{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:38:13Z","timestamp":1774021093136,"version":"3.50.1"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10096566","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["StreamSpeech: Low-Latency Neural Architecture for High-Quality on-Device Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Georgi","family":"Shopov","sequence":"first","affiliation":[{"name":"Institute of Information and Communication Technologies,Bulgarian Academy of Sciences"}]},{"given":"Stefan","family":"Gerdjikov","sequence":"additional","affiliation":[{"name":"Institute of Information and Communication Technologies,Bulgarian Academy of Sciences"}]},{"given":"Stoyan","family":"Mihov","sequence":"additional","affiliation":[{"name":"Institute of Information and Communication Technologies,Bulgarian Academy of Sciences"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688154"},{"key":"ref12","article-title":"DeviceTTS: A small-footprint, fast, stable network for on-device text-to-speech","author":"huang","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1655"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414809"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-018-2810-y"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746103"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1642"},{"key":"ref21","article-title":"Programming dense linear algebra kernels on vectorized architectures","author":"peyton","year":"2013","journal-title":"M S thesis"},{"key":"ref2","article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref1","first-page":"6588","article-title":"FastPitch: Parallel text-to-speech with pitch prediction","author":"?a?cucki","year":"2021","journal-title":"ICASSP 2021-2021 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1017\/9781108756945"},{"key":"ref16","first-page":"220","article-title":"Fast and lightweight on-device TTS with Tacotron 2 and LPCNet","author":"popov","year":"2020","journal-title":"InterSpeech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639276"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1156"},{"key":"ref7","article-title":"DurIAN: Duration informed attention network for multimodal synthesis","author":"yu","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1463"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref6","article-title":"Depthwise separable convolutions for neural machine translation","author":"kaiser","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414403"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10096566.pdf?arnumber=10096566","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:07:48Z","timestamp":1700507268000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10096566\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10096566","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}