{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:47:36Z","timestamp":1767340056282,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,16]],"date-time":"2023-12-16T00:00:00Z","timestamp":1702684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,16]]},"DOI":"10.1109\/asru57964.2023.10389772","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-7","source":"Crossref","is-referenced-by-count":6,"title":["Promptspeaker: Speaker Generation Based on Text Descriptions"],"prefix":"10.1109","author":[{"given":"Yongmao","family":"Zhang","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanghou","family":"Liu","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Lei","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunlin","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Mobvoi Information Technology Co., Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Yin","sequence":"additional","affiliation":[{"name":"Shanghai Mobvoi Information Technology Co., Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhifei","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Mobvoi Information Technology Co., Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A survey on neural speech synthesis","volume":"abs\/2106.15561","author":"Tan","year":"2021","journal-title":"CoRR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747345"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10195"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.07.001"},{"key":"ref5","article-title":"Hierarchical text-conditional image generation with CLIP latents","volume":"abs\/2204.06125","author":"Ramesh","year":"2022","journal-title":"CoRR"},{"key":"ref6","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","volume":"abs\/2301.12503","author":"Liu","year":"2023","journal-title":"CoRR"},{"key":"ref7","article-title":"Make-an-audio: Text-toaudio generation with prompt-enhanced diffusion models","volume":"abs\/2301.12661","author":"Huang","year":"2023","journal-title":"CoRR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-465"},{"key":"ref9","article-title":"Instructtts: Modelling expressive TTS in discrete latent space with natural language style prompt","volume":"abs\/2301.13662","author":"Yang","year":"2023","journal-title":"CoRR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1779"},{"key":"ref11","article-title":"Prompttts: Controllable text-to-speech with text descriptions","volume":"abs\/2211.12171","author":"Guo","year":"2022","journal-title":"CoRR"},{"key":"ref12","first-page":"10236","article-title":"Glow: Generative flow with invertible 1x1 convolutions","volume-title":"Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018","author":"Kingma"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref14","first-page":"3165","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019","author":"Ren"},{"key":"ref15","first-page":"5167","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, July 10-15, 2018","volume":"80","author":"Wang"},{"key":"ref16","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021","volume":"139","author":"Kim"},{"key":"ref17","first-page":"2709","article-title":"Yourtts: Towards zero-shot multispeaker TTS and zero-shot voice conversion for everyone","volume-title":"International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA","volume":"162","author":"Casanova"},{"key":"ref18","first-page":"10040","article-title":"Neural voice cloning with a few samples","volume-title":"Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018","author":"\u00d6mer Arik"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-755"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414423"},{"key":"ref21","article-title":"Wespeaker: A research and production oriented speaker embedding learning toolkit","volume":"abs\/2210.17016","author":"Wang","year":"2022","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-417"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2023,12,16]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,12,20]]}},"container-title":["2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10388490\/10389614\/10389772.pdf?arnumber=10389772","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:36:38Z","timestamp":1706027798000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389772\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389772","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}