{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T13:21:39Z","timestamp":1758892899865,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1109\/icassp.2016.7472733","type":"proceedings-article","created":{"date-parts":[[2016,6,23]],"date-time":"2016-06-23T21:58:30Z","timestamp":1466719110000},"page":"5520-5524","source":"Crossref","is-referenced-by-count":7,"title":["Gating recurrent mixture density networks for acoustic modeling in statistical parametric speech synthesis"],"prefix":"10.1109","author":[{"given":"Wenfu","family":"Wang","sequence":"first","affiliation":[]},{"given":"Shuang","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Xu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"4470","article-title":"Unidirectional long short-term memory recurrent neural network with recurrent output layer for low-latency speech synthesis","author":"heiga","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref11","first-page":"4879","article-title":"Word embedding for recurrent neural network based TTS synthesis","author":"peilu","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref12","article-title":"EESEN: End-to-end speech recognition using deep RNN models and WFST-based decoding","author":"yajie","year":"2015","journal-title":"arXiv preprint arX-iv 1507 08240"},{"key":"ref13","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"alex","year":"2014","journal-title":"Proceedings of the 31st International Conference on Machine Learning (ICML-14)"},{"key":"ref14","article-title":"Neural machine translation by jointly learning to align and translate","author":"dzmitry","year":"2014","journal-title":"arXiv preprint arXiv 1409 0473"},{"key":"ref15","article-title":"Learning phrase representations using rn-n encoder-decoder for statistical machine translation","author":"kyunghyun","year":"2014","journal-title":"arXiv preprint arXiv 1406 1078"},{"key":"ref16","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"junyoung","year":"2014","journal-title":"arXiv preprint arXiv 1412 3555"},{"key":"ref17","article-title":"Sequence modeling using gated recurrent neural networks","author":"mohammad","year":"2015","journal-title":"arXiv preprint arXiv 1501 00299"},{"article-title":"Mixture density networks","year":"1994","author":"bishop","key":"ref18"},{"key":"ref19","first-page":"3844","article-title":"Deep mixture density networks for acoustic modeling in statistical parametric speech synthesis","author":"heiga","year":"2014","journal-title":"Proc ICASSP"},{"key":"ref4","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"heiga","year":"2013","journal-title":"Proc ICASSP"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1996.541110"},{"key":"ref6","article-title":"Sequence generation error (SGE) minimization based deep neural networks training for text-to-speech synthesis","author":"yuchen","year":"2015","journal-title":"Sixteenth Annual Conference of the International Speech Communication Association"},{"key":"ref5","first-page":"4460","article-title":"Deep neural networks employing multi-task learning and stacked bottleneck features for speech synthesis","author":"zhizheng","year":"2015","journal-title":"Proc ICASSP"},{"key":"ref8","article-title":"Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition","author":"sak","year":"2014","journal-title":"arXiv preprint arXiv 1402 1128"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1016\/j.specom.2009.04.004","article-title":"Statistical parametric speech synthesis","volume":"51","author":"heiga","year":"2009","journal-title":"Speech Communication"},{"key":"ref1","first-page":"2347","article-title":"Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis","author":"takayoshi","year":"1999","journal-title":"Proc 6th European Conf on Speech Communication and Technology"},{"key":"ref9","first-page":"1964","article-title":"TTS synthesis with bidirectional LSTM based recurrent neural networks","author":"fan","year":"2014","journal-title":"Proc INTERSPEECH"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1109\/72.279181","article-title":"Learning long-term dependencies with gradient descent is difficult","volume":"5","author":"yoshua","year":"1994","journal-title":"Neural Networks IEEE Transactions on"},{"key":"ref22","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":"hideki","year":"1999","journal-title":"Speech Communication"},{"key":"ref21","first-page":"1315","article-title":"Speech parameter generation algorithms for HMM -based speech synthesis","volume":"3","author":"keiichi","year":"2000","journal-title":"Proc ICASSP"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e90-d.5.816"},{"article-title":"The kaldi speech recognition toolkit","year":"2011","author":"daniel","key":"ref23"}],"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\/07472733.pdf?arnumber=7472733","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,24]],"date-time":"2017-06-24T13:00:17Z","timestamp":1498309217000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7472733\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp.2016.7472733","relation":{},"subject":[],"published":{"date-parts":[[2016,3]]}}}