{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:15:09Z","timestamp":1750220109214,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":8,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,6,24]],"date-time":"2022-06-24T00:00:00Z","timestamp":1656028800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,6,24]]},"DOI":"10.1145\/3548608.3559304","type":"proceedings-article","created":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T17:47:01Z","timestamp":1665769621000},"page":"774-777","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CRCTTS: Convolution-Recurrent-Convolution Text-to-Speech System"],"prefix":"10.1145","author":[{"given":"Kuo","family":"Chen","sequence":"first","affiliation":[{"name":"Key Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuebin","family":"Sun","sequence":"additional","affiliation":[{"name":"Key Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,10,14]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473","author":"Bahdanau D.","year":"2014","unstructured":"Bahdanau , D. , Cho , K. , & Bengio , Y. ( 2014 ). Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 . Bahdanau, D., Cho, K., & Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473."},{"key":"e_1_3_2_1_2_1","volume-title":"Tacotron: Towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135","author":"Wang Y.","year":"2017","unstructured":"Wang , Y. , Skerry-Ryan , R. J. , Stanton , D. , Wu , Y. , Weiss , R. J. , Jaitly , N. , ... & Saurous , R. A. ( 2017 ). Tacotron: Towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135 . Wang, Y., Skerry-Ryan, R. J., Stanton, D., Wu, Y., Weiss, R. J., Jaitly, N., ... & Saurous, R. A. (2017). Tacotron: Towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461829"},{"key":"e_1_3_2_1_4_1","volume-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning. arXiv preprint arXiv:1710.07654","author":"Ping W.","year":"2017","unstructured":"Ping , W. , Peng , K. , Gibiansky , A. , Arik , S. O. , Kannan , A. , Narang , S. , ... & Miller , J. ( 2017 ). Deep voice 3: Scaling text-to-speech with convolutional sequence learning. arXiv preprint arXiv:1710.07654 . Ping, W., Peng, K., Gibiansky, A., Arik, S. O., Kannan, A., Narang, S., ... & Miller, J. (2017). Deep voice 3: Scaling text-to-speech with convolutional sequence learning. arXiv preprint arXiv:1710.07654."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054106"},{"key":"e_1_3_2_1_7_1","volume-title":"Training very deep networks. arXiv preprint arXiv:1507.06228","author":"Srivastava R. K.","year":"2015","unstructured":"Srivastava , R. K. , Greff , K. , & Schmidhuber , J. ( 2015 ). Training very deep networks. arXiv preprint arXiv:1507.06228 . Srivastava, R. K., Greff, K., & Schmidhuber, J. (2015). Training very deep networks. arXiv preprint arXiv:1507.06228."},{"key":"e_1_3_2_1_8_1","volume-title":"The LJ Speech Dataset. https:\/\/keithito.com\/LJ-Speech-Dataset","author":"Keith Ito","year":"2017","unstructured":"Keith Ito . ( 2017 ). The LJ Speech Dataset. https:\/\/keithito.com\/LJ-Speech-Dataset . Keith Ito. (2017). The LJ Speech Dataset. https:\/\/keithito.com\/LJ-Speech-Dataset."}],"event":{"name":"ICCIR 2022: 2022 2nd International Conference on Control and Intelligent Robot","acronym":"ICCIR 2022","location":"Nanjing China"},"container-title":["Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3548608.3559304","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3548608.3559304","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:38Z","timestamp":1750183838000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3548608.3559304"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,24]]},"references-count":8,"alternative-id":["10.1145\/3548608.3559304","10.1145\/3548608"],"URL":"https:\/\/doi.org\/10.1145\/3548608.3559304","relation":{},"subject":[],"published":{"date-parts":[[2022,6,24]]},"assertion":[{"value":"2022-10-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}