{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:05:53Z","timestamp":1775199953741,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434703","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Acoustic Phonetic Temporal Speech Representation"],"prefix":"10.1109","author":[{"given":"Yunbin","family":"Deng","sequence":"first","affiliation":[{"name":"Lincoln Labortoary MIT,Lexington,MA,USA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","volume-title":"Advances in neural information processing systems","author":"Kumar","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/app13053100"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747476"},{"key":"ref4","article-title":"Toward Robust Real-World Audio Deepfake Detection: Closing the Explainability Gap","author":"Channing","year":"2024","journal-title":"arXiv preprint arXiv:2410.07436"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-16"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00097"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3276480"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS55849.2022.9975428"},{"key":"ref9","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Advances in neural information processing systems","volume":"33","author":"Kong","year":"2020"},{"key":"ref10","article-title":"Diffwave: A versatile diffusion model for audio synthesis","volume-title":"arXiv preprint arXiv:2009.(09761)","author":"Kong","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IWBF63717.2025.11113428"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1283"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-254"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-108"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746112"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414234"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref19","first-page":"8067","article-title":"Glowtts: A generative flow for text-to-speech via monotonic alignment search","volume":"33","author":"Kim","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","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":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413889"},{"key":"ref22","article-title":"Talknet: Fully convolutional non-autoregressive speech synthesis model","volume-title":"arXiv preprint arXiv:2005.05514","author":"Beliaev","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746107"},{"key":"ref24","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"International Conference on Machine Learning","author":"Kim"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2867"},{"key":"ref26","volume-title":"gTTS","author":"Durette","year":"2022"},{"key":"ref27","article-title":"Silero models: pre-trained enterprise-grade stt\/tts models and benchmarks","author":"Team","year":"2021"},{"key":"ref28","article-title":"Towards human-centered explainable ai: A survey of user studies for model explanations","author":"Yao","year":"2023","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"ref29","article-title":"Efficient neural audio synthesis","volume-title":"International Conference on Machine Learning","author":"Kalchbrenner"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref31","article-title":"VCTK corpus: English multi-speaker corpus for cstr voice cloning toolkit","author":"Yamagishi","year":"2019"},{"key":"ref32","article-title":"The LJ Speech Dataset","author":"Ito","year":"2017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3643491.3660292"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887568"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11434703.pdf?arnumber=11434703","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:30Z","timestamp":1775192310000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434703\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434703","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}