{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:18:19Z","timestamp":1776885499094,"version":"3.51.2"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T00:00:00Z","timestamp":1673222400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,9]]},"DOI":"10.1109\/slt54892.2023.10023147","type":"proceedings-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:54:03Z","timestamp":1674845643000},"page":"747-754","source":"Crossref","is-referenced-by-count":10,"title":["An Analysis of Semantically-Aligned Speech-Text Embeddings"],"prefix":"10.1109","author":[{"given":"Muhammad","family":"Huzaifah","sequence":"first","affiliation":[{"name":"Institute for Infocomm Research,Agency for Science, Technology and Research,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ivan","family":"Kukanov","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research,Agency for Science, Technology and Research,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1310.4546"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n18-1202"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref4","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref6","first-page":"12736","article-title":"Fused acoustic and text encoding for multimodal bilingual pretraining and speech translation","volume-title":"International Conference on Machine Learning. PMLR","author":"Zheng","year":"2021"},{"key":"ref7","first-page":"15748","article-title":"Multimodal and multilingual embeddings for large-scale speech mining","volume":"34","author":"Duquenne","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","article-title":"Un-supervised cross-modal alignment of speech and text embedding spaces","volume":"31","author":"Chung","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1065"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.195"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17509"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.328"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2456"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.152"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1570"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1198"},{"key":"ref17","article-title":"Fine-grained analysis of sentence embeddings using auxiliary prediction tasks","volume-title":"International Conference on Learning Representations (ICLR)","author":"Adi","year":"2017"},{"key":"ref18","article-title":"What do you learn from context? probing for sentence structure in contextualized word representations","volume-title":"International Conference on Learning Representations (ICLR)","author":"Tenney","year":"2019"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1006"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1036"},{"key":"ref22","article-title":"fairseq s2t: Fast speech-to-text modeling with fairseq","author":"Wang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682632"},{"key":"ref24","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International Conference on Machine Learning","volume":"139","author":"Jia","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref29","first-page":"2012","article-title":"MuST -C: A Multilingual Speech Translation Corpus","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Di Gangi","year":"2019"},{"key":"ref30","first-page":"4197","article-title":"CoVoST: A di-verse multilingual speech-to-text translation corpus","volume-title":"Proceedings of the 12th Language Resources and Evaluation Conference","author":"Wang","year":"2020"},{"key":"ref31","article-title":"Interpreting and explaining deep neural networks for classification of audio signals","volume":"abs\/1807.03418","author":"Becker","year":"2018","journal-title":"CoRR"},{"key":"ref32","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"TIMIT acoustic pho-netic continuous speech corpus","author":"Garofolo","year":"1993","journal-title":"Linguistic Data Con-sortium"},{"key":"ref34","volume-title":"Silero models: pre-trained enterprise-grade STT \/ TTS models and benchmarks","author":"Team","year":"2021"}],"event":{"name":"2022 IEEE Spoken Language Technology Workshop (SLT)","location":"Doha, Qatar","start":{"date-parts":[[2023,1,9]]},"end":{"date-parts":[[2023,1,12]]}},"container-title":["2022 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10022052\/10022330\/10023147.pdf?arnumber=10023147","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T09:25:15Z","timestamp":1707816315000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10023147\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,9]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/slt54892.2023.10023147","relation":{},"subject":[],"published":{"date-parts":[[2023,1,9]]}}}