{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T06:41:50Z","timestamp":1729665710894,"version":"3.28.0"},"reference-count":45,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1109\/asru.2015.7404783","type":"proceedings-article","created":{"date-parts":[[2016,2,12]],"date-time":"2016-02-12T13:55:42Z","timestamp":1455285342000},"page":"116-123","source":"Crossref","is-referenced-by-count":1,"title":["Speaker intonation adaptation for transforming text-to-speech synthesis speaker identity"],"prefix":"10.1109","author":[{"given":"Mahsa Sadat Elyasi","family":"Langarani","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"van Santen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"The festival speech synthesis system, version 1.4. 2","author":"black","year":"2001","journal-title":"Unpublished document available via"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"1732","DOI":"10.21437\/Interspeech.2010-497","article-title":"Text-independent f0 transformation with non-parallel data for voice conversion","author":"wu","year":"2010","journal-title":"InterSpeech"},{"key":"ref33","article-title":"F0 transformation within the voice conversion framework","author":"hanzl\u00ed?ek","year":"2007","journal-title":"InterSpeech"},{"key":"ref32","first-page":"199","article-title":"Voice conversion based on joint pitch and spectral transformation with component group-gmm","author":"ma","year":"2005","journal-title":"Natural Language Processing and Knowledge Engineering 2005 IEEE NLP-KE'05 Proceedings of 2005 IEEE International Conference on"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.09.006"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCSIT.2010.5565148"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"1394","DOI":"10.1109\/TASL.2009.2034771","article-title":"Hierarchical prosody conversion using regression-based clustering for emotional speech synthesis","volume":"18","author":"wu","year":"2010","journal-title":"Audio Speech and Language Processing IEEE Transactions on"},{"key":"ref36","article-title":"Voice conversion methods for vocal tract and pitch contour modification","author":"t\u00fcrk","year":"2003","journal-title":"InterSpeech"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638766"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2014.6936599"},{"key":"ref10","first-page":"236","article-title":"10 perception of intonation","author":"vaissi\u00e8re","year":"2008","journal-title":"The Handbook of Speech Perception"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/89.661472"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511808814"},{"key":"ref12","article-title":"Intonation, perception, and language","author":"lieberman","year":"1967","journal-title":"MIT Res Mono"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-011-4317-2_12"},{"article-title":"Intra-lingual and cross-lingual prosody modelling","year":"2013","author":"anumanchipalli","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2005.01.008"},{"key":"ref16","first-page":"161","article-title":"Toward measurement of pitch alignment","volume":"18","author":"van santen","year":"2006","journal-title":"Italian Linguistics"},{"key":"ref17","article-title":"Semi-supervised training of a voice conversion mapping function using a joint-autoencoder","author":"mohammadi","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"1506","DOI":"10.1109\/TASLP.2014.2333242","article-title":"Exemplar-based sparse representation with residual compensation for voice conversion","volume":"22","author":"wu","year":"2014","journal-title":"Audio Speech and Language Processing IEEE\/ACM Transactions on"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078543"},{"key":"ref28","article-title":"Emotional voice conversion for mandarin using tone nucleus model-small corpus and high efficiency","author":"wang","year":"2012","journal-title":"Proc Speech Prosody"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.675407"},{"key":"ref27","article-title":"A new method for pitch prediction from spectral envelope and its application in voice conversion","author":"en-najjary","year":"2003","journal-title":"InterSpeech"},{"key":"ref3","first-page":"805","article-title":"Adaptation of pitch and spectrum for hmm-based speech synthesis using mllr","volume":"2","author":"tamura","year":"2001","journal-title":"Acoustics Speech and Signal Processing 2001 Proceedings (ICASSP '01) 2001 IEEE International Conference on"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"111","DOI":"10.21437\/SpeechProsody.2008-26","article-title":"Pitch and duration transformation with non-parallel data","author":"lolive","year":"2008","journal-title":"Proc Speech Prosody 2008"},{"key":"ref29","first-page":"490","article-title":"A system for transforming the emotion in speech: combining data-driven conversion techniques for prosody and voice quality","author":"inanoglu","year":"2007","journal-title":"InterSpeech"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366961"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"2122","DOI":"10.21437\/Interspeech.2008-550","article-title":"Emotion conversion using f0 segment selection","author":"inanoglu","year":"2008","journal-title":"InterSpeech"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1109\/TASL.2006.876113","article-title":"Prosody conversion from neutral speech to emotional speech","volume":"14","author":"tao","year":"2006","journal-title":"Audio Speech and Language Processing IEEE Transactions on"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2012-151","article-title":"Synthetic f0 can effectively convey speaker id in delexicalized speech","author":"morley","year":"2012","journal-title":"InterSpeech"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"2765","DOI":"10.21437\/Interspeech.2011-692","article-title":"Intonation conversion from neutral to expressive speech","author":"veaux","year":"2011","journal-title":"InterSpeech"},{"key":"ref1","article-title":"On the importance of pure prosody in the perception of speaker identity","author":"helander","year":"2007","journal-title":"Eighth Annual Conference of the International Speech Communication Association"},{"article-title":"linguistic approach to pitch range modelling","year":"2000","author":"patterson","key":"ref20"},{"key":"ref45","article-title":"Studies in General and English Phonetics: Essays in Honour of Professor J. D. O?onnor","author":"cruttenden","year":"1995","journal-title":"Rises in English"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854067"},{"key":"ref21","first-page":"53","article-title":"A model for synthesis of pitch contours of connected speech","volume":"28","author":"fujisaki","year":"1969","journal-title":"Annual report"},{"key":"ref42","article-title":"The cmu arctic speech databases","author":"kominek","year":"2004","journal-title":"Proc Fifth ISCA Speech Synthesis Workshop"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2014.7078586"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1998.674423"},{"key":"ref23","article-title":"Data-driven foot-based intonation generator for text-to-speech synthesis","author":"elyasi langarani","year":"2015","journal-title":"InterSpeech"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639003"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"101","DOI":"10.21437\/Eurospeech.2003-74","article-title":"Transforming f0 contours","author":"gillett","year":"2003","journal-title":"Proceedings of EUROSPEECH"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1177\/1745691610393980"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638997"}],"event":{"name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","start":{"date-parts":[[2015,12,13]]},"location":"Scottsdale, AZ, USA","end":{"date-parts":[[2015,12,17]]}},"container-title":["2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7397480\/7404758\/07404783.pdf?arnumber=7404783","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T09:47:07Z","timestamp":1718358427000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7404783\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,12]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/asru.2015.7404783","relation":{},"subject":[],"published":{"date-parts":[[2015,12]]}}}