{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T08:51:12Z","timestamp":1781772672245,"version":"3.54.5"},"reference-count":22,"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.2025.0128","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T07:07:16Z","timestamp":1758524836000},"page":"20250128","update-policy":"https:\/\/doi.org\/10.1360\/scp-crossmark-policy-page","source":"Crossref","is-referenced-by-count":0,"title":["Efficient and Natural Tibetan Speech Synthesis via Gaussian Noise-Improved Monotonic Alignment Search and Lightweight iSTFT Multiband Decoder"],"prefix":"10.3724","volume":"8","author":[{"given":"Shiqi","family":"Wu","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":"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":"Tan X., Qin T., Soong F., and Liu T. -Y., \u201cA survey on neural speech synthesis,\u201d arXiv preprint, 2021."},{"key":"null","unstructured":"Van Den Oord A., Dieleman S., Zen H., Simonyan K., Vinyals O., Graves A., Kalchbrenner N., Senior A., Kavukcuoglu K., et al., \u201cWavenet: A generative model for raw audio,\u201d arXiv preprint, 2016."},{"key":"null","unstructured":"Ar\u0131k S. \u00d6., Chrzanowski M., Coates A., Diamos G., Gibiansky A., Kang Y., Li X., Miller J., Ng A., Raiman J., et al., \u201cDeep voice: Real-time neural text-to-speech,\u201d in Proc. Int. Conf. Mach. Learn., pp. 195\u2013204, PMLR, 2017."},{"key":"null","unstructured":"Gibiansky A., Arik S., Diamos G., Miller J., Peng K., Ping W., Raiman J., and Zhou Y., \u201cDeep voice 2: Multi-speaker neural text-to-speech,\u201d Adv. Neural Inf. Process. Syst., vol. 30, 2017."},{"key":"null","unstructured":"Ping W., Peng K., Gibiansky A., Arik S. O., Kannan A., Narang S., Raiman J., and Miller J., \u201cDeep voice 3: Scaling text-to-speech with convolutional sequence learning,\u201d arXiv preprint, 2017."},{"key":"null","unstructured":"Wang Y., Skerry-Ryan R. J., Stanton D., Wu Y., Weiss R. J., Jaitly N., Yang Z., Xiao Y., Chen Z., Bengio S., et al., \u201cTacotron: Towards end-to-end speech synthesis,\u201d arXiv preprint, 2017."},{"key":"null","unstructured":"Ren Y., Ruan Y., Tan X., Qin T., Zhao S., Zhao Z., and Liu T. -Y., \u201cFastSpeech: Fast, robust and controllable text to speech,\u201d Adv. Neural Inf. Process. Syst., vol. 32, 2019."},{"key":"null","unstructured":"Ren Y., Hu C., Tan X., Qin T., Zhao S., Zhao Z., and Liu T. -Y., \u201cFastspeech 2: Fast and high-quality end-to-end text to speech,\u201d arXiv preprint, 2020."},{"key":"null","unstructured":"Zhou Q., Xu X., and Zhao Y., \u201cTibetan speech synthesis based on pre-trained mixture alignment fastspeech2,\u201d Appl. Sci., vol. 14, no. 15, p. 6834, 2024."},{"key":"null","unstructured":"Kaur N. and Singh P., \u201cConventional and contemporary approaches used in text to speech synthesis: A review,\u201d Artif. Intell. Rev., vol. 56, no. 7, pp. 5837\u20135880, 2023."},{"key":"null","unstructured":"Kim J., Kong J., and Son J., \u201cConditional variational autoencoder with adversarial learning for end-to-end text-to-speech,\u201d in Proc. Int. Conf. Mach. Learn., pp. 5530\u20135540, PMLR, 2021."},{"key":"null","unstructured":"Xie X., \u201cResearch on speech synthesis technology of tibetan lhasa dialect,\u201d Master\u2019s thesis, Tibet Univ., 2021. (in Chinese)."},{"key":"null","unstructured":"Li Y., Cai Z., et al., \u201cUnit selection for tibetan speech synthesis,\u201d J. Softw., vol. 26, no. 6, pp. 1409\u20131420, 2015. (in Chinese)."},{"key":"null","unstructured":"Kong J., Park J., Kim B., Kim J., Kong D., and Kim S., \u201cVits2: Improving quality and efficiency of single-stage text-to-speech with adversarial learning and architecture design,\u201d arXiv preprint, 2023."},{"key":"null","unstructured":"Kawamura M., Shirahata Y., Yamamoto R., and Tachibana K., \u201cLightweight and high-fidelity end-to-end text-to-speech with multi-band generation and inverse short-time fourier transform,\u201d in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), pp. 1\u20135, IEEE, 2023."},{"key":"null","unstructured":"Guo Y., Lv Y., Dou J., Zhang Y., and Wang Y., \u201cFly-tts: Fast, lightweight and high-quality end-to-end text-to-speech synthesis,\u201d arXiv preprint, 2024."},{"key":"null","unstructured":"Kaneko T., Tanaka K., Kameoka H., and Seki S., \u201cistftnet: Fast and lightweight mel-spectrogram vocoder incorporating inverse short-time fourier transform,\u201d in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), pp. 6207\u20136211, IEEE, 2022."},{"key":"null","unstructured":"Cao L. and Zhao H., \u201cA survey on visual speech synthesis with emotional expressiveness,\u201d Comput. Eng. Sci., vol. 37, no. 4, p. 813, 2015. (in Chinese)."},{"key":"null","unstructured":"Casanova E., Weber J., Shulby C. D., Junior A. C., G\u00f6lge E., and Ponti M. A., \u201cYourtts: Towards zero-shot multispeaker tts and zero-shot voice conversion for everyone,\u201d in Proc. Int. Conf. Mach. Learn., pp. 2709\u20132720, PMLR, 2022."},{"key":"null","unstructured":"Wang C., Chen S., Wu Y., Zhang Z., Zhou L., Liu S., Chen Z., Liu Y., Wang H., Li J., et al., \u201cNeural codec language models are zero-shot text to speech synthesizers,\u201d arXiv preprint, 2023."},{"key":"null","unstructured":"Chen S., Liu S., Zhou L., Liu Y., Tan X., Li J., Zhao S., Qian Y., and Wei F., \u201cVall-e 2: Neural codec language models are human parity zero-shot text to speech synthesizers,\u201d arXiv preprint, 2024."},{"key":"null","unstructured":"Ju Z., Wang Y., Shen K., Tan X., Xin D., Yang D., Liu Y., Leng Y., Song K., Tang S., et al., \u201cNaturalspeech 3: Zero-shot speech synthesis with factorized codec and diffusion models,\u201d arXiv preprint, 2024."}],"container-title":["Data Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.sciengine.com\/sci-open\/api\/v1\/open\/file\/pdf\/D27462F4F53C4A688056D79B48D672D7","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.sciengine.com\/doi\/10.3724\/2096-7004.di.2025.0128","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.sciengine.com\/sci-open\/api\/v1\/open\/file\/pdf\/D27462F4F53C4A688056D79B48D672D7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T07:56:18Z","timestamp":1781769378000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.sciengine.com\/doi\/10.3724\/2096-7004.di.2025.0128"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"references-count":22,"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.2025.0128","relation":{},"ISSN":["2096-7004"],"issn-type":[{"value":"2096-7004","type":"print"}],"subject":[],"published":{"date-parts":[[2025,9,22]]}}}