{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T08:51:14Z","timestamp":1781772674663,"version":"3.54.5"},"reference-count":24,"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.2025.0137","type":"journal-article","created":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T05:29:32Z","timestamp":1759037372000},"page":"20250137","update-policy":"https:\/\/doi.org\/10.1360\/scp-crossmark-policy-page","source":"Crossref","is-referenced-by-count":0,"title":["Tibetan-Chinese Speech-to-Speech Translation Based on Large Speech Models"],"prefix":"10.3724","volume":"8","author":[{"given":"Hetong","family":"Fan","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":"Zairan","family":"Gong","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":[[2025,9,28]]},"reference":[{"key":"null","unstructured":"Du J., Zhang M., Zong C., and Sun L., \u201cOpportunities and challenges for machine translation research in China\u2014Summary and prospects for the 8th China Workshop on Machine Translation,\u201d J. Chinese Inf. Process., vol. 27, no. 4, pp. 1\u20138, 2013."},{"key":"null","unstructured":"Yang Z., \u201cResearch on key issues of Russian-Chinese military speech translation based on Seq2Seq model,\u201d M.S. thesis, Inf. Eng. Univ., Zhengzhou, China, 2019."},{"key":"null","unstructured":"Lavie A. et al., \u201cJANUS-III: Speech-to-speech translation in multiple languages,\u201d in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), Munich, Germany, 1997, vol. 1, pp. 99\u2013102."},{"key":"null","unstructured":"Nakamura S. et al., \u201cThe ATR multilingual speech-to-speech translation system,\u201d IEEE Trans. Audio, Speech, Lang. Process., vol. 14, no. 2, pp. 365\u2013376, Mar. 2006."},{"key":"null","unstructured":"Wahlster W., Verbmobil: Foundations of Speech-to-Speech Translation. Berlin, Germany: Springer, 2013."},{"key":"null","unstructured":"Xu X., Tan J., and Zhao Y., \u201cEnd-to-end Tibetan-Chinese speech translation based on multi-task and multi-level pre-training,\u201d in Proc. IEEE 6th Int. Conf. Pattern Recognit. Artif. Intell. (PRAI), 2023, pp. 852\u2013857."},{"key":"null","unstructured":"Liu R., Zhao Y., and Xu X., \u201cMulti-task self-supervised learning based Tibetan-Chinese speech-to-speech translation,\u201d in Proc. Int. Conf. Asian Lang. Process. (IALP), 2023, pp. 45\u201349."},{"key":"null","unstructured":"Jia Y. et al., \u201cDirect speech-to-speech translation with a sequence-to-sequence model,\u201d arXiv preprint, arXiv:1904.06037, 2019."},{"key":"null","unstructured":"Tjandra A., Sakti S., and Nakamura S., \u201cSpeech-to-speech translation between untranscribed unknown languages,\u201d in Proc. IEEE Autom. Speech Recognit. Understanding Workshop (ASRU), 2019, pp. 593\u2013600."},{"key":"null","unstructured":"Zhang C. et al., \u201cUWSpeech: Speech-to-speech translation for unwritten languages,\u201d in Proc. AAAI Conf. Artif. Intell., vol. 35, no. 16, 2021, pp. 14319\u201314327."},{"key":"null","unstructured":"van den Oord A., Vinyals O., et al., \u201cNeural discrete representation learning,\u201d in Adv. Neural Inf. Process. Syst., vol. 30, 2017."},{"key":"null","unstructured":"Lee A. et al., \u201cDirect speech-to-speech translation with discrete units,\u201d arXiv preprint, arXiv:2107.05604, 2021."},{"key":"null","unstructured":"Hsu W.-N. et al., \u201cHuBERT: Self-supervised speech representation learning by masked prediction of hidden units,\u201d IEEE\/ACM Trans. Audio, Speech, Lang. Process., vol. 29, pp. 3451\u20133460, 2021."},{"key":"null","unstructured":"Huang R. et al., \u201cTranspeech: Speech-to-speech translation with bilateral perturbation,\u201d arXiv preprint, arXiv:2205.12523, 2022."},{"key":"null","unstructured":"Wei K. et al., \u201cJoint pre-training with speech and bilingual text for direct speech-to-speech translation,\u201d in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2023, pp. 1\u20135."},{"key":"null","unstructured":"Radford A. et al., \u201cRobust speech recognition via large-scale weak supervision,\u201d in Proc. Int. Conf. Mach. Learn. (ICML), 2023, pp. 28492\u201328518."},{"key":"null","unstructured":"Pratap V. et al., \u201cScaling speech technology to 1,000+ languages,\u201d J. Mach. Learn. Res., vol. 25, no. 97, pp. 1\u201352, 2024."},{"key":"null","unstructured":"Rubenstein P. K. et al., \u201cAudioPaLM: A large language model that can speak and listen,\u201d arXiv preprint, arXiv:2306.12925, 2023."},{"key":"null","unstructured":"Barrault L. et al., \u201cSeamlessM4T: Massively multilingual and multimodal machine translation,\u201d arXiv preprint, arXiv:2308.11596, 2023."},{"key":"null","unstructured":"B\u00e9rard A., Pietquin O., Servan C., and Besacier L., \u201cListen and translate: A proof of concept for end-to-end speech-to-text translation,\u201d arXiv preprint, arXiv:1612.01744, 2016."},{"key":"null","unstructured":"Kano T., Sakti S., and Nakamura S., \u201cTransformer-based direct speech-to-speech translation with transcoder,\u201d in Proc. IEEE Spoken Lang. Technol. Workshop (SLT), 2021, pp. 958\u2013965."},{"key":"null","unstructured":"Kong J., Kim J., and Bae J., \u201cHiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis,\u201d in Adv. Neural Inf. Process. Syst., vol. 33, 2020, pp. 17022\u201317033."},{"key":"null","unstructured":"Post M., \u201cA call for clarity in reporting BLEU scores,\u201d arXiv preprint, arXiv:1804.08771, 2018."},{"key":"null","unstructured":"ITU-T, Methods for Subjective Determination of Transmission Quality, Int. Telecommun. Union, Geneva, Switzerland, 1996."}],"container-title":["Data Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.sciengine.com\/sci-open\/api\/v1\/open\/file\/pdf\/7DF43913D9B845C38FC3340C9A7FD3EE","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.sciengine.com\/doi\/10.3724\/2096-7004.di.2025.0137","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.sciengine.com\/sci-open\/api\/v1\/open\/file\/pdf\/7DF43913D9B845C38FC3340C9A7FD3EE","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T07:57:11Z","timestamp":1781769431000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.sciengine.com\/doi\/10.3724\/2096-7004.di.2025.0137"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,28]]},"references-count":24,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,9,28]]},"published-print":{"date-parts":[[2026,6,1]]}},"URL":"https:\/\/doi.org\/10.3724\/2096-7004.di.2025.0137","relation":{},"ISSN":["2096-7004"],"issn-type":[{"value":"2096-7004","type":"print"}],"subject":[],"published":{"date-parts":[[2025,9,28]]}}}