{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T08:51:02Z","timestamp":1781772662397,"version":"3.54.5"},"reference-count":32,"publisher":"China Science Publishing & Media Ltd.","issue":"2","content-domain":{"domain":["engine.scichina.com"],"crossmark-restriction":false},"short-container-title":["DI"],"published-print":{"date-parts":[[2026,6,1]]},"DOI":"10.3724\/2096-7004.di.2025.0135","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T07:07:57Z","timestamp":1758524877000},"page":"20250135","update-policy":"https:\/\/doi.org\/10.1360\/scp-crossmark-policy-page","source":"Crossref","is-referenced-by-count":0,"title":["PhoenixS: Enhanced Self-reconstruction with Pre-trained Decoder for Speech-to-Speech Translation Using Monolingual Data"],"prefix":"10.3724","volume":"8","author":[{"given":"Wei","family":"Zong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaona","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"2026","published-online":{"date-parts":[[2025,9,22]]},"reference":[{"key":"null","unstructured":"Lavie A. \u00a0 et al., \u201cJanus-iii: speech-to-speech translation in multiple languages,\u201d in\u00a0 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 1, 1997, pp. 99\u2013102."},{"key":"null","unstructured":"Nakamura S. \u00a0 et al., \u201cThe art multilingual speech-to-speech translation system,\u201d\u00a0 IEEE Transactions on Audio, Speech, and Language Processing, vol. 14, no. 2, pp. 365\u2013376, 2006."},{"key":"null","unstructured":"Jia Y. \u00a0 et al., \u201cDirect speech-to-speech translation with a sequence-to-sequence model,\u201d 2019. [Online]. Available: arXiv:1904.06037."},{"key":"null","unstructured":"Jia Y., Ramanovich M. T., Remez T., and Pomerantz R., \u201cTranslatotron 2: High-quality direct speech-to-speech translation with voice preservation,\u201d in\u00a0 International Conference on Machine Learning. PMLR, 2022, pp. 10120\u201310134."},{"key":"null","unstructured":"Lee A. \u00a0 et al., \u201cDirect speech-to-speech translation with discrete units,\u201d 2021. [Online]. Available: arXiv:2107.05604."},{"key":"null","unstructured":"Hsu W.-N., Bolte B., Tsai Y.-H. H., Lakhotia K., Salakhutdinov R., and Mohamed A., \u201cHubert: Self-supervised speech representation learning by masked prediction of hidden units,\u201d\u00a0 IEEE\/ACM Transactions on Audio, Speech, and Language Processing, vol. 29, pp. 3451\u20133460, 2021."},{"key":"null","unstructured":"Polyak A. \u00a0 et al., \u201cSpeech resynthesis from discrete disentangled self-supervised representations,\u201d 2021. [Online]. Available: arXiv:2104.00355."},{"key":"null","unstructured":"Lee A. \u00a0 et al., \u201cTextless speech-to-speech translation on real data,\u201d 2021. [Online]. Available: arXiv:2112.08352."},{"key":"null","unstructured":"Inaguma H. \u00a0 et al., \u201cUnity: Two-pass direct speech-to-speech translation with discrete units,\u201d 2022. [Online]. Available: arXiv:2212.08055."},{"key":"null","unstructured":"Dong Q., Yue F., Ko T., Wang M., Bai Q., and Zhang Y., \u201cLeveraging pseudo-labeled data to improve direct speech-to-speech translation,\u201d 2022. [Online]. Available: arXiv:2205.08993."},{"key":"null","unstructured":"Jia Y., Ramanovich M. T., Wang Q., and Zen H., \u201cCvss corpus and massively multilingual speech-to-speech translation,\u201d 2022. [Online]. Available: arXiv:2201.03713."},{"key":"null","unstructured":"Popuri S. \u00a0 et al., \u201cEnhanced direct speech-to-speech translation using self-supervised pre-training and data augmentation,\u201d 2022. [Online]. Available: arXiv:2204.02967."},{"key":"null","unstructured":"Jia Y. \u00a0 et al., \u201cLeveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation,\u201d 2022. [Online]. Available: arXiv:2203.13339."},{"key":"null","unstructured":"Zhang C., Tan X., Ren Y., Qin T., Zhang K., and Liu T.-Y., \u201cUwspeech: Speech to speech translation for unwritten languages,\u201d in\u00a0 Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 16, 2021, pp. 14319\u201314327."},{"key":"null","unstructured":"Chen P.-J. \u00a0 et al., \u201cSpeech-to-speech translation for a real-world unwritten language,\u201d 2022. [Online]. Available: arXiv:2211.06474."},{"key":"null","unstructured":"Barrault L. \u00a0 et al., \u201cSeamlessm4t- massively multilingual & multimodal machine translation,\u201d 2023. [Online]. Available: arXiv:2308.11596."},{"key":"null","unstructured":"Duquenne P.-A. \u00a0 et al., \u201cSpeechmatrix: A large-scale mined corpus of multilingual speech-to-speech translations,\u201d 2022. [Online]. Available: arXiv:2211.04508."},{"key":"null","unstructured":"Nachmani E., Levkovitch A., Ding Y., Asawaroengchai C., Zen H., and Ramanovich M. T., \u201cTranslatotron 3: Speech to speech translation with monolingual data,\u201d in\u00a0 ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2024, pp. 10686\u201310690."},{"key":"null","unstructured":"Kim S.-B., Lee S.-H., and Lee S.-W., \u201cTransentence: speech-to-speech translation via language-agnostic sentence-level speech encoding without language-parallel data,\u201d in\u00a0 ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2024, pp. 12722\u201312726."},{"key":"null","unstructured":"Lavie A. \u00a0 et al., \u201cJanus-iii: Speech-to-speech translation in multiple languages,\u201d in\u00a0 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 1, 1997, pp. 99\u2013102."},{"key":"null","unstructured":"Nakamura S. \u00a0 et al., \u201cThe art multilingual speech-to-speech translation system,\u201d\u00a0 IEEE Transactions on Audio, Speech, and Language Processing, vol. 14, no. 2, pp. 365\u2013376, 2006."},{"key":"null","unstructured":"Wei K. \u00a0 et al., \u201cJoint pre-training with speech and bilingual text for direct speech to speech translation,\u201d in\u00a0 ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023, pp. 1\u20135."},{"key":"null","unstructured":"Babu A. \u00a0 et al., \u201cXls-r: Self-supervised cross-lingual speech representation learning at scale,\u201d 2021. [Online]. Available: arXiv:2111.09296."},{"key":"null","unstructured":"Liu Y., \u201cMultilingual denoising pre-training for neural machine translation,\u201d 2020. [Online]. Available: arXiv:2001.08210."},{"key":"null","unstructured":"Wang C. \u00a0 et al., \u201cVoxPopuli: A large-scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation,\u201d in\u00a0 Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Online, Aug. 2021, pp. 993\u20131003."},{"key":"null","unstructured":"Li X. \u00a0 et al., \u201cMultilingual speech translation with efficient finetuning of pretrained models,\u201d 2020. [Online]. Available: arXiv:2010.12829."},{"key":"null","unstructured":"Kong Z., Ping W., Dantrey A., and Catanzaro B., \u201cSpeech denoising in the waveform domain with self-attention,\u201d in\u00a0 ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2022, pp. 7867\u20137871."},{"key":"null","unstructured":"Ronneberger O., Fischer P., and Brox T., \u201cU-net: Convolutional networks for biomedical image segmentation,\u201d in\u00a0 Medical image computing and computer-assisted intervention \u2013 MICCAI 2015, 2015, pp. 234\u2013241."},{"key":"null","unstructured":"Ardila R. \u00a0 et al., \u201cCommon voice: A massively-multilingual speech corpus,\u201d 2019. [Online]. Available: arXiv:1912.06670."},{"key":"null","unstructured":"Vaswani A., \u201cAttention is all you need,\u201d in\u00a0 Adv. Neural Inf. Process. Syst. (NeurIPS), 2017, pp. 5998\u20136008."},{"key":"null","unstructured":"Kingma D. P. and Ba J., \u201cAdam: A method for stochastic optimization,\u201d 2017. [Online]. Available: arXiv:1412.6980."},{"key":"null","unstructured":"Post M., \u201cA call for clarity in reporting bleu scores,\u201d 2018. [Online]. Available: arXiv:1804.08771."}],"container-title":["Data Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.sciengine.com\/sci-open\/api\/v1\/open\/file\/pdf\/4C69908E1318421AAE6AADE204D0B437","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.sciengine.com\/doi\/10.3724\/2096-7004.di.2025.0135","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.sciengine.com\/sci-open\/api\/v1\/open\/file\/pdf\/4C69908E1318421AAE6AADE204D0B437","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T07:54:49Z","timestamp":1781769289000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.sciengine.com\/doi\/10.3724\/2096-7004.di.2025.0135"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"references-count":32,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,9,22]]},"published-print":{"date-parts":[[2026,6,1]]}},"URL":"https:\/\/doi.org\/10.3724\/2096-7004.di.2025.0135","relation":{},"ISSN":["2096-7004"],"issn-type":[{"value":"2096-7004","type":"print"}],"subject":[],"published":{"date-parts":[[2025,9,22]]}}}