{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T18:00:39Z","timestamp":1789236039842,"version":"build-2803163510"},"reference-count":96,"publisher":"MIT Press","license":[{"start":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T00:00:00Z","timestamp":1702857600000},"content-version":"vor","delay-in-days":351,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,13]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Automatic subtitling is the task of automatically translating the speech of audiovisual content into short pieces of timed text, i.e., subtitles and their corresponding timestamps. The generated subtitles need to conform to space and time requirements, while being synchronized with the speech and segmented in a way that facilitates comprehension. Given its considerable complexity, the task has so far been addressed through a pipeline of components that separately deal with transcribing, translating, and segmenting text into subtitles, as well as predicting timestamps. In this paper, we propose the first direct speech translation model for automatic subtitling that generates subtitles in the target language along with their timestamps with a single model. Our experiments on 7 language pairs show that our approach outperforms a cascade system in the same data condition, also being competitive with production tools on both in-domain and newly released out-domain benchmarks covering new scenarios.<\/jats:p>","DOI":"10.1162\/tacl_a_00607","type":"journal-article","created":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T11:19:27Z","timestamp":1702898367000},"page":"1355-1376","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":12,"title":["Direct Speech Translation for Automatic Subtitling"],"prefix":"10.1162","volume":"11","author":[{"given":"Sara","family":"Papi","sequence":"first","affiliation":[{"name":"Fondazione Bruno Kessler, Trento, Italy. spapi@fbk.eu"},{"name":"University of Trento, Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Gaido","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler, Trento, Italy. mgaido@fbk.eu"},{"name":"University of Trento, Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alina","family":"Karakanta","sequence":"additional","affiliation":[{"name":"Leiden University Centre for Linguistics, Leiden, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mauro","family":"Cettolo","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler, Trento, Italy. cettolo@fbk.eu"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matteo","family":"Negri","sequence":"additional","affiliation":[{"name":"Fondazione Bruno Kessler, Trento, Italy. negri@fbk.eu"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Turchi","sequence":"additional","affiliation":[{"name":"Zoom Video Communications, Karlsruhe, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","published-online":{"date-parts":[[2023,11,13]]},"reference":[{"key":"2023121816191553800_bib1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11042-015-2794-z","article-title":"Automating live and batch subtitling of multimedia contents\n                        for several european languages","volume":"75","author":"\u00c1lvarez","year":"2015","journal-title":"Multimedia Tools and\n                        Applications"},{"key":"2023121816191553800_bib2","doi-asserted-by":"publisher","first-page":"98","DOI":"10.18653\/v1\/2022.iwslt-1.10","article-title":"Findings of the IWSLT 2022 evaluation\n                        campaign","volume-title":"Proceedings of the 19th International\n                        Conference on Spoken Language Translation (IWSLT 2022)","author":"Anastasopoulos","year":"2022"},{"key":"2023121816191553800_bib3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18653\/v1\/2021.iwslt-1.1","article-title":"Findings of the IWSLT 2021 evaluation\n                        campaign","volume-title":"Proceedings of the 18th International\n                        Conference on Spoken Language Translation (IWSLT 2021)","author":"Anastasopoulos","year":"2021"},{"key":"2023121816191553800_bib4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095430","article-title":"Uconv-conformer: High reduction of input\n                        sequence length for end-to-end speech recognition","author":"Andrusenko","year":"2022","journal-title":"arXiv preprint arXiv:2208.07657"},{"key":"2023121816191553800_bib5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18653\/v1\/2020.iwslt-1.1","article-title":"Findings of the IWSLT 2020 evaluation\n                        campaign","volume-title":"Proceedings of the 17th International\n                        Conference on Spoken Language Translation","author":"Ansari","year":"2020"},{"key":"2023121816191553800_bib6","first-page":"4218","article-title":"Common voice: A massively-multilingual speech\n                        corpus","volume-title":"Proceedings of the 12th Language\n                        Resources and Evaluation Conference","author":"Ardila","year":"2020"},{"key":"2023121816191553800_bib7","doi-asserted-by":"publisher","first-page":"789","DOI":"10.18653\/v1\/P18-1073","article-title":"A robust self-learning method for fully\n                        unsupervised cross-lingual mappings of word embeddings","volume-title":"Proceedings of the 56th Annual Meeting of the Association for\n                        Computational Linguistics (Volume 1: Long Papers)","author":"Artetxe","year":"2018"},{"key":"2023121816191553800_bib8","first-page":"103","article-title":"Cross-lingual sentence compression for\n                        subtitles","volume-title":"Proceedings of the 16th Annual\n                        conference of the European Association for Machine Translation","author":"Aziz","year":"2012"},{"key":"2023121816191553800_bib9","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1109\/ASRU46091.2019.9003774","article-title":"A comparative study on end-to-end speech to text\n                        translation","volume-title":"Proceedings of International\n                        Workshop on Automatic Speech Recognition and Understanding (ASRU)","author":"Bahar","year":"2019"},{"key":"2023121816191553800_bib10","doi-asserted-by":"publisher","first-page":"2873","DOI":"10.18653\/v1\/2021.acl-long.224","article-title":"Cascade versus direct speech translation:\n                        Do the differences still make a difference?","volume-title":"Proceedings of the 59th Annual Meeting of the Association for\n                        Computational Linguistics and the 11th International Joint Conference on\n                        Natural Language Processing (Volume 1: Long Papers)","author":"Bentivogli","year":"2021"},{"key":"2023121816191553800_bib11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461690","article-title":"End-to-end automatic speech translation of\n                        audiobooks","volume-title":"Proceedings of ICASSP 2018 - IEEE\n                        International Conference on Acoustics, Speech and Signal\n                    Processing","author":"B\u00e9rard","year":"2018"},{"key":"2023121816191553800_bib12","article-title":"Listen and translate: A proof of concept\n                        for end-to-end speech-to-text translation","volume-title":"NIPS\n                        Workshop on end-to-end learning for speech and audio processing","author":"B\u00e9rard","year":"2016"},{"key":"2023121816191553800_bib13","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","article-title":"Enriching word vectors with subword\n                        information","volume":"5","author":"Bojanowski","year":"2017","journal-title":"Transactions of the Association for\n                        Computational Linguistics"},{"key":"2023121816191553800_bib14","doi-asserted-by":"publisher","first-page":"12","DOI":"10.3115\/v1\/W14-3302","article-title":"Findings of the 2014 workshop on\n                        statistical machine translation","volume-title":"Proceedings of\n                        the Ninth Workshop on Statistical Machine Translation","author":"Bojar","year":"2014"},{"key":"2023121816191553800_bib15","doi-asserted-by":"publisher","first-page":"271","DOI":"10.18653\/v1\/2021.eacl-demos.32","article-title":"ELITR multilingual live subtitling: Demo\n                        and strategy","volume-title":"Proceedings of the 16th Conference\n                        of the European Chapter of the Association for Computational Linguistics:\n                        System Demonstrations","author":"Bojar","year":"2021"},{"key":"2023121816191553800_bib16","doi-asserted-by":"publisher","first-page":"4403","DOI":"10.21437\/Interspeech.2021-1762","article-title":"Toward genre adapted closed captioning","volume-title":"Proceedings of Interspeech 2021","author":"Buet","year":"2021"},{"key":"2023121816191553800_bib17","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1109\/ASRU51503.2021.9687874","article-title":"Efficient conformer: Progressive\n                        downsampling and grouped attention for automatic speech\n                        recognition","volume-title":"2021 IEEE Automatic Speech\n                        Recognition and Understanding Workshop (ASRU)","author":"Burchi","year":"2021"},{"issue":"3","key":"2023121816191553800_bib18","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1093\/deafed\/enn003","article-title":"Parameters in television captioning for\n                        deaf and hard-of-hearing adults: Effects of caption rate versus text\n                        reduction on comprehension","volume":"13","author":"Burnham","year":"2008","journal-title":"The Journal of Deaf\n                        Studies and Deaf Education"},{"issue":"4","key":"2023121816191553800_bib19","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1080\/0907676X.2013.831920","article-title":"Parallel subtitle corpora and their\n                        applications in machine translation and translatology","volume":"21","author":"Bywood","year":"2013","journal-title":"Perspectives"},{"key":"2023121816191553800_bib20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2816","article-title":"End-to-end asr with adaptive span\n                        self-attention","volume-title":"INTERSPEECH","author":"Chang","year":"2020"},{"key":"2023121816191553800_bib21","doi-asserted-by":"publisher","DOI":"10.4324\/9781315674278","volume-title":"Subtitling: Concepts and Practices","author":"Cintas","year":"2021"},{"key":"2023121816191553800_bib22","doi-asserted-by":"publisher","first-page":"8440","DOI":"10.18653\/v1\/2020.acl-main.747","article-title":"Unsupervised cross-lingual representation\n                        learning at scale","volume-title":"Proceedings of the 58th Annual\n                        Meeting of the Association for Computational Linguistics","author":"Conneau","year":"2020"},{"key":"2023121816191553800_bib23","doi-asserted-by":"publisher","first-page":"1133","DOI":"10.21437\/Interspeech.2019-3045","article-title":"Adapting transformer to end-to-end spoken\n                        language translation","volume-title":"Proceedings of Interspeech\n                        2019","author":"Di Gangi","year":"2019"},{"key":"2023121816191553800_bib24","doi-asserted-by":"publisher","first-page":"8037","DOI":"10.1109\/ICASSP43922.2022.9747158","article-title":"Duration modeling of neural tts for\n                        automatic dubbing","author":"Effendi","year":"2022","journal-title":"ICASSP 2022 - 2022 IEEE\n                        International Conference on Acoustics, Speech and Signal Processing\n                        (ICASSP)"},{"key":"2023121816191553800_bib25","first-page":"46","article-title":"Machine translation for subtitling: A large-scale\n                        evaluation","volume-title":"Proceedings of the Ninth\n                        International Conference on Language Resources and Evaluation\n                        (LREC\u201914)","author":"Etchegoyhen","year":"2014"},{"key":"2023121816191553800_bib26","doi-asserted-by":"publisher","first-page":"1481","DOI":"10.21437\/Interspeech.2020-2983","article-title":"Evaluating and optimizing prosodic\n                        alignment for automatic dubbing","volume-title":"Proceedings of\n                        Interspeech 2020","author":"Federico","year":"2020"},{"key":"2023121816191553800_bib27","doi-asserted-by":"publisher","first-page":"690","DOI":"10.18653\/v1\/2021.eacl-main.57","article-title":"CTC-based compression for direct speech\n                        translation","volume-title":"Proceedings of the 16th Conference\n                        of the European Chapter of the Association for Computational Linguistics:\n                        Main Volume","author":"Gaido","year":"2021"},{"key":"2023121816191553800_bib28","first-page":"55","article-title":"Beyond voice activity detection: Hybrid\n                        audio segmentation for direct speech translation","volume-title":"Proceedings of the 4th International Conference on Natural Language\n                        and Speech Processing (ICNLSP 2021)","author":"Gaido","year":"2021"},{"key":"2023121816191553800_bib29","doi-asserted-by":"publisher","first-page":"177","DOI":"10.18653\/v1\/2022.iwslt-1.13","article-title":"Efficient yet competitive speech\n                        translation: FBK@IWSLT2022","volume-title":"Proceedings of\n                        the 19th International Conference on Spoken Language Translation (IWSLT\n                        2022)","author":"Gaido","year":"2022"},{"issue":"2","key":"2023121816191553800_bib30","doi-asserted-by":"publisher","first-page":"137","DOI":"10.47476\/jat.v2i2.84","article-title":"Template files: The holy grail of\n                        subtitling","volume":"2","author":"Georgakopoulou","year":"2019","journal-title":"Journal of Audiovisual\n                        Translation"},{"key":"2023121816191553800_bib31","doi-asserted-by":"publisher","first-page":"219","DOI":"10.35360\/njes.32","article-title":"Subtitles and international\n                        anglification","volume":"3","author":"Gottlieb","year":"2004","journal-title":"Nordic Journal of English\n                        Studies"},{"key":"2023121816191553800_bib32","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1145\/1143844.1143891","article-title":"Connectionist temporal classification:\n                        Labelling unsegmented sequence data with recurrent neural\n                        networks","volume-title":"Proceedings of the 23rd International\n                        Conference on Machine Learning","author":"Graves","year":"2006"},{"key":"2023121816191553800_bib33","first-page":"II\u20131764","article-title":"Towards end-to-end speech recognition with\n                        recurrent neural networks","volume-title":"Proceedings of the\n                        31st International Conference on International Conference on Machine\n                        Learning - Volume 32","author":"Graves","year":"2014"},{"key":"2023121816191553800_bib34","article-title":"Seed words based data selection for\n                        language model adaptation","author":"Gretter","year":"2021","journal-title":"arXiv preprint\n                        arXiv:2107.09433"},{"key":"2023121816191553800_bib35","doi-asserted-by":"publisher","first-page":"5036","DOI":"10.21437\/Interspeech.2020-3015","article-title":"Conformer: Convolution-augmented transformer for speech\n                        recognition","volume-title":"Proceedings of Interspeech\n                        2020","author":"Gulati","year":"2020"},{"key":"2023121816191553800_bib36","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1007\/978-3-319-99579-3_21","article-title":"Ted-lium 3: Twice as much data and corpus\n                        repartition for experiments on speaker adaptation","volume-title":"Speech and Computer","author":"Hernandez","year":"2018"},{"key":"2023121816191553800_bib37","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1109\/ASRU46091.2019.9003832","article-title":"Multilingual end-to-end speech\n                        translation","volume-title":"Proceedings of the 2019 IEEE\n                        Automatic Speech Recognition and Understanding Workshop (ASRU)","author":"Inaguma","year":"2019"},{"key":"2023121816191553800_bib38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415093","article-title":"Non-autoregressive end-to-end speech\n                        translation with parallel autoregressive rescoring","author":"Inaguma","year":"2021","journal-title":"arXiv preprint arXiv:2109.04411"},{"key":"2023121816191553800_bib39","doi-asserted-by":"publisher","first-page":"8229","DOI":"10.1109\/ICASSP40776.2020.9054626","article-title":"Europarl-st: A multilingual corpus for speech translation of\n                        parliamentary debates","volume-title":"ICASSP 2020 - 2020 IEEE\n                        International Conference on Acoustics, Speech and Signal Processing\n                        (ICASSP)","author":"Iranzo-S\u00e1nchez","year":"2020"},{"key":"2023121816191553800_bib40","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.18653\/v1\/2020.findings-emnlp.147","article-title":"SimAlign: High quality word alignments\n                        without parallel training data using static and contextualized\n                        embeddings","volume-title":"Findings of the Association for\n                        Computational Linguistics: EMNLP 2020","author":"Sabet","year":"2020"},{"key":"2023121816191553800_bib41","first-page":"3069","article-title":"Evaluating subtitle segmentation for end-to-end generation\n                        systems","volume-title":"Proceedings of the 13th Language\n                        Resources and Evaluation Conference (LREC)","author":"Karakanta","year":"2022"},{"key":"2023121816191553800_bib42","doi-asserted-by":"publisher","first-page":"215","DOI":"10.18653\/v1\/2021.iwslt-1.26","article-title":"Between flexibility and consistency: Joint\n                        generation of captions and subtitles","volume-title":"Proceedings\n                        of the 18th International Conference on Spoken Language Translation (IWSLT\n                        2021)","author":"Karakanta","year":"2021"},{"key":"2023121816191553800_bib43","doi-asserted-by":"publisher","first-page":"209","DOI":"10.18653\/v1\/2020.iwslt-1.26","article-title":"Is 42 the answer to everything in\n                        subtitling-oriented speech translation?","volume-title":"Proceedings of the 17th International Conference on Spoken Language\n                        Translation","author":"Karakanta","year":"2020"},{"key":"2023121816191553800_bib44","first-page":"3727","article-title":"MuST-cinema: A speech-to-subtitles\n                        corpus","volume-title":"Proceedings of the 12th Language\n                        Resources and Evaluation Conference","author":"Karakanta","year":"2020"},{"key":"2023121816191553800_bib45","article-title":"Squeezeformer: An efficient transformer\n                        for automatic speech recognition","author":"Kim","year":"2022","journal-title":"arxiv:2206.00888"},{"key":"2023121816191553800_bib46","doi-asserted-by":"publisher","first-page":"4835","DOI":"10.1109\/ICASSP.2017.7953075","article-title":"Joint CTC-attention based end-to-end\n                        speech recognition using multi-task learning","volume-title":"Proceedings of the 2017 IEEE International Conference on Acoustics,\n                        Speech and Signal Processing (ICASSP)","author":"Kim","year":"2017"},{"key":"2023121816191553800_bib47","doi-asserted-by":"publisher","first-page":"1317","DOI":"10.18653\/v1\/D16-1139","article-title":"Sequence-level knowledge distillation","volume-title":"Proceedings of the 2016 Conference on Empirical Methods in Natural\n                        Language Processing","author":"Kim","year":"2016"},{"key":"2023121816191553800_bib48","article-title":"Adam: A method for stochastic optimization","volume-title":"3rd International Conference on Learning Representations, ICLR 2015,\n                        San Diego, CA, USA, May 7\u20139, 2015, Conference Track\n                        Proceedings","author":"Kingma","year":"2015"},{"key":"2023121816191553800_bib49","first-page":"388","article-title":"Statistical significance tests for machine\n                        translation evaluation","volume-title":"Proceedings of the 2004\n                        Conference on Empirical Methods in Natural Language Processing","author":"Koehn","year":"2004"},{"key":"2023121816191553800_bib50","first-page":"115","article-title":"MT for subtitling: User evaluation of\n                        post-editing productivity","volume-title":"Proceedings of the\n                        22nd Annual Conference of the European Association for Machine\n                        Translation","author":"Koponen","year":"2020"},{"issue":"3","key":"2023121816191553800_bib51","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1080\/0907676X.2001.9961416","article-title":"The creation of interlingual subtitles:\n                        Semiotics, equivalence and condensation","volume":"9","author":"Kruger","year":"2001","journal-title":"Perspectives"},{"key":"2023121816191553800_bib52","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1007\/978-3-030-60276-5_27","article-title":"CTC-segmentation of large corpora for\n                        german end-to-end speech recognition","volume-title":"Speech and\n                        Computer","author":"K\u00fcrzinger","year":"2020"},{"key":"2023121816191553800_bib53","article-title":"Controlling the output length of neural\n                        machine translation","volume-title":"Proceedings of the 16th\n                        International Conference on Spoken Language Translation","author":"Lakew","year":"2019"},{"key":"2023121816191553800_bib54","doi-asserted-by":"publisher","first-page":"7538","DOI":"10.1109\/ICASSP39728.2021.9414411","article-title":"Machine translation verbosity control for\n                        automatic dubbing","volume-title":"ICASSP 2021 - 2021 IEEE\n                        International Conference on Acoustics, Speech and Signal Processing\n                        (ICASSP)","author":"Lakew","year":"2021"},{"key":"2023121816191553800_bib55","doi-asserted-by":"publisher","first-page":"6242","DOI":"10.1109\/ICASSP43922.2022.9747023","article-title":"Isometric mt: Neural machine translation\n                        for automatic dubbing","volume-title":"ICASSP 2022 - 2022 IEEE\n                        International Conference on Acoustics, Speech and Signal Processing\n                        (ICASSP)","author":"Lakew","year":"2022"},{"issue":"8","key":"2023121816191553800_bib56","first-page":"707","article-title":"Binary codes capable of correcting\n                        deletions, insertions and reversals.","volume":"10","author":"Levenshtein","year":"1966","journal-title":"Soviet Physics Doklady"},{"issue":"4","key":"2023121816191553800_bib57","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1109\/TASLP.2014.2304637","article-title":"An overview of noise-robust automatic\n                        speech recognition","volume":"22","author":"Li","year":"2014","journal-title":"IEEE\/ ACM Transactions on Audio,\n                        Speech, and Language Processing"},{"key":"2023121816191553800_bib58","doi-asserted-by":"publisher","first-page":"247","DOI":"10.18653\/v1\/2020.iwslt-1.30","article-title":"Adapting end-to-end speech recognition\n                        for readable subtitles","volume-title":"Proceedings of the 17th\n                        International Conference on Spoken Language Translation","author":"Liu","year":"2020"},{"key":"2023121816191553800_bib59","article-title":"Bridging the modality gap for speech-to-text\n                        translation","author":"Liu","year":"2020","journal-title":"arXiv preprint\n                        arXiv:2010.14920"},{"key":"2023121816191553800_bib60","article-title":"Evaluating machine translation output with automatic sentence\n                        segmentation","volume-title":"Proceedings of the Second\n                        International Workshop on Spoken Language Translation","author":"Matusov","year":"2005"},{"key":"2023121816191553800_bib61","doi-asserted-by":"publisher","first-page":"82","DOI":"10.18653\/v1\/W19-5209","article-title":"Customizing neural machine translation for\n                        subtitling","volume-title":"Proceedings of the Fourth Conference\n                        on Machine Translation (Volume 1: Research Papers)","author":"Matusov","year":"2019"},{"key":"2023121816191553800_bib62","first-page":"204","article-title":"Flexible customization of a single neural\n                        machine translation system with multi-dimensional metadata\n                        inputs","volume-title":"Proceedings of the 14th Conference of the\n                        Association for Machine Translation in the Americas (Volume 2: User\n                        Track)","author":"Matusov","year":"2020"},{"key":"2023121816191553800_bib63","article-title":"Automatic multilingual subtitling in the\n                        eTITLE project","volume-title":"Proceedings of ASLIB Translating\n                        and the Computer 28","author":"Melero","year":"2006"},{"key":"2023121816191553800_bib64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64680-0_8","volume-title":"Robust features in deep-learning-based speech\n                        recognition","author":"Mitra","year":"2017"},{"key":"2023121816191553800_bib65","article-title":"The IWSLT 2019 evaluation\n                        campaign","volume-title":"Proceedings of the 16th International\n                        Conference on Spoken Language Translation","author":"Niehues","year":"2019"},{"key":"2023121816191553800_bib66","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1621","article-title":"Prosodic phrase alignment for machine\n                        dubbing","author":"\u00d6ktem","year":"2019","journal-title":"ArXiv"},{"key":"2023121816191553800_bib67","doi-asserted-by":"publisher","first-page":"48","DOI":"10.18653\/v1\/N19-4009","article-title":"fairseq: A fast, extensible toolkit for sequence\n                        modeling","volume-title":"Proceedings of the 2019 Conference of\n                        the North American Chapter of the Association for Computational Linguistics\n                        (Demonstrations)","author":"Ott","year":"2019"},{"key":"2023121816191553800_bib68","doi-asserted-by":"publisher","first-page":"5206","DOI":"10.1109\/ICASSP.2015.7178964","article-title":"Librispeech: An asr corpus based on public\n                        domain audio books","volume-title":"2015 IEEE International\n                        Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Panayotov","year":"2015"},{"key":"2023121816191553800_bib69","doi-asserted-by":"publisher","first-page":"1698","DOI":"10.18653\/v1\/2021.emnlp-main.127","article-title":"Speechformer: Reducing information loss in\n                        direct speech translation","volume-title":"Proceedings of the\n                        2021 Conference on Empirical Methods in Natural Language\n                    Processing","author":"Papi","year":"2021"},{"key":"2023121816191553800_bib70","first-page":"480","article-title":"Dodging the data bottleneck: Automatic\n                        subtitling with automatically segmented ST corpora","volume-title":"Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the\n                        Association for Computational Linguistics and the 12th International Joint\n                        Conference on Natural Language Processing (Volume 2: Short Papers)","author":"Papi","year":"2022"},{"key":"2023121816191553800_bib71","doi-asserted-by":"publisher","first-page":"2613","DOI":"10.21437\/Interspeech.2019-2680","article-title":"SpecAugment: A simple data augmentation method for automatic\n                        speech recognition","volume-title":"Proceedings of Interspeech\n                        2019","author":"Park","year":"2019"},{"issue":"1","key":"2023121816191553800_bib72","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1075\/btl.78.21per","article-title":"Subtitles and line-breaks: Towards\n                        improved readability","volume":"78","author":"Perego","year":"2008","journal-title":"Between Text and Image:\n                        Updating Research in Screen Translation"},{"key":"2023121816191553800_bib73","article-title":"Multimodal, multilingual resources in the\n                        subtitling process","volume-title":"Proceedings of the Fourth\n                        International Conference on Language Resources and Evaluation\n                        (LREC\u201904)","author":"Piperidis","year":"2004"},{"key":"2023121816191553800_bib74","doi-asserted-by":"publisher","first-page":"186","DOI":"10.18653\/v1\/W18-6319","article-title":"A call for clarity in reporting BLEU scores","volume-title":"Proceedings of the Third Conference on Machine Translation: Research\n                        Papers","author":"Post","year":"2018"},{"key":"2023121816191553800_bib75","doi-asserted-by":"publisher","first-page":"7398","DOI":"10.1109\/ICASSP.2013.6639100","article-title":"An investigation of deep neural networks for noise robust\n                        speech recognition","volume-title":"2013 IEEE International\n                        Conference on Acoustics, Speech and Signal Processing","author":"Seltzer","year":"2013"},{"key":"2023121816191553800_bib76","doi-asserted-by":"publisher","first-page":"1715","DOI":"10.18653\/v1\/P16-1162","article-title":"Neural machine translation of rare words with\n                        subword units","volume-title":"Proceedings of the 54th Annual\n                        Meeting of the Association for Computational Linguistics (Volume 1: Long\n                        Papers)","author":"Sennrich","year":"2016"},{"key":"2023121816191553800_bib77","doi-asserted-by":"publisher","first-page":"7409","DOI":"10.18653\/v1\/2020.acl-main.661","article-title":"Speech translation and the end-to-end\n                        promise: Taking stock of where we are","volume-title":"Proceedings of the 58th Annual Meeting of the Association for\n                        Computational Linguistics","author":"Sperber","year":"2020"},{"key":"2023121816191553800_bib78","first-page":"116","article-title":"Machine translation of speech","volume":"6","author":"Stentiford","year":"1988","journal-title":"British Telecom Technology Journal"},{"issue":"6","key":"2023121816191553800_bib79","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0199331,","article-title":"Viewers can keep up with fast subtitles:\n                        Evidence from eye movements","volume":"13","author":"Szarkowska","year":"2018","journal-title":"PLOS ONE"},{"issue":"2","key":"2023121816191553800_bib80","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1556\/084.2016.17.2.3","article-title":"The effects of text editing and subtitle\n                        presentation rate on the comprehension and reading patterns of interlingual\n                        and intralingual subtitles among deaf, hard of hearing and hearing\n                        viewers","volume":"17","author":"Szarkowska","year":"2016","journal-title":"Across Languages and Cultures"},{"key":"2023121816191553800_bib81","doi-asserted-by":"publisher","first-page":"1776","DOI":"10.21437\/Interspeech.2022-11136","article-title":"Isochrony-aware neural machine translation\n                        for automatic dubbing","volume-title":"Proceedings of Interspeech\n                        2022","author":"Tam","year":"2022"},{"key":"2023121816191553800_bib82","article-title":"OPUS\u2013parallel corpora for\n                        everyone","volume-title":"Proceedings of the 19th Annual\n                        Conference of the European Association for Machine Translation:\n                        Projects\/Products","author":"Tiedemann","year":"2016"},{"key":"2023121816191553800_bib83","article-title":"OPUS-MT\u2014Building open translation\n                        services for the World","volume-title":"Proceedings of the 22nd\n                        Annual Conferenec of the European Association for Machine Translation\n                        (EAMT)","author":"Tiedemann","year":"2020"},{"key":"2023121816191553800_bib84","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-59","article-title":"Shas: Approaching optimal segmentation for\n                        end-to-end speech translation","author":"Tsiamas","year":"2022"},{"key":"2023121816191553800_bib85","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"2023121816191553800_bib86","doi-asserted-by":"publisher","first-page":"7543","DOI":"10.1109\/ICASSP39728.2021.9414966","article-title":"Improvements to prosodic alignment for\n                        automatic dubbing","volume-title":"ICASSP 2021 - 2021 IEEE\n                        International Conference on Acoustics, Speech and Signal Processing\n                        (ICASSP)","author":"Virkar","year":"2021"},{"issue":"3","key":"2023121816191553800_bib87","doi-asserted-by":"publisher","first-page":"44","DOI":"10.47476\/jat.v4i3.2021.197","article-title":"Automation in the intralingual subtitling\n                        process: Exploring productivity and user experience","volume":"4","author":"Vitikainen","year":"2021","journal-title":"Journal of Audiovisual Translation"},{"key":"2023121816191553800_bib88","first-page":"53","article-title":"Machine translation of TV subtitles for\n                        large scale production","volume-title":"Proceedings of the Second\n                        Joint EM+\/CNGL Workshop: Bringing MT to the User: Research on Integrating MT\n                        in the Translation Industry","author":"Volk","year":"2010"},{"key":"2023121816191553800_bib89","doi-asserted-by":"publisher","first-page":"793","DOI":"10.1109\/ICASSP.1991.150456","article-title":"Janus: A speech-to-speech translation\n                        system using connectionist and symbolic processing\n                        strategies","volume-title":"Proceedings of ICASSP 91: 1991\n                        International Conference on Acoustics, Speech, and Signal\n                        Processing","author":"Waibel","year":"1991"},{"key":"2023121816191553800_bib90","doi-asserted-by":"publisher","first-page":"993","DOI":"10.18653\/v1\/2021.acl-long.80","article-title":"VoxPopuli: A large-scale multilingual\n                        speech corpus for representation learning, semi-supervised learning and\n                        interpretation","volume-title":"Proceedings of the 59th Annual\n                        Meeting of the Association for Computational Linguistics and the 11th\n                        International Joint Conference on Natural Language Processing (Volume 1:\n                        Long Papers)","author":"Wang","year":"2021"},{"key":"2023121816191553800_bib91","article-title":"fairseq s2t: Fast speech-to-text modeling\n                        with fairseq","volume-title":"Proceedings of the 2020 Conference\n                        of the Asian Chapter of the Association for Computational Linguistics\n                        (AACL): System Demonstrations","author":"Wang","year":"2020"},{"key":"2023121816191553800_bib92","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2027","article-title":"Covost 2: A massively multilingual\n                        speech-to-text translation corpus","author":"Wang","year":"2020"},{"key":"2023121816191553800_bib93","doi-asserted-by":"publisher","first-page":"2625","DOI":"10.21437\/Interspeech.2017-503","article-title":"Sequence-to-sequence models can directly translate foreign\n                        speech","volume-title":"Proceedings of Interspeech 2017","author":"Weiss","year":"2017"},{"key":"2023121816191553800_bib94","doi-asserted-by":"publisher","first-page":"2533","DOI":"10.18653\/v1\/2021.eacl-main.216","article-title":"Streaming models for joint speech\n                        recognition and translation","volume-title":"Proceedings of the\n                        16th Conference of the European Chapter of the Association for Computational\n                        Linguistics: Main Volume","author":"Weller","year":"2021"},{"key":"2023121816191553800_bib95","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18653\/v1\/2022.iwslt-1.1","article-title":"SubER - A metric for automatic evaluation\n                        of subtitle quality","volume-title":"Proceedings of the 19th\n                        International Conference on Spoken Language Translation (IWSLT\n                        2022)","author":"Wilken","year":"2022"},{"key":"2023121816191553800_bib96","doi-asserted-by":"publisher","first-page":"74","DOI":"10.18653\/v1\/2022.iwslt-1.7","article-title":"Joint generation of captions and subtitles with dual\n                        decoding","volume-title":"Proceedings of the 19th International\n                        Conference on Spoken Language Translation (IWSLT 2022)","author":"Jitao","year":"2022"}],"container-title":["Transactions of the Association for Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00607\/2197786\/tacl_a_00607.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/tacl\/article-pdf\/doi\/10.1162\/tacl_a_00607\/2197786\/tacl_a_00607.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T11:19:47Z","timestamp":1702898387000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/tacl\/article\/doi\/10.1162\/tacl_a_00607\/118115\/Direct-Speech-Translation-for-Automatic-Subtitling"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":96,"URL":"https:\/\/doi.org\/10.1162\/tacl_a_00607","relation":{},"ISSN":["2307-387X"],"issn-type":[{"value":"2307-387X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023]]},"published":{"date-parts":[[2023]]}}}