{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T21:36:14Z","timestamp":1729632974898,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,1,19]]},"DOI":"10.1109\/slt48900.2021.9383507","type":"proceedings-article","created":{"date-parts":[[2021,3,25]],"date-time":"2021-03-25T20:46:54Z","timestamp":1616705214000},"page":"734-741","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Low-Quality Voice Recordings Using Disentangled Channel Factor and Neural Waveform Model"],"prefix":"10.1109","author":[{"given":"Haoyu","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Ai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2020-1613","article-title":"Reverberation modeling for source-filter-based neural vocoder","author":"ai","year":"2020"},{"key":"ref31","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.20982\/tqmp.04.1.p013"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1428","article-title":"SEGAN: Speech enhancement generative adversarial network","author":"pascual","year":"2017"},{"article-title":"Transformation of low-quality device-recorded speech to high-quality speech using improved SEGAN model","year":"2019","author":"sarfjoo","key":"ref11"},{"article-title":"Wavenet: A generative model for raw audio","year":"2016","author":"van den oord","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683654"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2143"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6489"},{"article-title":"Efficient neural audio synthesis","year":"2018","author":"kalchbrenner","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053296"},{"article-title":"Noise adaptive speech enhancement using domain adversarial training","year":"2018","author":"liao","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683561"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495701"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1979.1163209"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054701"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052251"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858531"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/11939993"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1985.1164550"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2379648"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2353991"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_11"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"7962","DOI":"10.1109\/ICASSP.2013.6639215","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"2013 IEEE International Conference on Acoustics Speech and Signal Processing"},{"article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","year":"2018","author":"wang","key":"ref20"},{"key":"ref22","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1030"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521347"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref26"},{"article-title":"Lib-riTTS: A corpus derived from LibriSpeech for text-to-speech","year":"2019","author":"zen","key":"ref25"}],"event":{"name":"2021 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2021,1,19]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,1,22]]}},"container-title":["2021 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9383468\/9383452\/09383507.pdf?arnumber=9383507","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,24]],"date-time":"2023-10-24T00:22:36Z","timestamp":1698106956000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9383507\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,19]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/slt48900.2021.9383507","relation":{},"subject":[],"published":{"date-parts":[[2021,1,19]]}}}