{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:04:09Z","timestamp":1779383049045,"version":"3.53.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/asru46091.2019.9003829","type":"proceedings-article","created":{"date-parts":[[2020,2,21]],"date-time":"2020-02-21T07:01:33Z","timestamp":1582268493000},"page":"192-199","source":"Crossref","is-referenced-by-count":39,"title":["Controlling Emotion Strength with Relative Attribute for End-to-End Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Xiaolian","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Geng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref31","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2007.19.5.1155"},{"key":"ref10","first-page":"3331","article-title":"CHiVE: Varying prosody in speech synthesis with a linguistically driven dynamic hierarchical conditional variational network","volume":"97","author":"kenter","year":"2019","journal-title":"Proc PMLR"},{"key":"ref11","first-page":"433","article-title":"Learning visual attributes","author":"ferrari","year":"2008","journal-title":"Proc NIPS"},{"key":"ref12","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with Tacotron","author":"skerry-ryan","year":"2018","journal-title":"Proc ICML"},{"key":"ref13","article-title":"Effective use of variational embedding capacity in expressive end-to-end speech synthesis","author":"battenberg","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682368"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683827"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACIIAsia.2018.8470334"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953138"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2009-103","article-title":"The interspeech 2009 emotion challenge","author":"schuller","year":"2009","journal-title":"Proc INTERSPEECH"},{"key":"ref4","first-page":"4779","article-title":"Natural TTS synthesis by conditioning wavenet on mel spectrogram predictions","author":"jonathan","year":"2018","journal-title":"Proc ICASSP"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502224"},{"key":"ref3","article-title":"Char2wav: End-to-end speech synthesis","author":"sotelo","year":"2017","journal-title":"Proc ICML"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953089"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126281"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282282"},{"key":"ref8","author":"li","year":"2018","journal-title":"Close to human quality TTS with transformer"},{"key":"ref7","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","author":"wang","year":"2018","journal-title":"Proc ICML"},{"key":"ref2","first-page":"195","article-title":"Deep voice: Real-time neural text-to-speech","author":"arik","year":"2017","journal-title":"Proc ICML"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1109\/SLT.2018.8639682","article-title":"Predicting expressive speaking style from text in end-to-end speech synthesis","author":"stanton","year":"2018","journal-title":"Proceedings of 2018 IEEE Spoken Language Technology Workshop (SLT)"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: A fully end-to-end text-to-speech synthesis model","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref20","article-title":"Expressive speech synthesis using a concate-native synthesizer","author":"bulut","year":"2002","journal-title":"Seventh International Conference on Spoken Language Processing"},{"key":"ref22","author":"henter","year":"2018","journal-title":"Deep encoder-decoder models for unsupervised learning of controllable speech synthesis"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.03.002"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2017.8282231"},{"key":"ref23","article-title":"Emotional transplant in statistical speech synthesis based on emotion additive model","author":"ohtani","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref26","author":"lee","year":"2017","journal-title":"Emotional End-to-End Neural Speech Synthesizer"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683682"}],"event":{"name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"SG, Singapore","start":{"date-parts":[[2019,12,14]]},"end":{"date-parts":[[2019,12,18]]}},"container-title":["2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8985378\/9003727\/09003829.pdf?arnumber=9003829","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,27]],"date-time":"2023-09-27T08:49:30Z","timestamp":1695804570000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9003829\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/asru46091.2019.9003829","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}