{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,19]],"date-time":"2025-11-19T07:08:46Z","timestamp":1763536126190,"version":"3.35.0"},"reference-count":28,"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\/icassp49357.2023.10097178","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["Personalized Lightweight Text-to-Speech: Voice Cloning with Adaptive Structured Pruning"],"prefix":"10.1109","author":[{"given":"Sung-Feng","family":"Huang","sequence":"first","affiliation":[{"name":"National Taiwan University"}]},{"given":"Chia-Ping","family":"Chen","sequence":"additional","affiliation":[{"name":"Intelligo Technology Inc"}]},{"given":"Zhi-Sheng","family":"Chen","sequence":"additional","affiliation":[{"name":"Intelligo Technology Inc"}]},{"given":"Yu-Pao","family":"Tsai","sequence":"additional","affiliation":[{"name":"Intelligo Technology Inc"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","year":"2018","author":"jia","key":"ref12"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2096"},{"key":"ref14","article-title":"VoiceLoop: Voice fitting and synthesis via a phonological loop","author":"taigman","year":"2018","journal-title":"ICLRE"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414727"},{"article-title":"Adaspeech: Adaptive text to speech for custom voice","year":"2021","author":"chen","key":"ref10"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1032"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1737"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3167258"},{"key":"ref18","article-title":"Investigating on incorporating pre-trained and learnable speaker representations for multi-speaker multi-style text-to-speech","author":"chien","year":"2021","journal-title":"ICASSP"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"article-title":"Learning sparse neural networks through l_0 regularization","year":"2017","author":"louizos","key":"ref23"},{"key":"ref26","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","volume":"32","author":"kumar","year":"2019","journal-title":"Advances in neural information processing systems"},{"article-title":"CSTR VCTK Corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92), [sound]","year":"2019","author":"yamagishi","key":"ref25"},{"article-title":"Meta-voice: Fast few-shot style transfer for expressive voice cloning using meta learning","year":"2021","author":"liu","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747728"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414403"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-140"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"article-title":"Sample efficient adaptive text-to-speech","year":"2018","author":"chen","key":"ref8"},{"article-title":"Neural voice cloning with a few samples","year":"2018","author":"arik","key":"ref7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1745"},{"key":"ref4","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume":"32","author":"ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"article-title":"The lj speech dataset","year":"2017","author":"ito","key":"ref6"},{"article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","year":"2020","author":"ren","key":"ref5"}],"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\/10097178.pdf?arnumber=10097178","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T19:06:35Z","timestamp":1738263995000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10097178\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10097178","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}