{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T11:40:09Z","timestamp":1748778009616,"version":"3.41.0"},"reference-count":34,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1109\/asru.2015.7404782","type":"proceedings-article","created":{"date-parts":[[2016,2,12]],"date-time":"2016-02-12T13:55:42Z","timestamp":1455285342000},"page":"111-115","source":"Crossref","is-referenced-by-count":0,"title":["Learning continuous representation of text for phone duration modeling in statistical parametric speech synthesis"],"prefix":"10.1109","author":[{"given":"Sai Krishna","family":"Rallabandi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sai Sirisha","family":"Rallabandi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Padmini","family":"Bandi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suryakanth V","family":"Gangashetty","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Festvox: Tools for creation and analyses of large speech corpora","author":"anumanchipalli","year":"2011","journal-title":"Proc Very-Large-Scale Phonetics Workshop"},{"key":"ref32","article-title":"The festival speech synthesis system, version 1.4. 2","author":"black","year":"2001","journal-title":"Unpublished document available via"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2006-488","article-title":"Clustergen: a statistical parametric synthesizer using trajectory modeling","author":"black","year":"2006","journal-title":"InterSpeech"},{"article-title":"Automatic building of synthetic voices from audio books","year":"2010","author":"prahallad","key":"ref30"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2005-72","article-title":"The blizzard challenge 2005: Evaluating corpus-based speech synthesis on common databases","author":"black","year":"2005","journal-title":"Proceedings of Interspeech"},{"article-title":"The architecture of the festival speech synthesis system","year":"1998","author":"taylor","key":"ref10"},{"key":"ref11","first-page":"v?313","article-title":"Modeling syllable duration in indian languages using neural networks","volume":"5","author":"sreenivasa rao","year":"2004","journal-title":"Acoustics Speech and Signal Processing 2004 Proceedings (ICASSP '04) IEEE International Conference on"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.12.003"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176347963"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.1997-663","article-title":"Modeling segmental duration with multivariate adaptive regression splines","author":"riedi","year":"1997","journal-title":"Eurospeech"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.10.002"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2010.07.005"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1976.1162873"},{"key":"ref18","first-page":"1","article-title":"Language identification and language specific letter-to-sound rules","volume":"17","author":"lewis","year":"2004","journal-title":"Colorado Research in Linguistics"},{"article-title":"Method for letter-to-sound in text-to-speech synthesis","year":"2000","author":"kuhn","key":"ref19"},{"key":"ref28","first-page":"2177","article-title":"Neural word embedding as implicit matrix factorization","author":"levy","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Duration modeling for arabic text to speech synthesis","author":"hifny","year":"2002","journal-title":"InterSpeech"},{"key":"ref27","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"arXiv preprint arXiv 1301 3781"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2004-460","article-title":"Hidden semi-markov model based speech synthesis","author":"zen","year":"2004","journal-title":"InterSpeech"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WSS.2002.1224395"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/383952.384019"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1016\/0167-6393(90)90021-Z","article-title":"Pitch-synchronous waveform processing techniques for text-to-speech synthesis using di-phones","volume":"9","author":"moulines","year":"1990","journal-title":"Speech Communication"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-81000-8_5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(92)90027-5"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.21437\/Blizzard.2013-9","article-title":"Mile tts for tamil and kannada for blizzard challenge 2013","author":"kumar","year":"2013","journal-title":"Blizzard Challenge Workshop 2013"},{"journal-title":"Classification and Regression Trees","year":"1984","author":"breiman","key":"ref9"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2005-284","article-title":"Multidimensional scaling of listener responses to synthetic speech","author":"mayo","year":"2005"},{"key":"ref20","article-title":"Letter to sound rules for accented lexicon compression","author":"pagel","year":"1998","journal-title":"arXiv preprint cmp-lg\/9807008"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/133160.133190"},{"article-title":"Issues in building general letter to sound rules","year":"1998","author":"black","key":"ref21"},{"article-title":"Unsupervised learning for text-to-speech synthesis","year":"2013","author":"watts","key":"ref24"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/0306-4573(94)00056-9"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947611"},{"key":"ref25","first-page":"1045","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"11 Th Annual Conference of the International Speech Communication Association INTERSPEECH-2010"}],"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\/07404782.pdf?arnumber=7404782","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T10:58:10Z","timestamp":1748775490000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7404782\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,12]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/asru.2015.7404782","relation":{},"subject":[],"published":{"date-parts":[[2015,12]]}}}