{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T15:05:24Z","timestamp":1725807924425},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414809","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"5689-5693","source":"Crossref","is-referenced-by-count":6,"title":["Multi-Rate Attention Architecture for Fast Streamable Text-to-Speech Spectrum Modeling"],"prefix":"10.1109","author":[{"given":"Qing","family":"He","sequence":"first","affiliation":[{"name":"Facebook AI"}]},{"given":"Zhiping","family":"Xiu","sequence":"additional","affiliation":[{"name":"Facebook AI"}]},{"given":"Thilo","family":"Koehler","sequence":"additional","affiliation":[{"name":"Facebook AI"}]},{"given":"Jilong","family":"Wu","sequence":"additional","affiliation":[{"name":"Facebook AI"}]}],"member":"263","reference":[{"key":"ref10","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"year":"2015","key":"ref11","article-title":"The international phonetic alphabet"},{"year":"2017","key":"ref12","article-title":"Soft-dtw: a differentiable loss function for time-series"},{"article-title":"Interactive text-to-speech via semi-supervised style transfer learning","year":"2020","author":"gao","key":"ref13"},{"key":"ref14","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"International Conference on Learning Representations"},{"year":"0","key":"ref15","article-title":"Tacotron 2 - pytorch implementation with faster-than-realtime inference"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref3","first-page":"3171","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref6","first-page":"125","article-title":"Wavenet: A generative model for raw audio","author":"oord","year":"0","journal-title":"9th ISCA Speech Synthesis Workshop"},{"key":"ref5","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"ICML"},{"article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","year":"2017","author":"ping","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref1","first-page":"4006","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proc Inter-speech 2017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414809.pdf?arnumber=9414809","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,2]],"date-time":"2022-08-02T20:17:43Z","timestamp":1659471463000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414809\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414809","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}