{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:39:41Z","timestamp":1775158781347,"version":"3.50.1"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,11,13]],"date-time":"2022-11-13T00:00:00Z","timestamp":1668297600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,11,13]],"date-time":"2022-11-13T00:00:00Z","timestamp":1668297600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1007\/s10772-022-10008-7","type":"journal-article","created":{"date-parts":[[2022,11,13]],"date-time":"2022-11-13T11:02:51Z","timestamp":1668337371000},"page":"1013-1024","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["An end-to-end TTS model with pronunciation predictor"],"prefix":"10.1007","volume":"25","author":[{"given":"Chol-Jin","family":"Han","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Un-Chol","family":"Ri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song-Il","family":"Mun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kang-Song","family":"Jang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song-Yun","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,13]]},"reference":[{"key":"10008_CR1","doi-asserted-by":"crossref","unstructured":"Achanta, S., Pandey, A., & Gangashetty, S. V. (2016). Analysis of sequence to sequence neural networks on grapheme to phoneme conversion task. In Proceedings of international joint conference on neural networks (IJCNN) (pp. 2798\u20132804).","DOI":"10.1109\/IJCNN.2016.7727552"},{"key":"10008_CR2","unstructured":"Arik, S. O., Chrzanowski, M., Coates, A., Diamos, G., Gibiansky, A., Kang, Y., Li, X., Miller, J., Ng, A., Raiman, J., Sengupta, S., & Shoeybi, M. (2017). Deep voice: Real-time neural text-to-speech. In Proceeedings of international conference on machine learning (ICML) (pp. 195\u2013204)."},{"key":"10008_CR3","unstructured":"Beliaev, S., Rebryk, Y., & Ginsburg, B. (2020). TalkNet: Fully-convolutional non-autoregressive speech synthesis model. arXiv preprint arXiv:2005.05514"},{"key":"10008_CR4","unstructured":"Gibiansky, A., Arik, S., Diamos, G., Miller, J., Peng, K., Ping, W., Raiman, J., & Zhou, Y. (2017). Deep voice 2: Multi-speaker neural text-to-speech. In Advances in neural information processing systems (pp. 2962\u20132970)."},{"issue":"2","key":"10008_CR5","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1109\/TASSP.1984.1164317","volume":"32","author":"D Griffin","year":"1984","unstructured":"Griffin, D., & Lim, J. (1984). Signal estimation from modified short-time fourier transform. IEEE Transactions on Acoustics, Speech, and Signal Processing, 32(2), 236\u2013243.","journal-title":"IEEE Transactions on Acoustics, Speech, and Signal Processing"},{"key":"10008_CR6","doi-asserted-by":"crossref","unstructured":"Hunt, A. J., & Black, A. W. (1996). Unit selection in a concatenative speech synthesis system using a large speech database. In Proceedings of international conference on acoustics, speech and signal processing (ICASSP 1996) (pp. 373\u2013376).","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"10008_CR7","unstructured":"Kalchbrenner, N., Elsen, E., Simonyan K., Noury, S., Casagrande, N., Lockhart, E., Stimberg, F., van den Oord, A., Dieleman, S., & Kavukcuoglu, K. (2018). Efficient neural audio synthesis. In Proceedings of international conference on machine learning (ICML) (pp. 2415\u20132424)."},{"key":"10008_CR8","unstructured":"Kingma, D., & Ba, J. (2015). Adam: A method for stochastic optimization. In Proceedings of international conference on learning representations (ICLR)."},{"key":"10008_CR9","unstructured":"Kumar, K., Kumar, R., Boissiere, T., Gestin, L., Teoh, W.Z., Sotelo, J., Brebisson, A., Bengio, Y., & Courville, A.C. (2019). Melgan: Generative adversarial networks for conditional waveform synthesis. In Advances in neural information processing systems (pp. 14881\u201314892)."},{"key":"10008_CR10","doi-asserted-by":"crossref","unstructured":"\u0141ancucki, A. (2020). Fastpitch: Parallel text-to-speech with pitch prediction. arXiv preprint arXiv:2006.06873","DOI":"10.1109\/ICASSP39728.2021.9413889"},{"key":"10008_CR12","doi-asserted-by":"crossref","unstructured":"Li, J., Wu, Z., Li, R., Zhi, P., Yang, S., & Meng, H. (2019a). Knowledge-based linguistic encoding for end-to-end mandarin text-to-speech synthesis. In Proceedings of Interspeech (pp. 4494\u20134498).","DOI":"10.21437\/Interspeech.2019-1118"},{"key":"10008_CR11","doi-asserted-by":"crossref","unstructured":"Li, N., Liu, S., Liu, Y., Zhao, S., & Liu, M. (2019b). Neural speech synthesis with transformer network. In Proceedings of the AAAI conference on artificial intelligence, Vol. 33, (pp. 6706\u20136713).","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"10008_CR13","doi-asserted-by":"crossref","unstructured":"Miao, C., Liang, S., Chen, M., Ma, J., Wang, S., & Xiao, J. (2020). Flowtts: A non-autoregressive network for text to speech based on flow. In Proceedings of international conference on acoustics, speech and signal processing (ICASSP 2020) (pp. 7209\u20137213).","DOI":"10.1109\/ICASSP40776.2020.9054484"},{"issue":"7","key":"10008_CR14","doi-asserted-by":"publisher","first-page":"1877","DOI":"10.1587\/transinf.2015EDP7457","volume":"99","author":"M Morise","year":"2016","unstructured":"Morise, M., Yokomori, F., & Ozawa, K. (2016). WORLD: A vocoder-based high-quality speech synthesis system for real-time applications. IEICE Transactions on Information and Systems, 99(7), 1877\u20131884.","journal-title":"IEICE Transactions on Information and Systems"},{"key":"10008_CR15","unstructured":"Oord, A. V. D., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., & Kavukcuoglu, K. (2016). WaveNet: A generative model for raw audio. In 9th ISCA speech synthesis workshop (pp. 125\u2013125)."},{"key":"10008_CR16","unstructured":"Peng, K., Ping, W., Song, Z., & Zhao, K. (2020). Non-autoregressive neural text-to-speech. In Proceedings of international conference on machine learning (ICML) (pp. 10192\u201310204)."},{"key":"10008_CR18","unstructured":"Ping, W., Peng, K., & Chen, J. (2019). Clarinet: Parallel wave generation in end-to-end text-tospeech. In Proceedings of international conference on learning representations (ICLR)."},{"key":"10008_CR17","unstructured":"Ping, W., Peng, K., Gibiansky, A., Arik, S. O., Kannan, A., Narang, S., Raiman, J., & Miller, J. (2018). Deep voice 3: 2000-speaker neural text-to-speech. In Proceedings of international conference on learning representations (ICLR)."},{"key":"10008_CR19","doi-asserted-by":"crossref","unstructured":"Prenger, R., Valle, R., & Catanzaro, B. (2019). Waveglow: A flow-based generative network for speech synthesis. In Proceedings of international conference on acoustics, speech and signal processing (ICASSP 2019) (pp. 3617\u20133621).","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"10008_CR21","unstructured":"Ren, Y., Hu, C., Qin, T., Zhao, S., Zhao, Z., & Liu, T. (2020). Fastspeech 2: Fast and high-quality end-to-end text-to-speech. arXiv preprint arXiv:2006.04558"},{"key":"10008_CR20","unstructured":"Ren, Y., Ruan, Y., Tan, X., Qin, T., Zhao, S., Zhao, Z., & Liu, T. (2019). Fastspeech: Fast, robust and controllable text to speech. In Advances in neural information processing systems (pp. 3165\u20133174)."},{"key":"10008_CR22","doi-asserted-by":"crossref","unstructured":"Shen, J., Pang, R., Weiss, R.J., Schuster, M., Jaitly, N., Yang, Z., Chen, Z., Zhang, Y., Wang, Y., et al. (2018). Natural tts synthesis by conditioning wavenet on mel spectrogram predictions. In Proceedings of international conference on acoustics, speech and signal processing (ICASSP 2018) (pp. 4779\u20134783).","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"10008_CR23","unstructured":"Sotelo, J., Mehri, S., Kumar, K., Santos, J. F., Kastner, K., Courville, A., & Bengio, Y. (2017). Char2wav: End-to-end speech synthesis. In Proceedings of international conference on learning representations (ICLR) (pp. 24\u201326)."},{"key":"10008_CR24","doi-asserted-by":"crossref","unstructured":"Taylor, J., & Richmond K. (2019). Analysis of pronunciation learning in end-to-end speech synthesis. In Proceedings of Interspeech (pp. 2070\u20132074).","DOI":"10.21437\/Interspeech.2019-2830"},{"key":"10008_CR25","unstructured":"Valle, R., Shih, K. J., Prenger, R., & Catanzaro, B. (2021). Flowtron: an autoregressive flow-based generative network for text-to-speech synthesis. In Proceedings of international conference on learning representations (ICLR)."},{"key":"10008_CR26","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, \u0141., & Polosukhin, I. (2017). Attention is all you need. In Advances in neural information processing systems (pp. 5998\u20136008)."},{"key":"10008_CR27","doi-asserted-by":"crossref","unstructured":"Wang, Y., Skerry-Ryan, R., Stanton, D., Wu, Y., Weiss, R.J., Jaitly, N., Yang, Z., Xiao, Y., Chen, Z., Bengio, S., Le, Q., Agiomyrgiannakis, Y., Clark, R., & Saurous, R. A. (2017). Tacotron: Towards end-to-end speech synthesis. In Proceedings of Interspeech (pp. 4006\u20134010).","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"10008_CR28","doi-asserted-by":"crossref","unstructured":"Yang, G., Yang, S., Liu, K., Fang, P., Chen, W., & Xie, L. (2020). Multi-band MelGAN: Faster waveform generation for high-quality text-to-speech. arXiv preprint, arXiv:2005.05106.","DOI":"10.1109\/SLT48900.2021.9383551"},{"key":"10008_CR29","doi-asserted-by":"crossref","unstructured":"Yao, K., & Zweig, G. (2015). Sequence-to-sequence neural net models for grapheme-to-phoneme conversion. In Proceedings of Interspeech (pp. 3330\u20133334).","DOI":"10.21437\/Interspeech.2015-134"},{"key":"10008_CR30","doi-asserted-by":"crossref","unstructured":"Zen, H., Senior, A., & Schuster, M. (2013). Statistical parametric speech synthesis using deep neural networks. In Proceedings of international conference on acoustics, speech and signal processing (ICASSP 2013) (pp. 7962\u20137966).","DOI":"10.1109\/ICASSP.2013.6639215"},{"issue":"11","key":"10008_CR31","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.1016\/j.specom.2009.04.004","volume":"51","author":"H Zen","year":"2009","unstructured":"Zen, H., Tokuda, K., & Black, A. W. (2009). Statistical parametric speech synthesis. Speech Communication, 51(11), 1039\u20131064.","journal-title":"Speech Communication"},{"key":"10008_CR32","doi-asserted-by":"crossref","unstructured":"Zeng, Z., Wang, J., Cheng, N., Xia, T., & Xiao, J. (2020). Aligntts: Efficient feed-forward text-to-speech system without explicit alignment. In Proceedings of international conference on acoustics, speech and signal processing (ICASSP 2020) (pp. 6714\u20136718).","DOI":"10.1109\/ICASSP40776.2020.9054119"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-022-10008-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-022-10008-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-022-10008-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T11:19:43Z","timestamp":1670843983000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-022-10008-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,13]]},"references-count":32,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["10008"],"URL":"https:\/\/doi.org\/10.1007\/s10772-022-10008-7","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,13]]},"assertion":[{"value":"7 November 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 October 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 November 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"There are no our items corresponding with the guideline.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}}]}}