{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T04:37:33Z","timestamp":1729658253837,"version":"3.28.0"},"reference-count":44,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.23919\/apsipa.2018.8659638","type":"proceedings-article","created":{"date-parts":[[2019,3,18]],"date-time":"2019-03-18T19:11:49Z","timestamp":1552936309000},"page":"1776-1781","source":"Crossref","is-referenced-by-count":3,"title":["Novel Inter Mixture Weighted GMM Posteriorgram for DNN and GAN-based Voice Conversion"],"prefix":"10.23919","author":[{"given":"Nirmesh J.","family":"Shah","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"R.","family":"Sreeraj","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Neil","family":"Shah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hemant A.","family":"Patil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref38","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref33","first-page":"1","article-title":"Using posterior-based features in template matching for speech recognition","author":"aradilla","year":"2006","journal-title":"InterSpeech"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2017.03.004"},{"journal-title":"Design of QbE-STD system Audio representation and matching perspective","year":"2017","author":"madhavi","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372931"},{"key":"ref37","first-page":"1","article-title":"Maximum likelihood from incomplete data via the EM algorithm","volume":"39","author":"dempster","year":"1977","journal-title":"Journal of the Royal Statistical Society"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(95)00009-D"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10772-013-9217-1"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960457"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853600"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1066"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IALP.2014.6973508"},{"key":"ref12","first-page":"2254","article-title":"MAP-based adaptation for speech conversion using adaptation data selection and non-parallel training","author":"lee","year":"2006","journal-title":"InterSpeech"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953215"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"3364","DOI":"10.21437\/Interspeech.2017-63","article-title":"Voice conversion from unaligned corpora using variational autoencoding wasserstein generative adversarial networks","author":"hsu","year":"2017","journal-title":"InterSpeech"},{"key":"ref15","first-page":"1","article-title":"Voice conversion from non-parallel corpora using variational autoencoder","author":"hsu","year":"2016","journal-title":"Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA-ASC)"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"1283","DOI":"10.21437\/Interspeech.2017-970","article-title":"Sequence-to-sequence voice conversion with similarity metric learned using generative adversarial networks","author":"kaneko","year":"2017","journal-title":"InterSpeech"},{"key":"ref17","article-title":"High-quality nonparallel voice conversion based on cycle-consistent adversariel network","author":"fang","year":"2018","journal-title":"International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2761547"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1712"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178896"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016-22"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1565"},{"key":"ref3","first-page":"1","article-title":"On the impact of alignment on voice conversion performance","author":"helander","year":"2008","journal-title":"InterSpeech"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038669"},{"key":"ref29","first-page":"1","article-title":"Phonetic posterior-grams for many-to-one voice conversion without parallel data training","author":"sun","year":"2016","journal-title":"IEEE International Conference on Multimedia and Expo (ICME)"},{"key":"ref5","first-page":"299","volume":"10597","author":"shah","year":"2017","journal-title":"Analysis of features and metrics for alignment in text-dependent voice conversion"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282095"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472758"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.01.008"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1538"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960401"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462068"},{"key":"ref22","first-page":"1","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2016","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"3642","DOI":"10.21437\/Interspeech.2017-1428","article-title":"SEGAN: Speech enhancement generative adversarial network","author":"pascual","year":"2017","journal-title":"InterSpeech"},{"key":"ref42","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"1993","DOI":"10.21437\/Interspeech.2017-1465","article-title":"A fully convolutional neural network for speech enhancement","author":"park","year":"2017","journal-title":"InterSpeech"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"1809","DOI":"10.21437\/Interspeech.2011-35","article-title":"Improved HNM-based vocoder for statistical synthesizers","author":"erro","year":"2011","journal-title":"InterSpeech"},{"key":"ref23","first-page":"3642","article-title":"Conditional generative adversarial networks for speech enhancement and noise-robust speaker verification","author":"michelsanti","year":"2017","journal-title":"InterSpeech"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907344"},{"key":"ref26","article-title":"Novel mmse discogan for cross-domain whisper-to-speech conversion","author":"shah","year":"2018","journal-title":"Machine Learning in Speech and Language Processing (MLSLP) Workshop"},{"key":"ref43","first-page":"1","article-title":"ADAM: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462018"}],"event":{"name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2018,11,12]]},"location":"Honolulu, HI, USA","end":{"date-parts":[[2018,11,15]]}},"container-title":["2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8648538\/8659446\/08659638.pdf?arnumber=8659638","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T12:47:31Z","timestamp":1694695651000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8659638\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":44,"URL":"https:\/\/doi.org\/10.23919\/apsipa.2018.8659638","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}