{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:04:34Z","timestamp":1761897874397,"version":"3.28.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096471","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Delivering Speaking Style in Low-Resource Voice Conversion with Multi-Factor Constraints"],"prefix":"10.1109","author":[{"given":"Zhichao","family":"Wang","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":"Xinsheng","family":"Wang","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":"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":"Yuanzhe","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance,Speech, Audio & Music Intelligence (SAMI)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiao","family":"Tian","sequence":"additional","affiliation":[{"name":"ByteDance,Speech, Audio & Music Intelligence (SAMI)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuping","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance,Speech, Audio & Music Intelligence (SAMI)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2663"},{"key":"ref12","first-page":"5210","article-title":"Autovc: Zero-shot Voice Style Transfer with Only Autoencoder Loss","author":"qian","year":"2019","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-283"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2132"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref30","first-page":"4693","article-title":"Towards End-to-end Prosody Transfer for Expressive Speech Synthesis with Tacotron","author":"skerry-ryan","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746405"},{"key":"ref10","first-page":"831","article-title":"Enriching Source Style Transfer in Recognition-synthesis based Non-parallel Voice Con- version","author":"wang","year":"2021","journal-title":"International Speech Communication Association (Inter-speech)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2412"},{"key":"ref17","first-page":"7748","article-title":"Meta-Stylespeech: Multi-speaker Adaptive Text-to-speech Generation","author":"min","year":"2021","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref16","article-title":"Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph","author":"yin","year":"2022","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref19","article-title":"TFGAN: Time and Frequency Domain based Generative Adversarial Network for High-fidelity Speech Synthesis","author":"tian","year":"2020","journal-title":"ArXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-947"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00966"},{"key":"ref23","first-page":"4006","article-title":"Tacotron: Towards End-to-End Speech Synthesis","author":"wang","year":"2017","journal-title":"International Speech Communication Association (Interspeech"},{"key":"ref26","first-page":"6182","article-title":"Wenet- speech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition","author":"zhang","year":"2022","journal-title":"International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-755"},{"key":"ref20","first-page":"1","article-title":"Generalizing from a Few Examples: A Survey on Few-shot Learning","volume":"53","author":"wang","year":"2020","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076369"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413391"},{"key":"ref8","article-title":"IQDUBBING: Prosody Modeling based on Discrete Self-supervised Speech Representation for Expressive Voice Conversion","volume":"abs 2201 269","author":"gan","year":"2022","journal-title":"ArXiv"},{"key":"ref7","article-title":"Expressive Voice Conversion: A Joint Framework for Speaker Identity and Emotional Style Transfer","volume":"abs 2107 3748","author":"zongyang","year":"2021","journal-title":"ArXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP49672.2021.9362110"},{"key":"ref4","first-page":"3364","article-title":"Voice Conversion from Unaligned Corpora Using Variational Autoencoding Wasserstein Generative Adversarial Networks","author":"hsu","year":"2017","journal-title":"International Speech Communication Association (Interspeech"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2016.7552917"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2861"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472664"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096471.pdf?arnumber=10096471","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T14:05:44Z","timestamp":1700489144000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096471\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096471","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}