{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:21:27Z","timestamp":1776885687919,"version":"3.51.2"},"reference-count":22,"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\/icassp49357.2023.10096374","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":8,"title":["PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many Mapping"],"prefix":"10.1109","author":[{"given":"Junhyeok","family":"Lee","sequence":"first","affiliation":[{"name":"MINDsLab Inc.,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seungu","family":"Han","sequence":"additional","affiliation":[{"name":"Seoul National University (SNU),Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyunjae","family":"Cho","sequence":"additional","affiliation":[{"name":"MINDsLab Inc.,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wonbin","family":"Jung","sequence":"additional","affiliation":[{"name":"MINDsLab Inc.,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746282"},{"key":"ref12","first-page":"16251","article-title":"Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representations","author":"choi","year":"2021","journal-title":"NeurIPS"},{"key":"ref15","article-title":"The LJ Speech Dataset","author":"ito","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461329"},{"key":"ref20","first-page":"852","article-title":"Alias-Free Generative Adversarial Networks","author":"karras","year":"2021","journal-title":"NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414408"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-45"},{"key":"ref10","first-page":"12104","article-title":"Training Generative Adversarial Networks with Limited Data","author":"karras","year":"2020","journal-title":"NeurIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-36"},{"key":"ref2","first-page":"14910","article-title":"MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis","author":"kumar","year":"2019","journal-title":"NeurIPS"},{"key":"ref1","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref19","first-page":"5530","article-title":"Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech","author":"kim","year":"2021","journal-title":"ICML"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref8","author":"bak","year":"2022","journal-title":"Avocodo Generative Adversarial Network for Artifact-free Vocoder"},{"key":"ref7","author":"lee","year":"2022","journal-title":"Bigvgan A universal neural vocoder with large-scale training"},{"key":"ref9","first-page":"7559","article-title":"Differentiable Augmentation for Data-Efficient GAN Training","author":"zhao","year":"2020","journal-title":"NeurIPS"},{"key":"ref4","first-page":"17022","article-title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","author":"kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1238"},{"key":"ref6","article-title":"Chunked Autoregressive GAN for Conditional Wave-form Synthesis","author":"morrison","year":"2022","journal-title":"ICLRE"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-845"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"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\/10096374.pdf?arnumber=10096374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:09:08Z","timestamp":1700507348000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096374\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096374","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}