{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:29:28Z","timestamp":1775665768612,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012652","name":"ETH Z\u00fcrich Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012652","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688073","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"733-740","source":"Crossref","is-referenced-by-count":6,"title":["Assessing Evaluation Metrics for Speech-to-Speech Translation"],"prefix":"10.1109","author":[{"given":"Elizabeth","family":"Salesky","sequence":"first","affiliation":[{"name":"Johns Hopkins University,USA"}]},{"given":"Julian","family":"Mader","sequence":"additional","affiliation":[{"name":"ETH Zürich,Switzerland"}]},{"given":"Severin","family":"Klinger","sequence":"additional","affiliation":[{"name":"ETH Zürich,Switzerland"}]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324915000315"},{"key":"ref33","first-page":"15","article-title":"ASR for Non-standardised Languages with Dialectal Variation: the case of Swiss German","author":"nigmatulina","year":"0","journal-title":"Proceedings of the 7th Workshop on NLP for Similar Languages Va-rieties and Dialects"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003990"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1201\/9780429246593"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-3204"},{"key":"ref37","first-page":"4061","article-title":"ArchiMob - a corpus of spoken Swiss German","author":"samardzic","year":"2016","journal-title":"Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)"},{"key":"ref36","first-page":"336","article-title":"To-wards Variability Resistant Dialectal Speech Evaluation","author":"ali","year":"0","journal-title":"InterSpeech"},{"key":"ref35","article-title":"Data-driven pro-nunciation modeling of swiss german dialectal speech for automatic speech recognition","author":"stadtschnitzer","year":"0","journal-title":"LREC"},{"key":"ref34","first-page":"2720","article-title":"A Swiss German dictionary: Variation in speech and writing","author":"schmidt","year":"2020","journal-title":"Proceedings of the 12th Language Resources and Evaluation Conference"},{"key":"ref10","article-title":"Wave-tacotron: Spectrogram-free end-to-end text-to-speech synthesis","author":"weiss","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref11","article-title":"UWSpeech: Speech to Speech Translation for Unwritten Languages","author":"zhang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383496"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2012.02.004"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-3049"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3_4"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1500"},{"key":"ref19","year":"2018","journal-title":"LibriVox"},{"key":"ref28","article-title":"Text-to-Speech (TTS) for Seven Swiss German Dialects","volume":"6","author":"traber","year":"2019","journal-title":"SwissText"},{"key":"ref4","first-page":"1291","article-title":"Speech translation for French in the Nespole! Euro-pean project","author":"besacier","year":"0","journal-title":"Eurospeech'01"},{"key":"ref27","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.599563"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.860774"},{"key":"ref29","article-title":"Text-to-Speech (TTS) for Seven Swiss German Dialects","volume":"6","author":"traber","year":"2020","journal-title":"SwissText"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3115\/1289189.1289233"},{"key":"ref8","article-title":"Di-rect speech-to-speech translation with a sequence-to-sequence model","author":"jia","year":"0","journal-title":"InterSpeech"},{"key":"ref7","author":"wahlster","year":"2013","journal-title":"Verbmobil Foundations of Speech-to-Speech Translation"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-60087-6_33"},{"key":"ref9","article-title":"Syn-thesizer voice quality of new languages calibrated with mean mel cepstral distortion","author":"kominek","year":"2008","journal-title":"Spoken Language Technologies for Under-resoured Languages"},{"key":"ref1","first-page":"1138","article-title":"Unsupervised phonetic and word level discov-ery for speech to speech translation for unwritten languages","author":"hillis","year":"0","journal-title":"InterSpeech"},{"key":"ref20","author":"dogan-sch\u00f6nberger","year":"2021","journal-title":"SwissDial Parallel Multidialectal Corpus of Spoken Swiss German"},{"key":"ref22","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"ashish","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref21","year":"2017","journal-title":"SPTK"},{"key":"ref24","article-title":"To-ward multilingual neural machine translation with uni-versal encoder and decoder","author":"ha","year":"0","journal-title":"Proceedings of IWSLT"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Cartagena, Colombia","start":{"date-parts":[[2021,12,13]]},"end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688073.pdf?arnumber=9688073","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:42:10Z","timestamp":1652733730000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688073\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688073","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}