{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T13:17:35Z","timestamp":1758892655235,"version":"3.37.3"},"reference-count":29,"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"}],"funder":[{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095848","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":3,"title":["Can Knowledge of End-to-End Text-to-Speech Models Improve Neural Midi-to-Audio Synthesis Systems?"],"prefix":"10.1109","author":[{"given":"Xuan","family":"Shi","sequence":"first","affiliation":[{"name":"University of Southern California,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erica","family":"Cooper","sequence":"additional","affiliation":[{"name":"National Institute of Informatics,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"National Institute of Informatics,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junichi","family":"Yamagishi","sequence":"additional","affiliation":[{"name":"National Institute of Informatics,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shrikanth","family":"Narayanan","sequence":"additional","affiliation":[{"name":"University of Southern California,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"DDSP: Differentiable digital signal processing","author":"engel","year":"2020","journal-title":"Proc ICLR"},{"article-title":"Multi-instrument music synthesis with spectrogram diffusion","year":"2022","author":"hawthorne","key":"ref12"},{"key":"ref15","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","author":"kim","year":"2021","journal-title":"Proc ICML"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref10","first-page":"449","article-title":"Automatic stylistic composition of Bach Chorales with deep LSTM","author":"liang","year":"2017","journal-title":"Proc ISMIR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747217"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-23"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2956145"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref18","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":"Proc NIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"ref23","first-page":"84","article-title":"Intuitive analysis, creation and manipulation of midi data with pretty midi","author":"raffel","year":"2014","journal-title":"Proc ISMIR late breaking and demo papers"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5616"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"4006","DOI":"10.21437\/Interspeech.2017-1452","article-title":"Tacotron: Towards end-to-end speech synthesis","author":"wang","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682353"},{"key":"ref22","article-title":"Enabling factorized piano music modeling and generation with the MAESTRO dataset","author":"hawthorne","year":"2019","journal-title":"Proc ICLR"},{"key":"ref21","article-title":"Music Transformer: Generating music with long-term structure","author":"huang","year":"2018","journal-title":"Proc ICLR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref27","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc ICLR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461329"},{"year":"0","key":"ref8","article-title":"Pianoteq 7"},{"article-title":"FluidSynth","year":"0","author":"moebert","key":"ref7"},{"key":"ref9","first-page":"96","article-title":"Self-supervised vq-vae for one-shot music style transfer","author":"c\u00edfka","year":"2021","journal-title":"Proc ICASSP"},{"key":"ref4","first-page":"14910","article-title":"MelGAN: Generative adversarial networks for conditional waveform synthesis","author":"kumar","year":"2019","journal-title":"Proc NIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011174"},{"key":"ref6","article-title":"MIDI-DDSP: Detailed control of musical performance via hierarchical modeling","author":"wu","year":"2022","journal-title":"Proc ICLR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683596"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","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\/10095848.pdf?arnumber=10095848","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:08:04Z","timestamp":1700507284000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095848\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095848","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}