{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:39:01Z","timestamp":1776883141404,"version":"3.51.2"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832258","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"668-674","source":"Crossref","is-referenced-by-count":3,"title":["Investigating Disentanglement in a Phoneme-Level Speech Codec for Prosody Modeling"],"prefix":"10.1109","author":[{"given":"Sotirios","family":"Karapiperis","sequence":"first","affiliation":[{"name":"Innoetics, Samsung Electronics,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikolaos","family":"Ellinas","sequence":"additional","affiliation":[{"name":"Innoetics, Samsung Electronics,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexandra","family":"Vioni","sequence":"additional","affiliation":[{"name":"Innoetics, Samsung Electronics,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junkwang","family":"Oh","sequence":"additional","affiliation":[{"name":"Mobile eXperience Business, Samsung Electronics,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gunu","family":"Jho","sequence":"additional","affiliation":[{"name":"Mobile eXperience Business, Samsung Electronics,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Inchul","family":"Hwang","sequence":"additional","affiliation":[{"name":"Mobile eXperience Business, Samsung Electronics,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Spyros","family":"Raptis","sequence":"additional","affiliation":[{"name":"Innoetics, Samsung Electronics,Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref2","first-page":"5530","article-title":"Conditional Variational Autoencoder with Adversarial Learning for End-toEnd Text-to-Speech","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref3","article-title":"Controllable and Lossless Non-Autoregressive End-to-End Text-to-Speech","author":"Liu","year":"2022","journal-title":"arXiv preprint arXiv:2207.06088"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3356232"},{"key":"ref5","article-title":"Neural Discrete Representation Learning","volume":"30","author":"van","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053436"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref8","article-title":"High Fidelity Neural Audio Compression","author":"D\u00e9fossez","year":"2022","journal-title":"arXiv preprint arXiv:2210.13438"},{"key":"ref9","article-title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2301.02111"},{"key":"ref10","article-title":"NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers","author":"Shen","year":"2023","journal-title":"arXiv preprint arXiv:2304.09116"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref12","article-title":"Sound-Storm: Efficient Parallel Audio Generation","author":"Borsos","year":"2023","journal-title":"arXiv preprint arXiv:2305.09636"},{"key":"ref13","first-page":"5180","article-title":"Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref14","article-title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","author":"Ren","year":"2020","journal-title":"arXiv preprint arXiv:2006.04558"},{"key":"ref15","first-page":"7748","article-title":"Meta-StyleSpeech: Multi-Speaker Adaptive Text-to-Speech Generation","volume-title":"International Conference on Machine Learning","author":"Min"},{"key":"ref16","article-title":"StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech Synthesis","author":"Li","year":"2022","journal-title":"arXiv preprint arXiv:2205.15439"},{"key":"ref17","article-title":"Hierarchical Generative Modeling for Controllable Speech Synthesis","author":"Hsu","year":"2018","journal-title":"arXiv preprint arXiv:1810.07217"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053520"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"ref20","article-title":"Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis","author":"Jiang","year":"2023","journal-title":"arXiv preprint arXiv:2307.07218"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-22"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2021-40"},{"key":"ref23","article-title":"Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling","author":"Shen","year":"2020","journal-title":"arXiv preprint arXiv:2010.04301"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref25","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":"Advances in neural information processing systems"},{"key":"ref26","first-page":"28492","article-title":"Robust Speech Recognition via Large-Scale Weak Supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2007.09.003"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960497"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","location":"Macao","start":{"date-parts":[[2024,12,2]]},"end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832258.pdf?arnumber=10832258","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T07:42:02Z","timestamp":1737099722000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832258\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832258","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}