{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T16:26:59Z","timestamp":1779208019821,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,8,20]],"date-time":"2020-08-20T00:00:00Z","timestamp":1597881600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China","award":["61822203 61772297 61632016 61761146003"],"award-info":[{"award-number":["61822203 61772297 61632016 61761146003"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,8,23]]},"DOI":"10.1145\/3394486.3403331","type":"proceedings-article","created":{"date-parts":[[2020,8,20]],"date-time":"2020-08-20T23:03:57Z","timestamp":1597964637000},"page":"2802-2812","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":52,"title":["LRSpeech"],"prefix":"10.1145","author":[{"given":"Jin","family":"Xu","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu","family":"Tan","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Ren","sequence":"additional","affiliation":[{"name":"Zhejiang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Qin","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sheng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Microsoft Azure Speech, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tie-Yan","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,8,20]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"On the cross-lingual transferability of monolingual representations. arXiv preprint arXiv:1910.11856","author":"Artetxe Mikel","year":"2019","unstructured":"Mikel Artetxe , Sebastian Ruder , and Dani Yogatama . 2019. On the cross-lingual transferability of monolingual representations. arXiv preprint arXiv:1910.11856 ( 2019 ). Mikel Artetxe, Sebastian Ruder, and Dani Yogatama. 2019. On the cross-lingual transferability of monolingual representations. arXiv preprint arXiv:1910.11856 (2019)."},{"key":"e_1_3_2_1_2_1","volume-title":"Effectiveness of self-supervised pre-training for speech recognition. arXiv preprint arXiv:1911.03912","author":"Baevski Alexei","year":"2019","unstructured":"Alexei Baevski , Michael Auli , and Abdelrahman Mohamed . 2019. Effectiveness of self-supervised pre-training for speech recognition. arXiv preprint arXiv:1911.03912 ( 2019 ). Alexei Baevski, Michael Auli, and Abdelrahman Mohamed. 2019. Effectiveness of self-supervised pre-training for speech recognition. arXiv preprint arXiv:1911.03912 (2019)."},{"key":"e_1_3_2_1_3_1","volume-title":"Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473","author":"Bahdanau Dzmitry","year":"2014","unstructured":"Dzmitry Bahdanau , Kyunghyun Cho , and Yoshua Bengio . 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 ( 2014 ). Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2061"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/292"},{"key":"e_1_3_2_1_8_1","volume-title":"Towards Unsupervised Automatic Speech Recognition Trained by Unaligned Speech and Text only. arXiv preprint arXiv:1803.10952","author":"Chen Yi-Chen","year":"2018","unstructured":"Yi-Chen Chen , Chia-Hao Shen , Sung-Feng Huang , and Hung-yi Lee. 2018. Towards Unsupervised Automatic Speech Recognition Trained by Unaligned Speech and Text only. arXiv preprint arXiv:1803.10952 ( 2018 ). Yi-Chen Chen, Chia-Hao Shen, Sung-Feng Huang, and Hung-yi Lee. 2018. Towards Unsupervised Automatic Speech Recognition Trained by Unaligned Speech and Text only. arXiv preprint arXiv:1803.10952 (2018)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2730"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"e_1_3_2_1_11_1","volume-title":"NIPS 2014 Workshop on Deep Learning","author":"Chorowski Jan","year":"2014","unstructured":"Jan Chorowski , Dzmitry Bahdanau , Kyunghyun Cho , and Yoshua Bengio . 2014 . End-to-end continuous speech recognition using attention-based recurrent nn: First results . In NIPS 2014 Workshop on Deep Learning , December 2014. Jan Chorowski, Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. End-to-end continuous speech recognition using attention-based recurrent nn: First results. In NIPS 2014 Workshop on Deep Learning, December 2014."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683862"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2018-140"},{"key":"e_1_3_2_1_15_1","unstructured":"Joel Harband. 2010. Text-to-Speech Costs - Licensing and Pricing. http:\/\/elearningtech.blogspot.com\/2010\/11\/text-to-speech-costs-licensing-and.html  Joel Harband. 2010. Text-to-Speech Costs - Licensing and Pricing. http:\/\/elearningtech.blogspot.com\/2010\/11\/text-to-speech-costs-licensing-and.html"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683307"},{"key":"e_1_3_2_1_17_1","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\/."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1139"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2007.2154"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.15388\/Informatica.2018.177"},{"key":"e_1_3_2_1_21_1","volume-title":"Ethnologue: Languages of the World","author":"Paul Lewis M","year":"2015","unstructured":"M Paul Lewis and F Gary . 2013. Simons, and Charles D. Fennig (eds.) .( 2015 ). Ethnologue: Languages of the World , Dallas, Texas : SIL International. Online version: http:\/\/www. ethnologue. com (2013). M Paul Lewis and F Gary. 2013. Simons, and Charles D. Fennig (eds.).(2015). Ethnologue: Languages of the World, Dallas, Texas: SIL International. Online version: http:\/\/www. ethnologue. com (2013)."},{"key":"e_1_3_2_1_22_1","unstructured":"Naihan Li Shujie Liu Yanqing Liu Sheng Zhao Ming Liu and M Zhou. 2019. Neural Speech Synthesis with Transformer Network. AAAI.  Naihan Li Shujie Liu Yanqing Liu Sheng Zhao Ming Liu and M Zhou. 2019. Neural Speech Synthesis with Transformer Network. AAAI."},{"key":"e_1_3_2_1_23_1","volume-title":"Towards Unsupervised Speech Recognition and Synthesis with Quantized Speech Representation Learning. arXiv preprint arXiv:1910.12729","author":"Liu Alexander H","year":"2019","unstructured":"Alexander H Liu , Tao Tu , Hung-yi Lee, and Lin-shan Lee. 2019. Towards Unsupervised Speech Recognition and Synthesis with Quantized Speech Representation Learning. arXiv preprint arXiv:1910.12729 ( 2019 ). Alexander H Liu, Tao Tu, Hung-yi Lee, and Lin-shan Lee. 2019. Towards Unsupervised Speech Recognition and Synthesis with Quantized Speech Representation Learning. arXiv preprint arXiv:1910.12729 (2019)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1800"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"e_1_3_2_1_28_1","volume-title":"International Conference on Learning Representations.","author":"Ping Wei","year":"2018","unstructured":"Wei Ping , Kainan Peng , Andrew Gibiansky , Sercan O. Arik , Ajay Kannan , Sharan Narang , Jonathan Raiman , and John Miller . 2018 . Deep Voice 3: 2000-Speaker Neural Text-to-Speech . In International Conference on Learning Representations. Wei Ping, Kainan Peng, Andrew Gibiansky, Sercan O. Arik, Ajay Kannan, Sharan Narang, Jonathan Raiman, and John Miller. 2018. Deep Voice 3: 2000-Speaker Neural Text-to-Speech. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2025"},{"key":"e_1_3_2_1_30_1","unstructured":"Yi Ren Yangjun Ruan Xu Tan Tao Qin Sheng Zhao Zhou Zhao and Tie-Yan Liu. 2019 a. Fastspeech: Fast robust and controllable text to speech. In Advances in Neural Information Processing Systems. 3165--3174.  Yi Ren Yangjun Ruan Xu Tan Tao Qin Sheng Zhao Zhou Zhao and Tie-Yan Liu. 2019 a. Fastspeech: Fast robust and controllable text to speech. In Advances in Neural Information Processing Systems. 3165--3174."},{"key":"e_1_3_2_1_31_1","volume-title":"International Conference on Machine Learning. 5410--5419","author":"Ren Yi","year":"2019","unstructured":"Yi Ren , Xu Tan , Tao Qin , Sheng Zhao , Zhou Zhao , and Tie-Yan Liu . 2019 b. Almost Unsupervised Text to Speech and Automatic Speech Recognition . In International Conference on Machine Learning. 5410--5419 . Yi Ren, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, and Tie-Yan Liu. 2019 b. Almost Unsupervised Text to Speech and Automatic Speech Recognition. In International Conference on Machine Learning. 5410--5419."},{"key":"e_1_3_2_1_32_1","volume-title":"Speech Recognition with Augmented Synthesized Speech. arXiv preprint arXiv:1909.11699","author":"Rosenberg Andrew","year":"2019","unstructured":"Andrew Rosenberg , Yu Zhang , Bhuvana Ramabhadran , Ye Jia , Pedro Moreno , Yonghui Wu , and Zelin Wu. 2019. Speech Recognition with Augmented Synthesized Speech. arXiv preprint arXiv:1909.11699 ( 2019 ). Andrew Rosenberg, Yu Zhang, Bhuvana Ramabhadran, Ye Jia, Pedro Moreno, Yonghui Wu, and Zelin Wu. 2019. Speech Recognition with Augmented Synthesized Speech. arXiv preprint arXiv:1909.11699 (2019)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1009"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1208"},{"key":"e_1_3_2_1_37_1","volume-title":"Multilingual Neural Machine Translation with Knowledge Distillation. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=S1gUsoR9YX","author":"Tan Xu","year":"2019","unstructured":"Xu Tan , Yi Ren , Di He , Tao Qin , and Tie-Yan Liu . 2019 . Multilingual Neural Machine Translation with Knowledge Distillation. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=S1gUsoR9YX Xu Tan, Yi Ren, Di He, Tao Qin, and Tie-Yan Liu. 2019. Multilingual Neural Machine Translation with Knowledge Distillation. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=S1gUsoR9YX"},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the 6th Workshop on South and Southeast Asian Natural Language Processing (WSSANLP2016)","author":"Thu Ye Kyaw","year":"2016","unstructured":"Ye Kyaw Thu , Win Pa Pa , Yoshinori Sagisaka , and Naoto Iwahashi . 2016 . Comparison of grapheme-to-phoneme conversion methods on a myanmar pronunciation dictionary . In Proceedings of the 6th Workshop on South and Southeast Asian Natural Language Processing (WSSANLP2016) . 11--22. Ye Kyaw Thu, Win Pa Pa, Yoshinori Sagisaka, and Naoto Iwahashi. 2016. Comparison of grapheme-to-phoneme conversion methods on a myanmar pronunciation dictionary. In Proceedings of the 6th Workshop on South and Southeast Asian Natural Language Processing (WSSANLP2016). 11--22."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268950"},{"key":"e_1_3_2_1_40_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 5998--6008.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 5998--6008."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"e_1_3_2_1_42_1","volume-title":"The evolutionary history of the human speech organs. Studies in language origins","author":"Wind Jan","year":"1989","unstructured":"Jan Wind . 1989. The evolutionary history of the human speech organs. Studies in language origins , Vol. 1 ( 1989 ), 173--197. Jan Wind. 1989. The evolutionary history of the human speech organs. Studies in language origins, Vol. 1 (1989), 173--197."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.5555\/2209804.2210265"},{"key":"e_1_3_2_1_44_1","volume-title":"Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram. arXiv preprint arXiv:1910.11480","author":"Yamamoto Ryuichi","year":"2019","unstructured":"Ryuichi Yamamoto , Eunwoo Song , and Jae-Min Kim . 2019. Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram. arXiv preprint arXiv:1910.11480 ( 2019 ). Ryuichi Yamamoto, Eunwoo Song, and Jae-Min Kim. 2019. Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram. arXiv preprint arXiv:1910.11480 (2019)."},{"key":"e_1_3_2_1_45_1","volume-title":"Unsupervised Speech Recognition via Segmental Empirical Output Distribution Matching. ICLR","author":"Yeh Chih-Kuan","year":"2019","unstructured":"Chih-Kuan Yeh , Jianshu Chen , Chengzhu Yu , and Dong Yu. 2019. Unsupervised Speech Recognition via Segmental Empirical Output Distribution Matching. ICLR ( 2019 ). Chih-Kuan Yeh, Jianshu Chen, Chengzhu Yu, and Dong Yu. 2019. Unsupervised Speech Recognition via Segmental Empirical Output Distribution Matching. ICLR (2019)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"event":{"name":"KDD '20: The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Virtual Event CA USA","acronym":"KDD '20","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394486.3403331","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394486.3403331","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:01:49Z","timestamp":1750197709000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394486.3403331"}},"subtitle":["Extremely Low-Resource Speech Synthesis and Recognition"],"short-title":[],"issued":{"date-parts":[[2020,8,20]]},"references-count":45,"alternative-id":["10.1145\/3394486.3403331","10.1145\/3394486"],"URL":"https:\/\/doi.org\/10.1145\/3394486.3403331","relation":{},"subject":[],"published":{"date-parts":[[2020,8,20]]},"assertion":[{"value":"2020-08-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}