{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T16:04:46Z","timestamp":1781366686691,"version":"3.54.1"},"reference-count":69,"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\/asru57964.2023.10389672","type":"proceedings-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T18:38:40Z","timestamp":1705689520000},"page":"1-8","source":"Crossref","is-referenced-by-count":4,"title":["Towards General-Purpose Text-Instruction-Guided Voice Conversion"],"prefix":"10.1109","author":[{"given":"Chun-Yi","family":"Kuan","sequence":"first","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen-An","family":"Li","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tsu-Yuan","family":"Hsu","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tse-Yang","family":"Lin","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ho-Lam","family":"Chung","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai-Wei","family":"Chang","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo-Yiin","family":"Chang","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022","journal-title":"NIPS"},{"key":"ref2","article-title":"AudioPaLM: A Large Language Model That Can Speak and Listen","author":"Rubenstein","year":"2023","journal-title":"arXiv preprint arXiv:2306.12925"},{"key":"ref3","article-title":"Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale","author":"Le","year":"2023","journal-title":"arXiv preprint arXiv:2306.15687"},{"key":"ref4","article-title":"Text-to-audio generation using instruction-tuned llm and latent diffusion model","author":"Ghosal","year":"2023","journal-title":"arXiv preprint arXiv:2304.13731"},{"key":"ref5","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","author":"Huang","year":"2023","journal-title":"arXiv preprint arXiv:2301.12661"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00618"},{"key":"ref7","article-title":"SoundStorm: Efficient Parallel Audio Generation","author":"Borsos","year":"2023"},{"key":"ref8","article-title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","author":"Wang","year":"2023"},{"key":"ref9","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv:2301.12503"},{"key":"ref10","article-title":"Speak foreign languages with your own voice: Cross-lingual neural codec language modeling","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2303.03926"},{"key":"ref11","article-title":"Simple and controllable music generation","author":"Copet","year":"2023","journal-title":"arXiv preprint arXiv:2306.05284"},{"key":"ref12","article-title":"Viola: Unified codec language models for speech recognition, synthesis, and translation","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2305.16107"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1779"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096285"},{"key":"ref15","article-title":"AudioGen: Textually Guided Audio Generation","author":"Kreuk","year":"2023","journal-title":"ICLR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2020.3038524"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-28"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.01.008"},{"key":"ref19","article-title":"Voice conversion challenge 2020: Intra-lingual semi-parallel and cross-lingual voice conversion","author":"Zhao","year":"2020","journal-title":"arXiv preprint arXiv:2008.12527"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2021.11.006"},{"key":"ref21","article-title":"High Fidelity Neural Audio Compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv preprint arXiv:2210.13438"},{"key":"ref22","article-title":"Textually Pretrained Speech Language Models","author":"Hassid","year":"2023","journal-title":"arXiv preprint arXiv:2305.13009"},{"key":"ref23","article-title":"Sox: Sound exchange","author":"Bagwell","year":"1991"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096509"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3288409"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10610"},{"key":"ref28","article-title":"Speechgen: Unlocking the generative power of speech language models with prompts","author":"Wu","year":"2023","journal-title":"arXiv preprint arXiv:2306.02207"},{"key":"ref29","article-title":"InstructTTS: Modelling Expressive TTS in Discrete Latent Space with Natural Language Style Prompt","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv:2301.13662"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5923\/j.ajsp.20120205.06"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.09.006"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2878"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.769"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-33"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054579"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tasl.2007.907344"},{"key":"ref38","article-title":"Oneshot voice conversion by separating speaker and content representations with instance normalization","author":"Chou","year":"2019","journal-title":"arXiv preprint arXiv:1904.05742"},{"key":"ref39","article-title":"Autovc: Zero-shot voice style transfer with only autoencoder loss","author":"Qian","year":"2019","journal-title":"ICLR"},{"key":"ref40","article-title":"Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations","author":"Choi","year":"2021","journal-title":"NeurlPS"},{"key":"ref41","article-title":"Yourtts: Towards zero-shot multispeaker tts and zero-shot voice conversion for everyone","author":"Casanova","year":"2022","journal-title":"ICML"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639535"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2236"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-319"},{"key":"ref46","article-title":"Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks","author":"Kaneko","year":"2017","journal-title":"arXiv preprint arXiv:1711.11293"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462342"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553236"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682897"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414851"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2280"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1830"},{"key":"ref53","article-title":"MelGAN-VC: Voice conversion and audio style transfer on arbitrarily long samples using spectrograms","author":"Pasini","year":"2019","journal-title":"arXiv preprint arXiv:1910.03713"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2016.7820786"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-63"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2018.8706604"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2917232"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054582"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054734"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1356"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413699"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747434"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn55064.2022.9892405"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746430"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415079"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-475"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-299"}],"event":{"name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Taipei, Taiwan","start":{"date-parts":[[2023,12,16]]},"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\/10389672.pdf?arnumber=10389672","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,23]],"date-time":"2024-01-23T16:42:34Z","timestamp":1706028154000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10389672\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,16]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/asru57964.2023.10389672","relation":{},"subject":[],"published":{"date-parts":[[2023,12,16]]}}}