{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:06:13Z","timestamp":1775199973306,"version":"3.50.1"},"reference-count":82,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434700","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["CAM\u00d5ES: A Comprehensive Automatic Speech Recognition Benchmark for European Portuguese"],"prefix":"10.1109","author":[{"given":"Carlos","family":"Carvalho","sequence":"first","affiliation":[{"name":"INESC-ID,Lisbon,Portugal"}]},{"given":"Francisco","family":"Teixeira","sequence":"additional","affiliation":[{"name":"INESC-ID,Lisbon,Portugal"}]},{"given":"Catarina","family":"Botelho","sequence":"additional","affiliation":[{"name":"INESC-ID,Lisbon,Portugal"}]},{"given":"Anna","family":"Pompili","sequence":"additional","affiliation":[{"name":"INESC-ID,Lisbon,Portugal"}]},{"given":"Rub\u00e9n","family":"Solera-Ure\u00f1a","sequence":"additional","affiliation":[{"name":"INESC-ID,Lisbon,Portugal"}]},{"given":"S\u00e9rgio","family":"Paulo","sequence":"additional","affiliation":[{"name":"INESC-ID,Lisbon,Portugal"}]},{"given":"Mariana","family":"Juli\u00e3o","sequence":"additional","affiliation":[{"name":"INESC-ID,Lisbon,Portugal"}]},{"given":"Thomas","family":"Rolland","sequence":"additional","affiliation":[{"name":"INESC-ID,Lisbon,Portugal"}]},{"given":"John","family":"Mendon\u00e7a","sequence":"additional","affiliation":[{"name":"INESC-ID,Lisbon,Portugal"}]},{"given":"Diogo","family":"Pereira","sequence":"additional","affiliation":[{"name":"INESC-ID,Lisbon,Portugal"}]},{"given":"Isabel","family":"Trancoso","sequence":"additional","affiliation":[{"name":"INESC-ID,Lisbon,Portugal"}]},{"given":"Alberto","family":"Abad","sequence":"additional","affiliation":[{"name":"INESC-ID,Lisbon,Portugal"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The most spoken languages worldwide in 2025","year":"2025","journal-title":"Statista"},{"key":"ref2","article-title":"Portuguese language","year":"2025","journal-title":"Ethnologue, SIL International"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198235811.001.0001"},{"key":"ref4","first-page":"4218","article-title":"Common Voice: A Massively-Multilingual Speech Corpus","volume-title":"Proc. LREC","author":"Ardila"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-022-09621-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023141"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389689"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-42448-9_5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462506"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003750"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10022656"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389701"},{"key":"ref14","article-title":"Speechstew: Simply mix all available speech recognition data to train one large neural network","author":"Chan","year":"2021","journal-title":"arXiv preprint arXiv:2104.02133"},{"key":"ref15","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/asru57964.2023.10389676"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.549"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-241"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/IberSPEECH.2021-40"},{"issue":"1","key":"ref20","first-page":"4798","article-title":"Scaling Speech Technology to 1,000+ Languages","volume":"25","author":"Pratap","year":"2024","journal-title":"The Journal of Machine Learning Research"},{"key":"ref21","article-title":"Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2303.01037"},{"key":"ref22","article-title":"Seamless: Multilingual Expressive and Streaming Speech Translation","author":"Barrault","year":"2023","journal-title":"arXiv preprint arXiv:2312.05187"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.570"},{"key":"ref24","article-title":"Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs","volume-title":"arXiv preprint arXiv:2503.01743","author":"Abouelenin","year":"2025"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1062"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1316"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref28","first-page":"5952","article-title":"WER We Stand: Benchmarking Urdu ASR Models","volume-title":"Proc. International Conference on Computational Linguistics","author":"Arif"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/O-COCOSDA64382.2024.10800399"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2443"},{"key":"ref31","first-page":"202","article-title":"Benchmarking Whisper for Low-Resource Speech Recognition: An N-Shot Evaluation on Pashto, Punjabi, and Urdu","volume-title":"Proc. First Workshop on Challenges in Processing South Asian Languages (CHiPSAL)","author":"Sehar"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1997-448"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ITS.1998.713103"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2001.1034651"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4517921"},{"key":"ref36","article-title":"Reconhecimento de fala em portugu\u00eas de Portugal num contexto com poucos recursos","author":"de S\u00e1","year":"2021"},{"key":"ref37","article-title":"Deep learning for speech to text transcription for the Portuguese language","volume-title":"master\u2019s thesis","author":"Medeiros","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/fi15050159"},{"key":"ref39","first-page":"2258","article-title":"Desenvolvimento de um Sistema de Reconhecimento Autom\u00e1tico de Voz Cont\u00ednua com Grande Vocabul\u00e1rio para o Portugu\u00eas Brasileiro","volume-title":"Proc. XXV Congresso da Sociedade Brasileira de Computa\u00e7\u00e3o","author":"Silva"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s13173-010-0023-1"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-21"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-276"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-28885-2_46"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2008.5074614"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-79029-4_3"},{"key":"ref46","first-page":"6076","article-title":"MuPe Life Stories Dataset: Spontaneous Speech in Brazilian Portuguese with a Case Study Evaluation on ASR Bias against Speakers Groups and Topic Modeling","volume-title":"Proc. 31st International Conference on Computational Linguistics","author":"Evaldo Leal"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/IberSPEECH.2018-17"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-98305-5_31"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888566"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.1997-485"},{"key":"ref51","first-page":"4012","article-title":"The DIRHA Portuguese Corpus: A Comparison of Home Automation Command Detection and Recognition in Simulated and Real Data","volume-title":"Proc. LREC","author":"Matos"},{"key":"ref52","article-title":"Automatic Methods for Building Speech Synthesis Corpora","author":"Paulo","year":"2009"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-09761-9_2"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40585-3_68"},{"key":"ref56","article-title":"The first European Portuguese elderly speech corpus","volume-title":"Proc. IberSPEECH","volume":"10","author":"H\u00e4m\u00e4l\u00e4inen"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45011-4_19"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.21437\/Eurospeech.2003-401"},{"key":"ref59","first-page":"1416","article-title":"The LECTRA corpus - classroom lecture transcriptions in European Portuguese","volume-title":"Proc. LREC","author":"Trancoso"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2279"},{"key":"ref61","article-title":"Corpus de di\u00e1logo CORAL","volume-title":"Proc. PROPOR","author":"Trancoso"},{"key":"ref62","first-page":"93","article-title":"The L2F broadcast news speech recognition system","volume-title":"Proc. FALA 2010","author":"Meinedo"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.21437\/IberSPEECH.2022-15"},{"key":"ref64","article-title":"Perfil Sociolingu\u00edstico da Fala Bracarense","year":"2009","journal-title":"Centro de Estudos Human\u00edsticos, Universidade do Minho"},{"key":"ref65","article-title":"Portugu\u00eas Fundamental","author":"Lingu\u00edstica","year":"2014"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4518588"},{"issue":"1","key":"ref67","first-page":"257","article-title":"Portugu\u00eas Falado: variedades geogr\u00e1ficas e sociais","author":"Bettencourt Gon\u00e7alves","year":"2000","journal-title":"Estudos de gram\u00e1tica portuguesa"},{"key":"ref68","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NIPS","volume":"33","author":"Baevski"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-78"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-143"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1456"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref75","article-title":"Benchmarking Rotary Position Embeddings for Automatic Speech Recognition","author":"Zhang","year":"2025","journal-title":"arXiv preprint arXiv:2501.06051"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2025-2025"},{"key":"ref77","first-page":"79","article-title":"Europarl: A Parallel Corpus for Statistical Machine Translation","volume-title":"Proc. Machine Translation Summit X: Papers","author":"Koehn"},{"key":"ref78","first-page":"923","article-title":"OpenSubtitles2016: Extracting Large Parallel Corpora from Movie and TV Subtitles","volume-title":"Proc. LREC","author":"Lison"},{"key":"ref79","first-page":"187","article-title":"KenLM: Faster and smaller language model queries","volume-title":"Proc. Sixth Workshop on Statistical Machine Translation","author":"Heafield"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890105"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-329"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.296"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434700.pdf?arnumber=11434700","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:35Z","timestamp":1775192315000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434700\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434700","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}