{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:04:10Z","timestamp":1775199850805,"version":"3.50.1"},"reference-count":62,"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"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11434670","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["MoLEx: Mixture of LoRA Experts in Speech Self-Supervised Models for Audio Deepfake Detection"],"prefix":"10.1109","author":[{"given":"Zihan","family":"Pan","sequence":"first","affiliation":[{"name":"Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR),Singapore,138634"}]},{"given":"Sailor Hardik","family":"Bhupendra","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR),Singapore,138634"}]},{"given":"Jinyang","family":"Wu","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR),Singapore,138634"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-1"},{"key":"ref2","article-title":"Cosyvoice 2: Scalable streaming speech synthesis with large language models","volume-title":"arXiv preprint arXiv:2412.10117","author":"Du","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-8"},{"key":"ref4","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-17"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACII59096.2023.10388152"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10625957"},{"key":"ref10","article-title":"Adalora: Adaptive budget allocation for parameter-efficient fine-tuning","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2303.10512"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1063\/5.0203126"},{"key":"ref12","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint arXiv:2106.09685"},{"key":"ref13","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017","journal-title":"arXiv preprint arXiv:1701.06538"},{"key":"ref14","article-title":"Mixture of a million experts","author":"He","year":"2024","journal-title":"arXiv preprint arXiv:2407.04153"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.datak.2023.102262"},{"issue":"2","key":"ref16","first-page":"4","article-title":"Adamix: Mixture-of-adapter for parameter-efficient tuning of large language models","volume":"1","author":"Wang","year":"2022","journal-title":"arXiv preprint arXiv:2205.12410"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1568"},{"key":"ref18","article-title":"Moe-ffd: Mixture of experts for generalized and parameter-efficient face forgery detection","author":"Kong","year":"2024"},{"key":"ref19","article-title":"Mixture of lora experts","volume-title":"The Twelfth International Conference on Learning Representations","author":"Wu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1472"},{"key":"ref22","article-title":"Scaling language models: Methods, analysis & insights from training gopher","author":"Rae","year":"2021","journal-title":"arXiv preprint arXiv:2112.11446"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2949598"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0515"},{"issue":"120","key":"ref25","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832226"},{"key":"ref27","article-title":"The expressive power of low-rank adaptation","author":"Zeng","year":"2023","journal-title":"arXiv preprint arXiv:2310.17513"},{"key":"ref28","article-title":"ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale","year":"2024","journal-title":"ASVspoof 5 Challenge"},{"key":"ref29","article-title":"The Singular Value Decomposition (SVD) and Low-Rank Matrix Approximations"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-18"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-26"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-23"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-11"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-25"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285283"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-108"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/ASVspoof.2024-9"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00097"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832250"},{"key":"ref41","article-title":"The Fake-or-Real Dataset","year":"2025","journal-title":"APTLY lab"},{"key":"ref42","article-title":"Speech arena: Speech deepfake leaderboard","author":"Arena","year":"2025"},{"key":"ref43","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit","author":"Veaux","year":"2017"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.03499"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref47","article-title":"Diffusion-based voice conversion with fast maximum likelihood sampling scheme","author":"Popov","year":"2021","journal-title":"arXiv preprint arXiv:2109.13821"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.aacl-main.56"},{"key":"ref49","first-page":"5530","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":"ref50","article-title":"Glow-tts: 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":"ref51","article-title":"Creating new language and voice components for the updated marytts text-to-speech synthesis platform","volume-title":"arXiv preprint arXiv:1712.04787","author":"Steiner","year":"2017"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3246"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448291"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0860"},{"key":"ref55","first-page":"8599","article-title":"Gradtts: A diffusion probabilistic model for text-to-speech","volume-title":"International conference on machine learning.","author":"Popov"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref58","article-title":"Diffwave: A versatile diffusion model for audio synthesis","volume-title":"arXiv preprint arXiv:2009.09761","author":"Kong","year":"2020"},{"key":"ref59","article-title":"Wavegrad: Estimating gradients for waveform generation","author":"Chen","year":"2020","journal-title":"arXiv preprint arXiv:2009.00713"},{"key":"ref60","article-title":"VoxForge speech dataset","year":"2025"},{"key":"ref61","article-title":"Deep voice 3: Scaling text-to-speech with convolutional sequence learning","author":"Ping","year":"2017","journal-title":"arXiv preprint arXiv:1710.07654"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1080\/09540099550039318"}],"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\/11434670.pdf?arnumber=11434670","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:01Z","timestamp":1775192281000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434670\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434670","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}