{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:13:51Z","timestamp":1740100431184,"version":"3.37.3"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:00:00Z","timestamp":1634688000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:00:00Z","timestamp":1634688000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:00:00Z","timestamp":1634688000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003696","name":"Electronics and Telecommunications Research Institute(ETRI) grant funded by the Korean government","doi-asserted-by":"publisher","award":["21ZS1100"],"id":[{"id":"10.13039\/501100003696","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,10,20]]},"DOI":"10.1109\/ictc52510.2021.9621175","type":"proceedings-article","created":{"date-parts":[[2021,12,7]],"date-time":"2021-12-07T20:49:57Z","timestamp":1638910197000},"page":"343-347","source":"Crossref","is-referenced-by-count":3,"title":["A Preliminary Study on Wav2Vec 2.0 Embeddings for Text-to-Speech"],"prefix":"10.1109","author":[{"given":"Yohan","family":"Lim","sequence":"first","affiliation":[]},{"given":"Namhyeong","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Seung","family":"Yun","sequence":"additional","affiliation":[]},{"given":"Sanghun","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Seung-Ik","family":"Lee","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Unsupervised Speech Recognition","author":"alexei","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413699"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2904"},{"key":"ref13","first-page":"6306","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"NIPS"},{"key":"ref14","article-title":"DiscreTalk: Text-to-Speech as a Machine Translation Problem","author":"tomoki","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref15","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"jacob","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref16","article-title":"Multilingual speech translation with efficient finetuning of pretrained models","author":"xian","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref17","article-title":"Exploring wav2vec 2.0 on speaker verification and language identification","author":"zhiyun","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref18","article-title":"Neural speech synthesis with transformer network","volume":"33","author":"naihan","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"journal-title":"The LJ speech dataset","year":"2017","author":"ito","key":"ref19"},{"key":"ref4","first-page":"1315","article-title":"Speech parameter generation algorithms for HMMbased speech synthesis","author":"tokuda","year":"0","journal-title":"Proc ICASSP"},{"key":"ref3","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"yi","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref6","first-page":"236","article-title":"Signal estimation from modified short-time Fourier transform","volume":"32 2","author":"daniel","year":"0","journal-title":"IEEE Transactions on Acoustics Speech and Signal Processing"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref8","article-title":"Parallel Wave-GAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram","author":"ryuichi","year":"0","journal-title":"ICASSP 2020-2020 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref7","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref2","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"yi","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref1","article-title":"Natural tts synthesis by conditioning wavenet on mel spectrogram predictions","author":"jonathan","year":"0","journal-title":"2018 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref9","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"alexei","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref20","article-title":"Espnet: End-to-end speech processing toolkit","author":"shinji","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref21","article-title":"Librispeech: an asr corpus based on public domain audio books","author":"vassil","year":"0","journal-title":"2015 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"}],"event":{"name":"2021 International Conference on Information and Communication Technology Convergence (ICTC)","start":{"date-parts":[[2021,10,20]]},"location":"Jeju Island, Korea, Republic of","end":{"date-parts":[[2021,10,22]]}},"container-title":["2021 International Conference on Information and Communication Technology Convergence (ICTC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9620727\/9620211\/09621175.pdf?arnumber=9621175","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:53:41Z","timestamp":1652201621000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9621175\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,20]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/ictc52510.2021.9621175","relation":{},"subject":[],"published":{"date-parts":[[2021,10,20]]}}}