{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T10:19:14Z","timestamp":1729678754407,"version":"3.28.0"},"reference-count":11,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012,12]]},"DOI":"10.1109\/slt.2012.6424229","type":"proceedings-article","created":{"date-parts":[[2013,2,8]],"date-time":"2013-02-08T21:28:38Z","timestamp":1360358918000},"page":"240-245","source":"Crossref","is-referenced-by-count":7,"title":["What makes this voice sound so bad? A multidimensional analysis of state-of-the-art text-to-speech systems"],"prefix":"10.1109","author":[{"given":"Florian","family":"Hinterleitner","sequence":"first","affiliation":[]},{"given":"Christoph","family":"Norrenbrock","sequence":"additional","affiliation":[]},{"given":"Sebastian","family":"Moller","sequence":"additional","affiliation":[]},{"given":"Ulrich","family":"Heute","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"3","article-title":"The festival speech synthesis system: System documentation","author":"black","year":"1997","journal-title":"Tech Rep HCRC\/TR-83"},{"key":"2","first-page":"1725","article-title":"Multidimensional scaling of listener responses to synthetic speech","author":"mayo","year":"2005","journal-title":"Proceedings of the 8th Annual Conference of the International Speech Communication Association (Interspeech"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1177\/1525822X0001200104"},{"key":"1","first-page":"351","article-title":"Quality evaluation of five german speech synthesis systems","volume":"3","author":"kraft","year":"1995","journal-title":"Acta Acustica"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1007\/BF02289694"},{"journal-title":"Modern Multidimensional Scaling-Theory and Applications 2nd Edition","year":"2005","author":"borg","key":"6"},{"journal-title":"Telecommunications International","article-title":"Objective measurement of active speech level","year":"1993","key":"5"},{"key":"4","first-page":"2177","article-title":"Perceptual quality dimensions of text-to-speech systems","author":"hinterleitner","year":"2011","journal-title":"Proceedings of the 11th Annual Conference of the International Speech Communication Association (Interspeech 2010)"},{"key":"9","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316641","author":"seber","year":"1984","journal-title":"Multivariate Observations"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1207\/S15327906MBR3503_02"},{"key":"11","article-title":"Quality analysis of macroprosodic f0 dynamics in text-to-speech signals","author":"norrenbrock","year":"2012","journal-title":"Proceedings of the 11th Annual Conference of the International Speech Communication Association (Interspeech 2010)"}],"event":{"name":"2012 IEEE Spoken Language Technology Workshop (SLT 2012)","start":{"date-parts":[[2012,12,2]]},"location":"Miami, FL, USA","end":{"date-parts":[[2012,12,5]]}},"container-title":["2012 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6416134\/6424159\/06424229.pdf?arnumber=6424229","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,21]],"date-time":"2017-06-21T07:13:07Z","timestamp":1498029187000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6424229\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,12]]},"references-count":11,"URL":"https:\/\/doi.org\/10.1109\/slt.2012.6424229","relation":{},"subject":[],"published":{"date-parts":[[2012,12]]}}}