{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:36:58Z","timestamp":1740123418779,"version":"3.37.3"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2018,4,6]],"date-time":"2018-04-06T00:00:00Z","timestamp":1522972800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,4,6]],"date-time":"2018-04-06T00:00:00Z","timestamp":1522972800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["24240032","26870371"],"award-info":[{"award-number":["24240032","26870371"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Translation"],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1007\/s10590-018-9217-7","type":"journal-article","created":{"date-parts":[[2018,4,6]],"date-time":"2018-04-06T20:10:23Z","timestamp":1523045423000},"page":"353-368","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["An end-to-end model for cross-lingual transformation of paralinguistic information"],"prefix":"10.1007","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9693-3785","authenticated-orcid":false,"given":"Takatomo","family":"Kano","sequence":"first","affiliation":[]},{"given":"Shinnosuke","family":"Takamichi","sequence":"additional","affiliation":[]},{"given":"Sakriani","family":"Sakti","sequence":"additional","affiliation":[]},{"given":"Graham","family":"Neubig","sequence":"additional","affiliation":[]},{"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[]},{"given":"Satoshi","family":"Nakamura","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,4,6]]},"reference":[{"key":"9217_CR1","doi-asserted-by":"crossref","unstructured":"Abe M, Nakamura S, Shikano K, Kuwabara H (1988) Voice conversion through vector quantization. In: ICASSP-88, international conference on acoustics, speech, and signal processing, New York City, vol\u00a01, pp 655\u2013658","DOI":"10.1109\/ICASSP.1988.196671"},{"key":"9217_CR2","doi-asserted-by":"crossref","unstructured":"Aguero PD, Adell J, Bonafonte A (2006) Prosody generation for speech-to-speech translation. In: 2006 IEEE international conference on acoustics speech and signal processing proceedings, Toulouse, France","DOI":"10.21437\/SpeechProsody.2006-118"},{"key":"9217_CR3","doi-asserted-by":"crossref","unstructured":"Anumanchipalli GK, Oliveira LC, Black AW (2012) Intent transfer in speech-to-speech machine translation. In: 2012 IEEE spoken language technology workshop (SLT), Miami, FL, pp 153\u2013158","DOI":"10.1109\/SLT.2012.6424214"},{"key":"9217_CR4","unstructured":"Do QT, Sakti S, Neubig G, Toda T, Nakamura S (2015a) Improving translation of emphasis with pause prediction in speech-to-speech translation systems. In: IWSLT 2015: proceedings of the 12th international workshop on spoken language translation, Da Nang, Vietnam, pp 204\u2013208"},{"key":"9217_CR5","doi-asserted-by":"crossref","unstructured":"Do QT, Takamichi S, Sakti S, Neubig G, Toda T, Nakamura S (2015b) Preserving word-level emphasis in speech-to-speech translation using linear regression HSMMs. In: INTERSPEECH 2015, 16th annual conference of the international speech communication association, Dresden, pp 3665\u20133669","DOI":"10.21437\/Interspeech.2015-727"},{"key":"9217_CR6","unstructured":"Do QT, Sakti S, Nakamura S (2017) Toward expressive speech translation: a unified sequence-to-sequence LSTMs approach for translating words and emphasis. In: Interspeech 2017, 18th annual conference of the international speech communication association, Stockholm, Sweden, pp 2640\u20132644"},{"key":"9217_CR7","doi-asserted-by":"crossref","unstructured":"Dreyer M, Dong Y (2015) Apro: all-pairs ranking optimization for mt tuning. In: Proceedings of the 2015 conference of the North American chapter of the association for computational linguistics: human language technologies, Denver, CO, pp 1018\u20131023","DOI":"10.3115\/v1\/N15-1106"},{"key":"9217_CR8","doi-asserted-by":"crossref","unstructured":"Duong L, Anastasopoulos A, Chiang D, Bird S, Cohn T (2016) An attentional model for speech translation without transcription. In: Proceedings of the 2016 conference of the North American chapter of the association for computational linguistics: human language technologies, San Diego, CA, pp 949\u2013959","DOI":"10.18653\/v1\/N16-1109"},{"key":"9217_CR9","unstructured":"Jiang J, Ahmed Z, Carson-Berndsen J, Cahill P, Way A (2011) Phonetic representation-based speech translation. In: Proceedings of machine translation summit XIII, Xiamen, China, pp 81\u201388"},{"key":"9217_CR10","unstructured":"Kano T, Sakti S, Takamichi S, Neubig G, Toda T, Nakamura S (2012) A method for translation of paralinguistic information. In: 2012 International workshop on spoken language translation, Hong Kong, pp 158\u2013163"},{"key":"9217_CR11","doi-asserted-by":"crossref","unstructured":"Kano T, Takamichi S, Sakti S, Neubig G, Toda T, Nakamura S (2013) Generalizing continuous-space translation of paralinguistic information. In: INTERSPEECH 2013, 14th Annual conference of the international speech communication association, Lyon, France, pp 2614\u20132618","DOI":"10.21437\/Interspeech.2013-602"},{"key":"9217_CR12","unstructured":"Koehn P, Hoang H (2007) Factored translation models. In: EMNLP-CoNLL-2007: proceedings of the 2007 joint conference on empirical methods in natural language processing and computational natural language learning, Prague, Czech Republic, pp 868\u2013876"},{"key":"9217_CR13","doi-asserted-by":"crossref","unstructured":"Koehn P, Hoang H, Birch A, Callison-Burch C, Federico M, Bertoldi N, Cowan B, Shen W, Moran C, Zens R, Dyer C, Bojar O, Constantin A, Herbst E (2007) Moses: open source toolkit for statistical machine translation. In: Proceedings of the 45th annual meeting of the ACL on interactive poster and demonstration sessions, Prague, Czech Republic, pp 177\u2013180","DOI":"10.3115\/1557769.1557821"},{"key":"9217_CR14","doi-asserted-by":"crossref","unstructured":"Leonard R (1984) A database for speaker-independent digit recognition. In: ICASSP \u201984. IEEE international conference on acoustics, speech, and signal processing, San Diego, CA, pp 328\u2013331","DOI":"10.1109\/ICASSP.1984.1172716"},{"key":"9217_CR15","doi-asserted-by":"crossref","unstructured":"Morishima S, Nakamura S (2002) Multi-modal translation system and its evaluation. In: Proceedings of the fourth IEEE international conference on multimodal interfaces, Pittsburgh, PA, pp 241\u2013246","DOI":"10.1109\/ICMI.2002.1167000"},{"key":"9217_CR16","unstructured":"Neubig G, Duh K, Ogushi M, Kano T, Kiso T, Sakti S, Toda T, Nakamura S (2012) The NAIST machine translation system for IWSLT 2012. In: IWSLT-2012: 9th international workshop on spoken language translation, Hong Kong, pp 54\u201360"},{"key":"9217_CR17","unstructured":"Papineni K, Roukos S, Ward T, Zhu WJ (2002) Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting on association for computational linguistics, Philadelphia, PA, pp 311\u2013318"},{"key":"9217_CR18","doi-asserted-by":"crossref","unstructured":"Pearce D, Hirsch HG (2000) The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions. In: ASR2000\u2014Automatic speech recognition: challenges for the new millenium, Paris, France, pp 181\u2013188","DOI":"10.21437\/ICSLP.2000-743"},{"issue":"2","key":"9217_CR19","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1016\/j.csl.2011.08.001","volume":"27","author":"VKR Sridhar","year":"2013","unstructured":"Sridhar VKR, Bangalore S, Narayanan S (2013) Enriching machine-mediated speech-to-speech translation using contextual information. Comput Speech Lang 27(2):492\u2013508","journal-title":"Comput Speech Lang"},{"issue":"1","key":"9217_CR20","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/s12193-013-0128-x","volume":"8","author":"\u00c9 Sz\u00e9kely","year":"2014","unstructured":"Sz\u00e9kely \u00c9, Steiner I, Ahmed Z, Carson-Berndsen J (2014) Facial expression-based affective speech translation. J Multimodal User Interfaces 8(1):87\u201396","journal-title":"J Multimodal User Interfaces"},{"key":"9217_CR21","doi-asserted-by":"crossref","unstructured":"Takezawa T, Morimoto T, Sagisaka Y, Campbell N, Iida H, Sugaya F, Yokoo A, Yamamoto S (1998) A Japanese-to-English speech translation system: ATR-MATRIX. In: 5th international conference on spoken language processing, ICSLP\u201998 proceedings, Sydney, Australia, pp 2779\u20132883","DOI":"10.21437\/ICSLP.1998-581"},{"issue":"8","key":"9217_CR22","doi-asserted-by":"publisher","first-page":"2222","DOI":"10.1109\/TASL.2007.907344","volume":"15","author":"T Toda","year":"2007","unstructured":"Toda T, Black AW, Tokuda K (2007) Voice conversion based on maximum-likelihood estimation of spectral parameter trajectory. IEEE Trans Audio Speech Lang Process 15(8):2222\u20132235","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"9217_CR23","unstructured":"Wahlster W (2001) Robust translation of spontaneous speech: a multi-engine approach. In: Proceedings of seventeenth international joint conference on artificial intelligence, invited papers, Seattle, WA, pp 19\u201328"},{"key":"9217_CR24","unstructured":"Weiss RJ, Chorowski J, Jaitly N, Wu Y, Chen Z (2017) Sequence-to-sequence models can directly transcribe foreign speech. arXiv:1703.08581"},{"issue":"11","key":"9217_CR25","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.1016\/j.specom.2009.04.004","volume":"51","author":"H Zen","year":"2009","unstructured":"Zen H, Tokuda K, Black AW (2009) Statistical parametric speech synthesis. Speech Commun 51(11):1039\u20131064","journal-title":"Speech Commun"},{"key":"9217_CR26","unstructured":"Zhang J, Nakamura S (2003) An efficient algorithm to search for a minimum sentence set for collecting speech database. In: 15th international congress of phonetic sciences (ICPhS-15), Barcelona, Spain, pp 3145\u20133148"}],"container-title":["Machine Translation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10590-018-9217-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10590-018-9217-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10590-018-9217-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T20:26:44Z","timestamp":1720211204000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10590-018-9217-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4,6]]},"references-count":26,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2018,12]]}},"alternative-id":["9217"],"URL":"https:\/\/doi.org\/10.1007\/s10590-018-9217-7","relation":{},"ISSN":["0922-6567","1573-0573"],"issn-type":[{"type":"print","value":"0922-6567"},{"type":"electronic","value":"1573-0573"}],"subject":[],"published":{"date-parts":[[2018,4,6]]},"assertion":[{"value":"18 July 2016","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 March 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 April 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}