical report. (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.08774","DOI":"10.48550\/arXiv.2303.08774"},{"key":"10126_CR29","doi-asserted-by":"publisher","first-page":"n71","DOI":"10.1136\/bmj.n71","volume":"372","author":"MJ Page","year":"2021","unstructured":"Page, M. J., McKenzie, J. E., Bossuyt, P. M., Boutron, I., Hoffmann, T. C., Mulrow, C. D., Shamseer, L., Tetzlaff, J. M., Akl, E. A., Brennan, S. E., et al. (2021). The PRISMA 2020 statement: An updated guideline for reporting systematic reviews. BMJ, 372, n71. https:\/\/doi.org\/10.1136\/bmj.n71","journal-title":"BMJ"},{"key":"10126_CR30","doi-asserted-by":"publisher","first-page":"45","DOI":"10.2753\/MIS0742-1222240302","volume":"24","author":"K Peffers","year":"2007","unstructured":"Peffers, K., Tuunanen, T., Rothenberger, M. A., & Chatterjee, S. (2007). A design science research methodology for information systems research. Journal of Management Information Systems, 24, 45\u201377. https:\/\/doi.org\/10.2753\/MIS0742-1222240302","journal-title":"Journal of Management Information Systems"},{"key":"10126_CR31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2212.04356","author":"A Radford","year":"2022","unstructured":"Radford, A., Kim, J. W., Xu, T., Brockman, G., McLeavey, C., & Sutskever, I. (2022). Robust speech recognition via large-scale weak supervision. https:\/\/doi.org\/10.48550\/ARXIV.2212.04356","journal-title":"Robust Speech Recognition via Large-Scale Weak Supervision"},{"key":"10126_CR32","unstructured":"Scopus\u2014Document search. Retrieved 21 May 2023, from https:\/\/www.scopus.com\/search\/form.uri?display=basic#basic"},{"key":"10126_CR33","unstructured":"The Official Home of the Python Programming Language. Website Python.Org. Retrieved 25 Sept 2023, from https:\/\/www.python.org\/"},{"key":"10126_CR34","unstructured":"Web of Science Core Collection\u2014Document search. Retrieved 21 May 2023, from https:\/\/www.webofscience.com\/wos\/woscc\/basic-search"},{"key":"10126_CR35","unstructured":"WER | calculate the word error rate with our tool. Retrieved 21 Oct 2023, from https:\/\/www.amberscript.com\/en\/wer-tool\/"},{"key":"10126_CR36","unstructured":"Whisper\/Approach.Png at Main Openai\/Whisper. Retrieved 27 Sept 2023, from https:\/\/github.com\/openai\/whisper\/blob\/main\/approach.png"},{"key":"10126_CR37","unstructured":"IEEE Xplore\u2014Document search. Retrieved 21 May 2023, from https:\/\/ieeexplore.ieee.org\/Xplore\/home.jsp"},{"key":"10126_CR38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.18223","author":"WX Zhao","year":"2023","unstructured":"Zhao, W. X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., Dong, Z., et al. (2023). A survey of large language models. https:\/\/doi.org\/10.48550\/arXiv.2303.18223","journal-title":"A Survey of Large Language Models"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-024-10126-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-024-10126-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-024-10126-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T12:10:45Z","timestamp":1726143045000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-024-10126-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,17]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["10126"],"URL":"https:\/\/doi.org\/10.1007\/s10772-024-10126-4","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,17]]},"assertion":[{"value":"1 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 July 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}