{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T05:40:01Z","timestamp":1725774001161},"reference-count":21,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1109\/icassp.2016.7472757","type":"proceedings-article","created":{"date-parts":[[2016,6,24]],"date-time":"2016-06-24T01:58:30Z","timestamp":1466733510000},"page":"5640-5644","source":"Crossref","is-referenced-by-count":12,"title":["Directly modeling voiced and unvoiced components in speech waveforms by neural networks"],"prefix":"10.1109","author":[{"given":"Keiichi","family":"Tokuda","sequence":"first","affiliation":[]},{"given":"Heiga","family":"Zen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E97.D.1438"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178765"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/89.482216"},{"journal-title":"Descrete-time Signal Processing","year":"1989","author":"oppenhem","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178816"},{"year":"2015","key":"ref15","article-title":"REAPER: Robust Epoch And Pitch EstimatoR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638312"},{"key":"ref17","article-title":"Long short-term memory recurrent neural network architectures for large scale acoustic modeling","author":"sak","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref18","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv preprint arXiv 1412 6980"},{"key":"ref19","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","author":"duchi","year":"2011","journal-title":"The Journal of Machine Learning Research"},{"key":"ref4","first-page":"2347","article-title":"Simultaneous modeling of spectrum, pitch and duration in HMM -based speech synthesis","author":"yoshimura","year":"1999","journal-title":"Proc EUROSPEECH"},{"key":"ref3","first-page":"13","article-title":"Aperiodicity extraction and control using mixed mode excitation and group delay manipulation for a high quality speech analysis, modification and synthesis system straight","author":"kawahara","year":"2001","journal-title":"Proc MAVEBA"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref5","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"Proc ICASSP"},{"key":"ref8","first-page":"3925","article-title":"Statistical approach to vocal tract transfer function estimation based on factor analyzed trajectory hmm","author":"toda","year":"2008","journal-title":"Proc ICASSP"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"577","DOI":"10.21437\/Interspeech.2008-170","article-title":"Minimum generation error training with direct log spectral distortion on LSPs for HMM -based speech synthesis","author":"wu","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1121\/1.1995189"},{"key":"ref1","first-page":"203","article-title":"Unbiased estimation of log spectrum","author":"imai","year":"1988","journal-title":"Proc EURASIP"},{"key":"ref9","first-page":"88","article-title":"Statistical parametric speech synthesis with joint estimation of acoustic and excitation model parameters","author":"maia","year":"2010","journal-title":"Proc ISCA SSW7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1990.2.4.490"},{"key":"ref21","article-title":"Improving neural networks by preventing co-adaptation of feature detectors","author":"hinton","year":"2012","journal-title":"arXiv preprint arXiv 1207 0580"}],"event":{"name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2016,3,20]]},"location":"Shanghai","end":{"date-parts":[[2016,3,25]]}},"container-title":["2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7465907\/7471614\/07472757.pdf?arnumber=7472757","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T21:27:13Z","timestamp":1718659633000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7472757\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp.2016.7472757","relation":{},"subject":[],"published":{"date-parts":[[2016,3]]}}}