{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T09:50:09Z","timestamp":1729677009243,"version":"3.28.0"},"reference-count":45,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/globalsip.2014.7032186","type":"proceedings-article","created":{"date-parts":[[2015,2,11]],"date-time":"2015-02-11T17:25:53Z","timestamp":1423675553000},"page":"592-596","source":"Crossref","is-referenced-by-count":12,"title":["Augmented speech production based on real-time statistical voice conversion"],"prefix":"10.1109","author":[{"given":"Tomoki","family":"Toda","sequence":"first","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"2505","volume":"20","author":"toda","year":"2012","journal-title":"Statistical voice conversion techniques for body-conducted unvoiced speech enhancement"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e89-d.1.1"},{"key":"ref33","first-page":"3072","author":"moriguchi","year":"2013","journal-title":"A digital signal processor implementation of silent\/electrolaryngeal speech enhancement based on real-time statistical voice conversion Proc INTERSPEECH"},{"key":"ref32","first-page":"272","volume":"7","author":"gales","year":"1999","journal-title":"Semi-Tied Covariance Matrices for Hidden Markov Models"},{"key":"ref31","first-page":"187","volume":"27","author":"kawahara","year":"1999","journal-title":"Restructuring speech representations using a pitch-adaptive time-frequency smoothing and an instantaneous-frequency-based F0extraction possible role of a repetitive structure in sounds Speech Communication"},{"key":"ref30","first-page":"1076","author":"muramatsu","year":"2008","journal-title":"Low-delay voice conversion based on maximum likelihood algorithm of spectral parameter trajectory Proc INTERSPEECH"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.08.002"},{"key":"ref36","first-page":"1429","volume":"e97","author":"tanaka","year":"2014","journal-title":"A hybrid approach to electrolaryngeal speech enhancement based on noise reduction and statistical excitation generation IEICE Trans Info & Syst"},{"key":"ref35","first-page":"172","volume":"22","author":"doi","year":"2014","journal-title":"Alaryn-geal speech enhancement based on one-to-many eigenvoice conversion"},{"key":"ref34","first-page":"1249","author":"toda","year":"2007","journal-title":"One-to-many and many-to-one voice conversion based on eigenvoices Proc ICASSP"},{"key":"ref10","first-page":"922","volume":"18","author":"erro","year":"2010","journal-title":"Voice conversion based on weighted frequency warping"},{"key":"ref40","first-page":"2158","author":"ohta","year":"2010","journal-title":"Adaptive voice-quality control based on one-to-many eigenvoice conversion Proc INTERSPEECH"},{"key":"ref11","first-page":"1946","volume":"e96","author":"takashima","year":"2013","journal-title":"Exemplar-based voice conversion using sparse representation in noisy environments IEICE Trans Fundamentals"},{"key":"ref12","first-page":"1506","volume":"22","author":"wu","year":"2014","journal-title":"Exemplar-based sparse representation with residual compensation for voice conversion"},{"key":"ref13","first-page":"76","volume":"90","author":"abe","year":"1991","journal-title":"Statistical analysis of bilingual speaker's speech for cross-language voice conversion J Acoust Soc Am"},{"key":"ref14","first-page":"1234","volume":"101","author":"tokuda","year":"2013","journal-title":"Speech ynthesis based on hidden Markov models Proceedings of the IEEE"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1016\/j.specom.2009.04.004","volume":"51","author":"zen","year":"2009","journal-title":"Statistical parametric speech synhesis Speech Communication"},{"key":"ref16","first-page":"291","volume":"2","author":"gauvain","year":"1994","journal-title":"Maximum a posteriori algorithm for multivariate Gaussian mixture observations of Markov chains"},{"key":"ref17","first-page":"75","volume":"12","author":"gales","year":"1998","journal-title":"Maximum likelihood linear transformations for HMM-based speech recognition Computer Speech & Language"},{"key":"ref18","first-page":"695","volume":"8","author":"kuhn","year":"2000","journal-title":"Rapid speaker adaptation in eigenvoice space"},{"key":"ref19","first-page":"533","volume":"e90","author":"yamagishi","year":"2007","journal-title":"Average-voice-based speech synhesis using HSMM-based speaker adaptation and adaptive training IEICE Trans Inf & Syst"},{"key":"ref28","first-page":"285","author":"kain","year":"1998","journal-title":"Spectral voice conversion for text-to-speech ynthesis Proc ICASSP"},{"journal-title":"Proc INTERSPEECH","year":"2012","author":"toda","key":"ref4"},{"key":"ref27","first-page":"215","volume":"50","author":"toda","year":"2008","journal-title":"Statistical mapping between articulatory movements and acoustic spectrum using a Gaussian mixture model Speech Communication"},{"key":"ref3","first-page":"2222","volume":"15","author":"toda","year":"2007","journal-title":"Voice conversion based on maximum likelihood algorithm of spectral parameter trajectory"},{"key":"ref6","first-page":"124","volume":"58","author":"xu","year":"2014","journal-title":"Voice conversion based on Gaussian processes by coherent and asymmetric training with limited training data"},{"key":"ref29","first-page":"1315","author":"tokuda","year":"2000","journal-title":"Speech parameter generation algorithms for HMM-based speech synthe-sis Proc ICASSP"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"2761","DOI":"10.21437\/Interspeech.2011-691","author":"pilkington","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref8","first-page":"1403","volume":"e97","author":"nakashika","year":"2014","journal-title":"Voice conversion based on speaker-dependent restricted Boltzmann machines IEICE Trans Inf & Syst"},{"key":"ref7","first-page":"207","volume":"16","author":"narendranath","year":"1995","journal-title":"Transformation of formants for voice conversion using artificial neural networks Speech communication"},{"key":"ref2","first-page":"131","volume":"6","author":"stylianou","year":"1998","journal-title":"Continuous probabilistic transform for voice conversion"},{"key":"ref9","first-page":"1859","volume":"22","author":"chen","year":"2014","journal-title":"Voice conversion using deep neural networks with layer-wise generative training IEEE\/ACM Trans Audio Speech & lang Process"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1250\/ast.11.71"},{"key":"ref20","first-page":"1406","volume":"e90","author":"nose","year":"2007","journal-title":"A style control technique for HMM-based expressive speech synhesis IEICE Trans Inf & Syst"},{"key":"ref45","first-page":"1826","author":"kameoka","year":"2013","journal-title":"Generative modeling of speech F0 contours Proc INTERSPEECH"},{"key":"ref22","first-page":"1145","volume":"14","author":"tao","year":"2006","journal-title":"Prosody conversion from neutral speech to emotional speech"},{"key":"ref21","first-page":"1109","volume":"14","author":"wu","year":"2006","journal-title":"Voice conversion using duration-embedded bi-HMMs for expressive speech ynhesis"},{"key":"ref42","first-page":"1419","volume":"e97","author":"kobayashi","year":"2014","journal-title":"Voice timbre control based on perceived age in singing voice conversion IEICE Trans Info & Syst"},{"key":"ref24","first-page":"268","volume":"51","author":"inanoglu","year":"2009","journal-title":"Data-driven emotion conversion in spoken English Speech Communication"},{"journal-title":"Singing voice conversion method based on many-to-many eigenvoice conversion and training data generation using a singing-to-singing ynthesis system Proc APSIPA ASC","year":"2012","author":"doi","key":"ref41"},{"key":"ref23","first-page":"1394","volume":"18","author":"wu","year":"2010","journal-title":"Hierarchical prosody conversion using regression-based clustering for emotional speech syntesis"},{"key":"ref44","first-page":"290","author":"takamichi","year":"2014","journal-title":"A postfilter to modify the modulation spectrum in HMM-based speech ynthesis Proc ICASSP"},{"key":"ref26","first-page":"2483","volume":"e93","author":"nose","year":"2010","journal-title":"HMM-based voice conversion using quantized F0 context IEICE Trans Inf & Syst"},{"key":"ref43","first-page":"794","volume":"20","author":"zen","year":"2012","journal-title":"Product of experts for statistical parametric speech yntesis"},{"key":"ref25","first-page":"343","author":"nakano","year":"2009","journal-title":"VocaListener a singing-to-singing ynthesis system based on iterative parameter algorithm Proc 6th Sound & Music Computing Conference"}],"event":{"name":"2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","start":{"date-parts":[[2014,12,3]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2014,12,5]]}},"container-title":["2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7010655\/7032060\/07032186.pdf?arnumber=7032186","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,29]],"date-time":"2022-04-29T07:12:59Z","timestamp":1651216379000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7032186\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/globalsip.2014.7032186","relation":{},"subject":[],"published":{"date-parts":[[2014,12]]}}}