{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T15:15:18Z","timestamp":1725808518518},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"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":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10446806","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"13341-13345","source":"Crossref","is-referenced-by-count":0,"title":["Dialog Modeling in Audiobook Synthesis"],"prefix":"10.1109","author":[{"given":"Cheng-Chieh","family":"Yeh","sequence":"first","affiliation":[{"name":"Apple,USA"}]},{"given":"Amirreza","family":"Shirani","sequence":"additional","affiliation":[{"name":"Apple,USA"}]},{"given":"Weicheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Apple,USA"}]},{"given":"Tuomo","family":"Raitio","sequence":"additional","affiliation":[{"name":"Apple,USA"}]},{"given":"Ramya","family":"Rasipuram","sequence":"additional","affiliation":[{"name":"Apple,USA"}]},{"given":"Ladan","family":"Golipour","sequence":"additional","affiliation":[{"name":"Apple,USA"}]},{"given":"David","family":"Winarsky","sequence":"additional","affiliation":[{"name":"Apple,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Intl. Conf. on Learn. Represent. (ICLR)","author":"Ren","key":"ref2"},{"article-title":"Efficient neural audio synthesis","volume-title":"Intl. Conf. on Machine Learning (ICML)","author":"Kalchbrenner","key":"ref3"},{"key":"ref4","article-title":"Natural TTS synthesis by conditioning WaveNet on Mel spectrogram predictions","author":"Shen","year":"2017","journal-title":"ICASSP"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3356232\/mm1"},{"key":"ref6","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional Transformers for language understanding","volume-title":"Annual Conf. of the North American Chapter of the Assoc. for Comp. Ling.: Human Language Techn. (NAACL-HLT)","author":"Devlin"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2023-22"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50026-X"},{"volume-title":"Mean opinion score (MOS) terminology","year":"2016","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413907"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11133"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3011975"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2467"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.440"},{"article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Intl. Conf. on Machine Learning (ICML)","author":"Wang","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-638"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2469"},{"article-title":"DeBERTa: Decoding-enhanced BERT with disentangled attention","volume-title":"Intl. Conf. on Learn. Represent. (ICLR)","author":"He","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639682"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-379"},{"key":"ref22","first-page":"391","article-title":"Crossutterance conditioned VAE for non-autoregressive text-to-speech","volume-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics","author":"Li"},{"key":"ref23","article-title":"Neural voice cloning with a few samples","author":"Ar\u0131k","year":"2018","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688154"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461296"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746253"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2861"},{"volume-title":"Human-in-the-Loop Machine Learning: Active learning and annotation for human-centered AI","year":"2021","author":"Munro Monarch","key":"ref28"},{"article-title":"Revisiting distributed synchronous SGD","volume-title":"Intl. Conf. on Learn. Represent. (ICLR)","author":"Chen","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-18"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10446806.pdf?arnumber=10446806","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:45:41Z","timestamp":1722573941000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446806\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446806","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}