{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T06:30:03Z","timestamp":1763620203407,"version":"3.28.0"},"reference-count":36,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1109\/icassp.2016.7472658","type":"proceedings-article","created":{"date-parts":[[2016,6,24]],"date-time":"2016-06-24T01:58:30Z","timestamp":1466733510000},"page":"5145-5149","source":"Crossref","is-referenced-by-count":18,"title":["Deep neural network-guided unit selection synthesis"],"prefix":"10.1109","author":[{"given":"Thomas","family":"Merritt","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert A. J.","family":"Clark","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhizheng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"King","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"International Telecommunication Union Telecommunication Standardization Sector Geneva Switzerland Objective measurement of active speech level","year":"2011","key":"ref33"},{"key":"ref32","article-title":"Hurricane natural speech corpus, [sound]","author":"cooke","year":"2013","journal-title":"LISTA Consortium"},{"key":"ref31","article-title":"Minimum trajectory error training for deep neural networks, combined with stacked bottleneck features","author":"wu","year":"0","journal-title":"Proceedings of Interspeech 2015"},{"key":"ref30","first-page":"294","article-title":"The HMM-based speech synthesis system (HTS) version 2.0","author":"heiga","year":"2007","journal-title":"Proc SSW6"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1894-4_23"},{"article-title":"Listening test materials for “Deep neural network-guided unit selection synthesis”, 2016 [dataset]","year":"0","author":"thomas","key":"ref35"},{"journal-title":"International Telecommunication Union Radiocommunication Assembly Geneva Switzerland Method for the subjective assessment of intermediate quality level of coding systems","year":"2003","key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.21437\/Eurospeech.1997-219","article-title":"Automatically clustering similar units for unit selection in speech synthesis","author":"black","year":"1997","journal-title":"Proc EUROSPEECH"},{"key":"ref12","article-title":"The architecture of the festival speech synthesis system","author":"paul","year":"1998","journal-title":"The Third ESCA\/COCOSDA Workshop on Speech Synthesis"},{"key":"ref13","first-page":"2038","article-title":"The target cost formulation in unit selection speech synthesis","author":"taylor","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1109\/TASL.2012.2221460","article-title":"A unified trajectory tiling approach to high quality speech rendering","volume":"21","author":"yao","year":"2013","journal-title":"Audio Speech and Language Processing IEEE Transactions on"},{"key":"ref15","article-title":"The USTC system for Blizzard Challenge 2008","author":"zhen-hua","year":"2008","journal-title":"Proc Blizzard Challenge"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2010.5495150"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"1825","DOI":"10.21437\/Interspeech.2008-175","article-title":"Synthesis by generation and concatenation of multiform segments","author":"pollet","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"337","DOI":"10.21437\/Interspeech.2011-124","article-title":"Uniform Speech Parameterization for Multi-form Segment Synthesis","author":"sorin","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"2214","DOI":"10.21437\/Interspeech.2012-590","article-title":"Psychoacous-tic Segment Scoring for Multi-Form Speech Synthesis","author":"sorin","year":"2012","journal-title":"Proc INTERSPEECH"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.01.014"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3989\/loquens.2014.006"},{"key":"ref27","article-title":"Festival 2-build your own general purpose unit selection speech synthesiser","author":"clark","year":"2004","journal-title":"Proc SSW5"},{"key":"ref3","article-title":"The Blizzard Challenge 2013","author":"king","year":"2013","journal-title":"Proc Blizzard Challenge"},{"key":"ref6","first-page":"1509","article-title":"Investigating source and filter contributions, and their interaction, to statistical parametric speech synthesis","author":"merritt","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366913"},{"key":"ref5","first-page":"165","article-title":"Investigating the shortcomings of HMM synthesis","author":"merritt","year":"2013","journal-title":"Proc ISCA Speech Synthesis Workshop"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178766"},{"key":"ref7","first-page":"1504","article-title":"Measuring the perceptual effects of modelling assumptions in speech synthesis using stimuli constructed from repeated natural speech","author":"eje henter","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref2","article-title":"The Blizzard Challenge 2012","author":"king","year":"2012","journal-title":"Proc Blizzard Challenge"},{"key":"ref9","article-title":"Deep neural network context embeddings for model selection in rich-context HMM synthesis","author":"merritt","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref1","article-title":"The Blizzard Challenge 2011","author":"king","year":"2011","journal-title":"Proc Blizzard Challenge"},{"key":"ref20","first-page":"790","article-title":"Refined Inter-segment Joining in Multi-Form Speech Synthesis","author":"sorin","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178814"},{"key":"ref21","article-title":"Using Deep Bidirectional Recurrent Neural Networks for Prosodic-Target Prediction in a Unit-Selection Text-to-Speech System","author":"fernandez","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref24","article-title":"Acoustic Modeling in Statistical Parametric Speech Synthesis - From HMM to LSTM-RNN","author":"zen","year":"2015","journal-title":"Proc MLSLP"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1109\/MSP.2014.2359987","article-title":"Deep learning for acoustic modeling in parametric speech generation: A systematic review of existing techniques and future trends","volume":"32","author":"zhen-hua","year":"2015","journal-title":"IEEE Signal Processing Magazine"},{"key":"ref26","first-page":"1755","article-title":"Rich context modeling for high quality HMM-based TTS","author":"yan","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/89.668817"}],"event":{"name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2016,3,20]]},"location":"Shanghai","end":{"date-parts":[[2016,3,25]]}},"container-title":["2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7465907\/7471614\/07472658.pdf?arnumber=7472658","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T21:25:30Z","timestamp":1718659530000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7472658\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icassp.2016.7472658","relation":{},"subject":[],"published":{"date-parts":[[2016,3]]}}}