{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T23:16:56Z","timestamp":1771888616768,"version":"3.50.1"},"reference-count":27,"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\/icassp49357.2023.10094639","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":7,"title":["EfficientSpeech: An On-Device Text to Speech Model"],"prefix":"10.1109","author":[{"given":"Rowel","family":"Atienza","sequence":"first","affiliation":[{"name":"University of the Philippines,Electrical and Electronics Engineering Institute and AI Graduate Program"}]}],"member":"263","reference":[{"key":"ref13","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume":"33","author":"kong","year":"2020","journal-title":"NeurIPS"},{"key":"ref12","first-page":"5530","article-title":"Conditional variational au-toencoder with adversarial learning for end-to-end text-to-speech","author":"kim","year":"2021","journal-title":"ICML"},{"key":"ref15","article-title":"The lj speech dataset","author":"ito","year":"2017"},{"key":"ref14","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention"},{"key":"ref11","article-title":"Nix-tts: An incredibly lightweight end-to-end text-to-speech model via non end-to-end distillation","author":"chevi","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414403"},{"key":"ref2","first-page":"6588","article-title":"Fastpitch: Parallel text-to-speech with pitch prediction","author":"la?cucki","year":"2021","journal-title":"ICASSP 2021"},{"key":"ref1","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2021","journal-title":"ICLRE"},{"key":"ref17","article-title":"Gaussian error linear units (gelus)","author":"hendrycks","year":"2016"},{"key":"ref16","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref19","first-page":"12077","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"xie","year":"2021","journal-title":"NeurIPS"},{"key":"ref18","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref24","article-title":"The efficiency misnomer","author":"dehghani","year":"2021","journal-title":"ICLRE"},{"key":"ref23","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2018","journal-title":"ICLRE"},{"key":"ref26","article-title":"Nemo: a toolkit for building ai applications using neural modules","author":"kuchaiev","year":"2019"},{"key":"ref25","article-title":"fvcore","year":"2022"},{"key":"ref20","article-title":"g2pe","author":"park","year":"2019"},{"key":"ref22","article-title":"Fast and reliable f0 estimation method based on the period extraction of vocal fold vibration of singing voice and speech","author":"morise","year":"2009","journal-title":"Intl Conf Audio for Games"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"498","DOI":"10.21437\/Interspeech.2017-1386","article-title":"Montreal forced aligner: Trainable text-speech alignment using kaldi","volume":"2017","author":"mcauliffe","year":"2017","journal-title":"InterSpeech"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"623","DOI":"10.1007\/978-3-642-19551-8_23","article-title":"Speech quality assessment","author":"loizou","year":"2011","journal-title":"Multimedia Analysis Processing and Communications"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-188"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688154"},{"key":"ref9","first-page":"13963","article-title":"Portaspeech: Portable and high-quality generative text-to-speech","volume":"34","author":"ren","year":"2021","journal-title":"NeurIPS"},{"key":"ref4","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","author":"ping","year":"2018","journal-title":"ICLRE"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref6","first-page":"7482","article-title":"Mixertts: non-autoregressive, fast and compact text-to-speech model conditioned on language model embeddings","author":"tatanov","year":"2022","journal-title":"ICASSP 2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"}],"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\/10094639.pdf?arnumber=10094639","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:07:05Z","timestamp":1700507225000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094639\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094639","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}