{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T03:40:27Z","timestamp":1725594027571},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,11,1]],"date-time":"2019-11-01T00:00:00Z","timestamp":1572566400000},"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":[[2019,11]]},"DOI":"10.1109\/apsipaasc47483.2019.9023146","type":"proceedings-article","created":{"date-parts":[[2020,3,6]],"date-time":"2020-03-06T12:03:54Z","timestamp":1583496234000},"page":"618-622","source":"Crossref","is-referenced-by-count":1,"title":["A Study on Acoustic Parameter Selection Strategies to Improve Deep Learning-Based Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Hyeonjoo","family":"Kang","sequence":"first","affiliation":[]},{"given":"Young-Sun","family":"Joo","sequence":"additional","affiliation":[]},{"given":"Inseon","family":"Jang","sequence":"additional","affiliation":[]},{"given":"Chunghyun","family":"Ahn","sequence":"additional","affiliation":[]},{"given":"Hong-Goo","family":"Kang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Acoustic theory of speech production with calculations based on X-ray studies of Russian articulations","year":"1960","author":"fant","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-23"},{"key":"ref12","first-page":"404","article-title":"Asynchronous f0 and spectrum modeling for hmm-based speech synthesis","author":"wang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-27"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.11.002"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639659"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178904"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICIS.2016.7550889"},{"journal-title":"Wavelets and Operators","year":"1992","author":"meyer","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"journal-title":"Vocal Tract Length Perturbation (VTLP) improves speech recognition","year":"2013","author":"jaitly","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861820"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953152"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854318"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639081"},{"key":"ref5","first-page":"4006","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref8","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref7","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","author":"arik","year":"0","journal-title":"Proc Neural Information Processing Systems (NIPS)"},{"key":"ref2","article-title":"Deep neural network-based statistical parametric speech synthesis system using improved time-frequency trajectory excitation model","author":"song","year":"0","journal-title":"Proc INTERSPEECH"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2819886"},{"key":"ref1","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"0","journal-title":"Proc IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref20","first-page":"iii-1139","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"0","journal-title":"Proceedings of the 30th International Conference on International Conference on Machine Learning (ICML)"},{"key":"ref22","article-title":"Optimization methods for large-scale machine learning","author":"bottou","year":"2006","journal-title":"ArXiv Preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729392"},{"key":"ref24","article-title":"Mel-generalized cepstral analysis - A unified approach to speech spectral estimation","author":"tokuda","year":"0","journal-title":"Proc International Conference on Spoken Language Processing (ICSLP 94)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163899"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"}],"event":{"name":"2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2019,11,18]]},"location":"Lanzhou, China","end":{"date-parts":[[2019,11,21]]}},"container-title":["2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8989870\/9023008\/09023146.pdf?arnumber=9023146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T17:48:19Z","timestamp":1658080099000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9023146\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc47483.2019.9023146","relation":{},"subject":[],"published":{"date-parts":[[2019,11]]}}}