{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T04:24:09Z","timestamp":1751430249752,"version":"3.41.0"},"reference-count":43,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/apsipa.2017.8282289","type":"proceedings-article","created":{"date-parts":[[2018,2,14]],"date-time":"2018-02-14T20:31:33Z","timestamp":1518640293000},"page":"1547-1555","source":"Crossref","is-referenced-by-count":9,"title":["A dual alignment scheme for improved speech-to-singing voice conversion"],"prefix":"10.1109","author":[{"given":"Karthika","family":"Vijayan","sequence":"first","affiliation":[]},{"given":"Minghui","family":"Dong","sequence":"additional","affiliation":[]},{"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"514","article-title":"Pitch track target deviation in natural singing","author":"gerhard","year":"2005","journal-title":"ISMIR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2594282"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1180639.1180777"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288920"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2010.5582961"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.21437\/ICSLP.2000-581","article-title":"Investigation of analysis and synthesis parameters of straight by subjective evaluation","author":"zolfaghari","year":"2000","journal-title":"ICSLP"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74048-3"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1978.1163055"},{"key":"ref34","article-title":"Segmentation of speech signals in template-based speech to singing conversion","author":"cen","year":"2011","journal-title":"Asia-Pacific Signal and Information Processing Association Annual Summit and Conference"},{"key":"ref10","first-page":"1141","article-title":"Discrimination between singing and speaking voices","author":"ohishi","year":"2005","journal-title":"Eurospeech"},{"key":"ref40","article-title":"Montreal forced aligner: an accurate and trainable aligner using Kaldi","author":"michael","year":"2017","journal-title":"Annual Meeting of the Linguistic Society of America"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2006.38"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"359","DOI":"10.21437\/Interspeech.2013-100","article-title":"Factored maximum likelihood kernelized regression for HMM-based singing voice synthesis","author":"sung","year":"2013","journal-title":"InterSpeech"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853599"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2015.04.001"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2041386"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"2598","DOI":"10.21437\/Interspeech.2010-254","article-title":"Statistical modeling of f0 dynamics in singing voices based on gaussian processes with multiple oscillation bases","author":"ohishi","year":"2010","journal-title":"InterSpeech"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISSPIT.2010.5711772"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2436345"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1997.599668"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846338"},{"key":"ref4","first-page":"21","article-title":"The level of the ‘singing formant’ and the source spectra of professional bass singers","volume":"11","author":"sundberg","year":"1970","journal-title":"STL-Quarterly Progress and Status Report"},{"key":"ref27","first-page":"2754","article-title":"Statis-tical singing voice conversion based on direct waveform modification with global variance","author":"kobayashi","year":"2015","journal-title":"InterSpeech"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1121\/1.402929"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1250\/ast.7.303"},{"key":"ref29","article-title":"Speech synthesis perfects everyone's singing","author":"dong","year":"2014","journal-title":"IEEE Signal Processing Society - STLC Newsletter"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0892-1997(05)80108-0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1155\/S1110865704401127"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S0892-1997(01)00049-2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495212"},{"key":"ref9","first-page":"121","article-title":"Sectrally estimated vocal tract lengths of singing voices and their contributing factor","author":"sakaguchi","year":"2013","journal-title":"Proc MAVEBA"},{"key":"ref1","first-page":"2148","article-title":"I2R speech2singing perfects everyone's singing","author":"dong","year":"2014","journal-title":"InterSpeech"},{"key":"ref20","first-page":"4009","article-title":"Vocaloid-commercial singing synthesizer based on sample concatenation","author":"kenmochi","year":"2007","journal-title":"InterSpeech"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2007.323266"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"2162","DOI":"10.21437\/Interspeech.2010-596","article-title":"Applying voice conversion to concate-native singing-voice synthesis","author":"villavicencio","year":"2010","journal-title":"InterSpeech"},{"key":"ref42","article-title":"The SOLAFS time-scale modification algorithm","author":"hejna","year":"1991","journal-title":"BBN Technical Report"},{"key":"ref24","first-page":"4005","article-title":"Vocal conversion from speaking voice to singing voice using straight","author":"saitou","year":"2007","journal-title":"InterSpeech"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/NCC.2015.7084926"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ASPAA.2007.4393001"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"2514","DOI":"10.21437\/Interspeech.2014-539","article-title":"Statistical singing voice conversion with direct waveform modification based on the spectrum differential","author":"kobayashi","year":"2014","journal-title":"InterSpeech"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.4337\/9781781003152.00014"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"2001","DOI":"10.21437\/Interspeech.2011-526","article-title":"Singing voice synthesis: Singer-dependent vibrato modeling and coherent processing of spectral envelope","author":"lee","year":"2011","journal-title":"InterSpeech"}],"event":{"name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2017,12,12]]},"location":"Kuala Lumpur","end":{"date-parts":[[2017,12,15]]}},"container-title":["2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8270695\/8281978\/08282289.pdf?arnumber=8282289","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T21:05:18Z","timestamp":1751403918000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8282289\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/apsipa.2017.8282289","relation":{},"subject":[],"published":{"date-parts":[[2017,12]]}}}