{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T02:03:45Z","timestamp":1725588225661},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,11,5]],"date-time":"2020-11-05T00:00:00Z","timestamp":1604534400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,11,5]],"date-time":"2020-11-05T00:00:00Z","timestamp":1604534400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,11,5]],"date-time":"2020-11-05T00:00:00Z","timestamp":1604534400000},"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":[[2020,11,5]]},"DOI":"10.1109\/o-cocosda50338.2020.9295020","type":"proceedings-article","created":{"date-parts":[[2020,12,28]],"date-time":"2020-12-28T20:48:58Z","timestamp":1609188538000},"page":"139-144","source":"Crossref","is-referenced-by-count":0,"title":["Towards Speech Entrainment: Considering ASR Information in Speaking Rate Variation of TTS Waveform Generation"],"prefix":"10.1109","author":[{"given":"Mayuko","family":"Okamoto","sequence":"first","affiliation":[]},{"given":"Sakriani","family":"Sakti","sequence":"additional","affiliation":[]},{"given":"Satoshi","family":"Nakamura","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1995.479684"},{"journal-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","year":"2018","author":"skerry-ryan","key":"ref11"},{"journal-title":"Style tokens Unsupervised style modeling control and transfer in end-to-end speech synthesis","year":"2018","author":"wang","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683827"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-985"},{"key":"ref15","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"0","journal-title":"Proceedings of the Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref16","first-page":"4960","author":"chan","year":"2016","journal-title":"Listen attend and spell A neural network for large vocabulary conversational speech recognition"},{"journal-title":"Neural machine translation by jointly learning to align and translate","year":"2014","author":"bahdanau","key":"ref17"},{"key":"ref18","article-title":"The CMU arctic speech databases","author":"kominek","year":"0","journal-title":"Proceedings of SSW"},{"journal-title":"Phoneme-level speaking rate variation on waveform generation using gan-tts","year":"0","key":"ref19"},{"journal-title":"Tacotron A fully end-to-end text-to-speech synthesis model","year":"2017","author":"wang","key":"ref4"},{"key":"ref3","first-page":"7962","article-title":"Statistical parametric speech synthesis using deep neural networks","author":"zen","year":"0","journal-title":"Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"journal-title":"Efficient Neural Audio Synthesis","year":"2018","author":"kalchbrenner","key":"ref6"},{"journal-title":"WaveNet A Generative Model for Raw Audio","year":"2016","author":"oord","key":"ref5"},{"key":"ref8","first-page":"2347","article-title":"Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis","author":"yoshimura","year":"0","journal-title":"Proceedings of EUROSPEECH"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2761547"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.evolhumbehav.2013.08.001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1093\/ietisy\/e88-d.3.502"},{"key":"ref1","first-page":"11","article-title":"Acoustic-prosodic entrainment and social behavior","author":"levitan","year":"0","journal-title":"Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies (NAACL HLT)"},{"key":"ref20","first-page":"381","article-title":"Creating corpora for speech-to-speech translation","author":"kikui","year":"0","journal-title":"Proc of European Conference of Speech Communication and Technology"},{"journal-title":"Effective Approaches to Attention-based Neural Machine Translation","year":"2015","author":"luong","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-5941"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.861820"},{"journal-title":"Empirical evaluation of rectified activations in convolutional network","year":"2015","author":"xu","key":"ref23"},{"journal-title":"The HMM-Based Speech Synthesis System (HTS)","year":"0","key":"ref25"}],"event":{"name":"2020 23rd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","start":{"date-parts":[[2020,11,5]]},"location":"Yangon, Myanmar","end":{"date-parts":[[2020,11,7]]}},"container-title":["2020 23rd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9294763\/9294994\/09295020.pdf?arnumber=9295020","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:56:09Z","timestamp":1656453369000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9295020\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,5]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/o-cocosda50338.2020.9295020","relation":{},"subject":[],"published":{"date-parts":[[2020,11,5]]}}}