{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T07:07:28Z","timestamp":1761808048687,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1109\/icassp.2016.7472730","type":"proceedings-article","created":{"date-parts":[[2016,6,24]],"date-time":"2016-06-24T01:58:30Z","timestamp":1466733510000},"page":"5505-5509","source":"Crossref","is-referenced-by-count":29,"title":["From HMMS to DNNS: Where do the improvements come from?"],"prefix":"10.1109","author":[{"given":"Oliver","family":"Watts","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gustav Eje","family":"Henter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Merritt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhizheng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"King","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1121\/1.2022883"},{"key":"ref11","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":"ref12","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":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876880"},{"key":"ref14","first-page":"854","article-title":"Fusion of multiple parameterisations for DNN-based sinusoidal speech synthesis with multi-task learning","author":"hu","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref15","first-page":"2212","article-title":"An investigation of context clustering for statistical speech synthesis with deep neural network","author":"chen","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854321"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref18","first-page":"294","article-title":"The HMM-based speech synthesis system (HTS) version 2.0","author":"heiga","year":"2007","journal-title":"Proc ISCA SSW6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICOSP.2014.7015070"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854318"},{"key":"ref3","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"2013","journal-title":"Proc IEEE Int Conf on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178813"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178814"},{"key":"ref8","article-title":"Acoustic modeling in statistical parametric speech synthesis - from HMM to LSTM-RNN","author":"zen","year":"2015","journal-title":"Proc MLSLP"},{"key":"ref7","first-page":"1762","article-title":"CLUSTERGEN: a statistical parametric synthesizer using trajectory modeling","author":"black","year":"2006","journal-title":"Proc INTERSPEECH"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178766"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1998.0048"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.25080\/Majora-92bf1922-003","article-title":"Theano: a CPU and GPU math expression compiler","author":"bergstra","year":"2010","journal-title":"Proceedings of the Python for Scientific Computing Conference"},{"journal-title":"Objective Measurement of Active Speech Level","article-title":"International Telecommunication Union, Telecommunication Standardization Sector, Geneva, Switzerland","year":"2011","key":"ref22"},{"journal-title":"Method for the Subjective Assessment of Intermediate Quality Level of Audio Systems","article-title":"International Telecommunication Union Radiocommunication Assembly, Geneva, Switzerland","year":"2014","key":"ref21"},{"key":"ref24","article-title":"Robust TTS duration modelling using DNNs","author":"eje henter","year":"2016","journal-title":"Proc IEEE Int Conf on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1109\/TAU.1969.1162058","article-title":"IEEE recommended practice for speech quality measurements","volume":"17","author":"rothauser","year":"1969","journal-title":"IEEE Transactions on Audio and Electroacoustics"},{"key":"ref25","first-page":"1964","article-title":"TTS synthesis with bidirectional LSTM based recurrent neural networks","author":"fan","year":"2014","journal-title":"Proc 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\/07472730.pdf?arnumber=7472730","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,9,22]],"date-time":"2020-09-22T20:59:35Z","timestamp":1600808375000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7472730\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp.2016.7472730","relation":{},"subject":[],"published":{"date-parts":[[2016,3]]}}}