{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T03:19:23Z","timestamp":1729653563867,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/apsipa.2017.8282228","type":"proceedings-article","created":{"date-parts":[[2018,2,14]],"date-time":"2018-02-14T15:31:33Z","timestamp":1518622293000},"page":"1237-1242","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning-based speaking rate-dependent hierarchical prosodie model for Mandarin TTS"],"prefix":"10.1109","author":[{"given":"Yen-Ting","family":"Lin","sequence":"first","affiliation":[]},{"given":"Chen-Yu","family":"Chiang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2014.09.003"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2516032"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472736"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2461448"},{"key":"ref14","article-title":"Deep belief network-based post-filtering for statistical parametric speech synthesis","author":"ya-jun","year":"2016","journal-title":"Acoustics Speech and Signal Processing (ICASSP) 2016 IEEE International Conference on IEEE"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2321482"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2598307"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2015.7357862"},{"key":"ref18","first-page":"786","article-title":"On Cross-Dialect and-Speaker Adaptation of Speaking Rate-Dependent Hierarchical Prosodic Model for a Hakka Text-to-Speech System","author":"chen-yu","year":"2016","journal-title":"Proc Speech Prosody 2016"},{"key":"ref19","first-page":"13171320","article-title":"Vector quantization of pitch information in Mandarin speech","volume":"38","author":"chen","year":"1990","journal-title":"IEEE Trans Communications"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854317"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639187"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854321"},{"key":"ref5","first-page":"8012","article-title":"Statistical Parametric Speech Synthesis Using Deep Neural Networks","author":"zen","year":"2013","journal-title":"Proc ICASSP"},{"key":"ref8","article-title":"TTS synthesis with bidirectional LSTM based recurrent neural networks","author":"yuchen","year":"2014","journal-title":"InterSpeech"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472654"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367298"},{"key":"ref1","first-page":"2347","article-title":"Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis","author":"yoshimura","year":"1999","journal-title":"Proc of Eurospeech"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/S0167-6393(98)00085-5","article-title":"Restructuring speech representations using a pitch-adaptive time-frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in sounds","volume":"27","author":"kawahara","year":"1999","journal-title":"Speech Commun"},{"key":"ref20","article-title":"Torch7: A matlab-like environment for machine learning","author":"collobert","year":"2011","journal-title":"BigLearn NIPS Workshop no EPFL-CONF-192376"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1121\/1.3056559"},{"journal-title":"Torch7 Scientific Computing for LuaJIT","year":"0","key":"ref21"}],"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\/08282228.pdf?arnumber=8282228","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,10]],"date-time":"2019-10-10T20:20:40Z","timestamp":1570738840000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8282228\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/apsipa.2017.8282228","relation":{},"subject":[],"published":{"date-parts":[[2017,12]]}}}