{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T18:33:20Z","timestamp":1761676400662,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1109\/icassp.2016.7472734","type":"proceedings-article","created":{"date-parts":[[2016,6,24]],"date-time":"2016-06-24T01:58:30Z","timestamp":1466733510000},"page":"5525-5529","source":"Crossref","is-referenced-by-count":7,"title":["Wavelet-based decomposition of F0 as a secondary task for DNN-based speech synthesis with multi-task learning"],"prefix":"10.1109","author":[{"given":"Manuel Sam","family":"Ribeiro","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oliver","family":"Watts","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert A. J.","family":"Clark","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-02732-6"},{"key":"ref11","article-title":"Continuous wavelet transform for analysis of speech prosody","author":"vainio","year":"2013","journal-title":"TRASP 2013-Tools and Resources for the Analysys of Speech Prosody An Interspeech 2013 satellite event August 30 2013 Laboratoire Parole et Language Aixen-Provence France Proceedings"},{"key":"ref12","article-title":"Wavelets for intonation modeling in hmm speech synthesis","author":"santeri suni","year":"2013","journal-title":"Proc ISCA Speech Synthesis Workshop"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178904"},{"key":"ref14","article-title":"Hierarchical modeling of f0 contours for voice conversion","author":"sanchez","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref15","article-title":"A perceptual investigation of wavelet-based decomposition of f0 for text-to-speech synthesis","author":"sam ribeiro","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639012"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1175\/1520-0477(1998)079<0061:APGTWA>2.0.CO;2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2013.2251852"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"85","DOI":"10.20396\/joss.v1i1.15014","article-title":"Speech prosody: a methodological review","volume":"1","author":"xu","year":"2012","journal-title":"Journal of Speech Sciences"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854318"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"7962","DOI":"10.1109\/ICASSP.2013.6639215","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"Acoustics Speech and Signal Processing (ICASSP) 2013 IEEE International Conference on"},{"key":"ref8","article-title":"Prosody contour prediction with long short-term memory, bi-directional, deep recurrent neural networks","author":"fernandez","year":"2014","journal-title":"Proceedings of the Annual Conference of International Speech Communication Association (INTERSPEECH)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854321"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511808814"},{"key":"ref1","article-title":"Measuring a decade of progress in text-to-speech","volume":"1","author":"king","year":"2011","journal-title":"Loquens"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178814"},{"key":"ref20","first-page":"2222","article-title":"Lightly supervised recognition for automatic alignment of large coherent speech recordings","author":"norbert","year":"2010","journal-title":"InterSpeech"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"1821","DOI":"10.21437\/Interspeech.2011-38","article-title":"Automatic sentence selection from speech corpora including diverse speech for improved hmm-tts synthesis quality","author":"braunschweiler","year":"2011","journal-title":"InterSpeech"}],"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\/07472734.pdf?arnumber=7472734","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T21:27:11Z","timestamp":1718659631000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7472734\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp.2016.7472734","relation":{},"subject":[],"published":{"date-parts":[[2016,3]]}}}