{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:29:16Z","timestamp":1763202556354,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T00:00:00Z","timestamp":1639353600000},"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":[[2021,12,13]]},"DOI":"10.1109\/asru51503.2021.9688154","type":"proceedings-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T20:31:00Z","timestamp":1643920260000},"page":"1155-1161","source":"Crossref","is-referenced-by-count":12,"title":["On-Device Neural Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Sivanand","family":"Achanta","sequence":"first","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Albert","family":"Antony","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ladan","family":"Golipour","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangchuan","family":"Li","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tuomo","family":"Raitio","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ramya","family":"Rasipuram","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesco","family":"Rossi","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jennifer","family":"Shi","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaimin","family":"Upadhyay","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Winarsky","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hepeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"SampleRNN: An un-conditional end-to-end neural audio generation model","author":"mehri","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref11","article-title":"Fastspeech: Fast, robust and controllable text to speech","author":"ren","year":"0","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume":"abs 2006 4558","author":"ren","year":"2020","journal-title":"ArXiv"},{"journal-title":"Parallel Tacotron Non-autoregressive and controllable TTS","year":"2020","author":"elias","key":"ref13"},{"key":"ref14","article-title":"End-to-end adver-sarial text-to-speech","author":"donahue","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref15","article-title":"ClariNet: Parallel wave generation in end-to-end text-to-speech","author":"ping","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref17","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"0","journal-title":"ADVANCES IN NEURAL IN-FORMATION PROCESSING SYSTEMS"},{"key":"ref18","article-title":"Wave-Tacotron: Spectrogram-free end-to-end text-to-speech synthesis","author":"weiss","year":"2020","journal-title":"ArXiv e-prints"},{"key":"ref19","article-title":"Online and linear-time at-tention by enforcing monotonic alignments","author":"raffel","year":"0","journal-title":"ICML"},{"key":"ref4","first-page":"3918","article-title":"Parallel WaveNet: Fast high-fidelity speech synthesis","volume":"80","author":"van den oord","year":"2018","journal-title":"Proceedings of the 35th International Conference on Ma-chine Learning"},{"key":"ref3","article-title":"Efficient neural audio synthesis","author":"kalchbrenner","year":"2018","journal-title":"ArXiv"},{"key":"ref6","first-page":"195","article-title":"Deep Voice: Real-time neural text-to-speech","author":"ar?k","year":"0","journal-title":"Proceedings of the 34th International Conference on Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref8","article-title":"Deep Voice 3: 2000-speaker neural text-to-speech","author":"ping","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref7","article-title":"Deep Voice 2: Multi-speaker neural text-to-speech","volume":"30","author":"gibiansky","year":"0","journal-title":"Advances in Neural Information Pro-cessing Systems"},{"key":"ref2","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"0","journal-title":"9th ISCA Speech Synthesis Workshop"},{"key":"ref9","article-title":"Char2Wav: End-to-end speech synthesis","author":"sotelo","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1972"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1424"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"ref24","article-title":"Categorical reparameterization with Gumbel-Softmax","author":"gu","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1798"},{"key":"ref25","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","author":"mnih","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"}],"event":{"name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","start":{"date-parts":[[2021,12,13]]},"location":"Cartagena, Colombia","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9687821\/9687855\/09688154.pdf?arnumber=9688154","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,16]],"date-time":"2022-05-16T20:42:11Z","timestamp":1652733731000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9688154\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,13]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/asru51503.2021.9688154","relation":{},"subject":[],"published":{"date-parts":[[2021,12,13]]}}}