{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T06:10:24Z","timestamp":1737699024804,"version":"3.33.0"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Samsung Research, Samsung Electronics Company Ltd"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/lsp.2025.3528858","type":"journal-article","created":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T20:35:01Z","timestamp":1736973301000},"page":"646-650","source":"Crossref","is-referenced-by-count":0,"title":["SegINR: Segment-Wise Implicit Neural Representation for Sequence Alignment in Neural Text-to-Speech"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8150-765X","authenticated-orcid":false,"given":"Minchan","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4689-3110","authenticated-orcid":false,"given":"Myeonghun","family":"Jeong","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3316-4808","authenticated-orcid":false,"given":"Joun Yeop","family":"Lee","sequence":"additional","affiliation":[{"name":"Samsung Research, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0568-4902","authenticated-orcid":false,"given":"Nam Soo","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00618"},{"key":"ref2","first-page":"3445","article-title":"High fidelity text-to-speech via discrete tokens using token transducer and group masked language model","volume-title":"Proc. Interspeech","author":"Yeop","year":"2024"},{"key":"ref3","article-title":"High fidelity neural audio compression","author":"Dfossez","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"article-title":"Hifi-codec: Group-residual vector quantization for high fidelity audio codec","year":"2023","author":"Yang","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"article-title":"Neural codec language models are zero-shot text to speech synthesizers","year":"2023","author":"Wang","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389791"},{"key":"ref8","first-page":"6621","article-title":"Speech-T: Transducer for text to speech and beyond","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen","year":"2021"},{"article-title":"Vall-T: Decoder-only generative transducer for robust and decoding-controllable text-to-speech","year":"2024","author":"Du","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-286"},{"key":"ref11","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ren","year":"2021"},{"key":"ref12","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref13","first-page":"8599","article-title":"Grad-TTs: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Popov","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref15","first-page":"8067","article-title":"Glow-TTs: A generative flow for text-to-speech via monotonic alignment search","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kim","year":"2020,"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747707"},{"key":"ref17","first-page":"7462","article-title":"Implicit neural representations with periodic activation functions","volume-title":"Proc. Adv. Neural Inf. Process Syst.","volume":"33","author":"Sitzmann","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"ref20","first-page":"5694","article-title":"From data to functa: Your data point is a function and you can treat it like one","volume-title":"Proc. 39th Int. Conf. Mach. Learn.,","author":"Dupont","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3381910"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07366-3"},{"key":"ref25","article-title":"Sequence transduction with recurrent neural networks","volume-title":"Proc. Representation Learn. Worksop","author":"Graves","year":"2012"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095431"},{"key":"ref27","article-title":"End-to-end adversarial text-to-speech","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Donahue","year":"2021"},{"article-title":"COIN: Compression with implicit neural representations","year":"2021","author":"Dupont","key":"ref28"},{"key":"ref29","article-title":"COIN : Neural compression across modalities","author":"Dupont","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"article-title":"Shap-e: Generating conditional 3D implicit functions","year":"2023","author":"Jun","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00609"},{"article-title":"Spatial functa: Scaling functa to imagenet classification and generation","year":"2023","author":"Bauer","key":"ref32"},{"key":"ref33","first-page":"7537","article-title":"Fourier features let networks learn high frequency functions in low dimensional domains","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Tancik","year":"2020"},{"key":"ref34","article-title":"Towards lightweight controllable audio synthesis with conditional implicit neural representations","volume-title":"Proc. NeurIPS 2021 Workshop Deep Generative Models Downstream Appl.","author":"Zuiderveld","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43421-1_39"},{"key":"ref36","article-title":"Hypernetworks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ha","year":"2017"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"article-title":"Unsupervised cross-lingual representation learning for speech recognition","year":"2020","author":"Conneau","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"article-title":"Speak foreign languages with your own voice: Cross-lingual neural codec language modeling","year":"2023","author":"Zhang","key":"ref40"},{"key":"ref41","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2023"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/10802935\/10839557.pdf?arnumber=10839557","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T05:53:36Z","timestamp":1737698016000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10839557\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/lsp.2025.3528858","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2025]]}}}