{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T14:15:29Z","timestamp":1788185729699,"version":"build-2803163510"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T00:00:00Z","timestamp":1785283200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["XDB1010202"],"award-info":[{"award-number":["XDB1010202"]}],"id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576336"],"award-info":[{"award-number":["62576336"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2441253"],"award-info":[{"award-number":["U2441253"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114499","type":"journal-article","created":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T06:40:11Z","timestamp":1784702411000},"page":"114499","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PE","title":["Quantization and disentanglement for cross-modal alignment in neural speech reconstruction from brain activity"],"prefix":"10.1016","volume":"180","author":[{"given":"Che","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changde","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiguang","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"7","key":"10.1016\/j.patcog.2026.114499_b1","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pbio.3003293","article-title":"Natural sounds can be reconstructed from human neuroimaging data using deep neural network representation","volume":"23","author":"Park","year":"2025","journal-title":"PLoS Biol."},{"key":"10.1016\/j.patcog.2026.114499_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2026.113741","article-title":"Multilevel prototype constraints based on hyperbolic space for eeg auditory attention decoding","volume":"179","author":"Gao","year":"2026","journal-title":"Pattern Recognit."},{"issue":"1","key":"10.1016\/j.patcog.2026.114499_b3","doi-asserted-by":"crossref","first-page":"4213","DOI":"10.1038\/s41467-023-39814-6","article-title":"Conformal in-ear bioelectronics for visual and auditory brain-computer interfaces","volume":"14","author":"Wang","year":"2023","journal-title":"Nat. Commun."},{"issue":"3","key":"10.1016\/j.patcog.2026.114499_b4","doi-asserted-by":"crossref","DOI":"10.1088\/1741-2552\/ad49d7","article-title":"Deep learning-based auditory attention decoding in listeners with hearing impairment","volume":"21","author":"Tanveer","year":"2024","journal-title":"J. Neural Eng."},{"issue":"7753","key":"10.1016\/j.patcog.2026.114499_b5","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1038\/s41586-019-1119-1","article-title":"Speech synthesis from neural decoding of spoken sentences","volume":"568","author":"Anumanchipalli","year":"2019","journal-title":"Nature"},{"key":"10.1016\/j.patcog.2026.114499_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2026.114134","article-title":"3D spatiotemporal attention for cross-subject inner speech recognition","volume":"180","author":"Wu","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114499_b7","series-title":"2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society","first-page":"93","article-title":"Decoding speech from intracortical multielectrode arrays in dorsal \u201carm\/hand areas\u201d of human motor cortex","author":"Stavisky","year":"2018"},{"issue":"3","key":"10.1016\/j.patcog.2026.114499_b8","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1056\/NEJMoa2027540","article-title":"Neuroprosthesis for decoding speech in a paralyzed person with anarthria","volume":"385","author":"Moses","year":"2021","journal-title":"N. Engl. J. Med."},{"issue":"2","key":"10.1016\/j.patcog.2026.114499_b9","doi-asserted-by":"crossref","first-page":"372","DOI":"10.11834\/jig.220525","article-title":"Review of visual neural encoding and decoding methods in fMRI","volume":"28","author":"Du","year":"2023","journal-title":"J. Image Graph."},{"key":"10.1016\/j.patcog.2026.114499_b10","article-title":"Decoding the brain via multi-view brain topology contrastive learning","volume":"172","author":"Li","year":"2026","journal-title":"Pattern Recognit."},{"issue":"1","key":"10.1016\/j.patcog.2026.114499_b11","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1007\/s11571-026-10496-2","article-title":"Linguistics and human brain: a perspective of computational neuroscience","volume":"20","author":"Zhang","year":"2026","journal-title":"Cogn. Neurodynamics","ISSN":"https:\/\/id.crossref.org\/issn\/1871-4099","issn-type":"print"},{"issue":"1","key":"10.1016\/j.patcog.2026.114499_b12","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pbio.1001251","article-title":"Reconstructing speech from human auditory cortex","volume":"10","author":"Pasley","year":"2012","journal-title":"PLoS Biol."},{"key":"10.1016\/j.patcog.2026.114499_b13","series-title":"Interspeech","first-page":"1121","article-title":"Speech reconstruction from human auditory cortex with deep neural networks.","author":"Yang","year":"2015"},{"key":"10.1016\/j.patcog.2026.114499_b14","series-title":"ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"Synthesizing speech from ecog with a combination of transformer-based encoder and neural vocoder","author":"Shigemi","year":"2023"},{"issue":"10","key":"10.1016\/j.patcog.2026.114499_b15","doi-asserted-by":"crossref","first-page":"1097","DOI":"10.1038\/s42256-023-00714-5","article-title":"Decoding speech perception from non-invasive brain recordings","volume":"5","author":"D\u00e9fossez","year":"2023","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114499_b16","series-title":"Mad: Multi-alignment meg-to-text decoding","author":"Yang","year":"2024"},{"key":"10.1016\/j.patcog.2026.114499_b17","series-title":"International Conference on Machine Learning","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023"},{"key":"10.1016\/j.patcog.2026.114499_b18","series-title":"2023 IEEE EMBS International Conference on Biomedical and Health Informatics","first-page":"1","article-title":"BrainTalker: Low-resource brain-to-speech synthesis with transfer learning using Wav2Vec 2.0","author":"Kim","year":"2023"},{"key":"10.1016\/j.patcog.2026.114499_b19","series-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"2200","article-title":"Neural2Speech: A transfer learning framework for neural-driven speech reconstruction","author":"Li","year":"2024"},{"key":"10.1016\/j.patcog.2026.114499_b20","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":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114499_b21","first-page":"1","article-title":"A neural speech decoding framework leveraging deep learning and speech synthesis","author":"Chen","year":"2024","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114499_b22","doi-asserted-by":"crossref","unstructured":"J. Li, Z. Song, J. Wang, M. Zhang, H. Liu, M. Zhang, Z. Zhang, Brainecho: Semantic brain signal decoding through vector-quantized spectrogram reconstruction for whisper-enhanced text generation, in: Findings of the Association for Computational Linguistics: ACL 2025, 2025, pp. 2762\u20132778.","DOI":"10.18653\/v1\/2025.findings-acl.142"},{"key":"10.1016\/j.patcog.2026.114499_b23","article-title":"Reverse the auditory processing pathway: Coarse-to-fine audio reconstruction from human brain activity","author":"Liu","year":"2025","journal-title":"Tsinghua Sci. Technol."},{"key":"10.1016\/j.patcog.2026.114499_b24","doi-asserted-by":"crossref","first-page":"28708","DOI":"10.52202\/068431-2081","article-title":"Masked autoencoders that listen","volume":"35","author":"Huang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114499_b25","unstructured":"Z. Ju, Y. Wang, K. Shen, X. Tan, D. Xin, D. Yang, Y. Liu, Y. Leng, K. Song, S. Tang, et al., NaturalSpeech 3: zero-shot speech synthesis with factorized codec and diffusion models, in: Proceedings of the 41st International Conference on Machine Learning, 2024, pp. 22605\u201322623."},{"key":"10.1016\/j.patcog.2026.114499_b26","doi-asserted-by":"crossref","first-page":"2871","DOI":"10.1109\/TASLP.2024.3399607","article-title":"Audioldm 2: Learning holistic audio generation with self-supervised pretraining","volume":"32","author":"Liu","year":"2024","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.patcog.2026.114499_b27","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1109\/TASLP.2021.3129994","article-title":"Soundstream: An end-to-end neural audio codec","volume":"30","author":"Zeghidour","year":"2021","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.patcog.2026.114499_b28","series-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022"},{"key":"10.1016\/j.patcog.2026.114499_b29","doi-asserted-by":"crossref","first-page":"27980","DOI":"10.52202\/075280-1214","article-title":"High-fidelity audio compression with improved rvqgan","volume":"36","author":"Kumar","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114499_b30","series-title":"ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"7053","article-title":"Learning disentangled phone and speaker representations in a semi-supervised vq-vae paradigm","author":"Williams","year":"2021"},{"key":"10.1016\/j.patcog.2026.114499_b31","series-title":"ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"Disentangled feature learning for real-time neural speech coding","author":"Jiang","year":"2023"},{"key":"10.1016\/j.patcog.2026.114499_b32","series-title":"ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"Learning source disentanglement in neural audio codec","author":"Bie","year":"2025"},{"key":"10.1016\/j.patcog.2026.114499_b33","doi-asserted-by":"crossref","unstructured":"Y. Duan, J. Zhou, Z. Wang, Y.-K. Wang, C.-T. Lin, DeWave: Discrete EEG Waves Encoding for Brain Dynamics to Text Translation, in: Proceedings of the 37th International Conference on Neural Information Processing Systems, 2023, pp. 9907\u20139918.","DOI":"10.52202\/075280-0432"},{"key":"10.1016\/j.patcog.2026.114499_b34","series-title":"BELT-2: Bootstrapping EEG-to-language representation alignment for multi-task brain decoding","author":"Zhou","year":"2024"},{"key":"10.1016\/j.patcog.2026.114499_b35","doi-asserted-by":"crossref","first-page":"79996","DOI":"10.52202\/079017-2542","article-title":"Du-IN: Discrete units-guided mask modeling for decoding speech from intracranial neural signals","volume":"37","author":"Zheng","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114499_b36","series-title":"BrainCodec: Neural fMRI codec for the decoding of cognitive brain states","author":"Nishimura","year":"2024"},{"key":"10.1016\/j.patcog.2026.114499_b37","doi-asserted-by":"crossref","unstructured":"R. Rombach, A. Blattmann, D. Lorenz, P. Esser, B. Ommer, High-resolution image synthesis with latent diffusion models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 10684\u201310695.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10.1016\/j.patcog.2026.114499_b38","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114499_b39","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112589","article-title":"EEG-driven natural image reconstruction with regional semantic awareness","volume":"172","author":"Xiang","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114499_b40","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":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114499_b41","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1","key":"10.1016\/j.patcog.2026.114499_b42","doi-asserted-by":"crossref","first-page":"862","DOI":"10.1038\/s41597-023-02752-5","article-title":"Introducing MEG-MASC a high-quality magneto-encephalography dataset for evaluating natural speech processing","volume":"10","author":"Gwilliams","year":"2023","journal-title":"Sci. Data"},{"issue":"1","key":"10.1016\/j.patcog.2026.114499_b43","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1038\/s41597-022-01382-7","article-title":"A 10-hour within-participant magnetoencephalography narrative dataset to test models of language comprehension","volume":"9","author":"Armeni","year":"2022","journal-title":"Sci. Data"},{"issue":"267","key":"10.1016\/j.patcog.2026.114499_b44","first-page":"1","article-title":"MEG and EEG data analysis with MNE-Python","volume":"7","author":"Gramfort","year":"2013","journal-title":"Front. Neurosci."},{"key":"10.1016\/j.patcog.2026.114499_b45","series-title":"Interspeech","first-page":"3670","article-title":"Gigaspeech: An evolving, multi-domain asr corpus with 10,000 hours of transcribed audio","author":"Chen","year":"2021"},{"key":"10.1016\/j.patcog.2026.114499_b46","series-title":"Interspeech","first-page":"2426","article-title":"Unsupervised cross-lingual representation learning for speech recognition","author":"Conneau","year":"2021"},{"issue":"6","key":"10.1016\/j.patcog.2026.114499_b47","doi-asserted-by":"crossref","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","article-title":"Wavlm: Large-scale self-supervised pre-training for full stack speech processing","volume":"16","author":"Chen","year":"2022","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"10.1016\/j.patcog.2026.114499_b48","series-title":"Interspeech","first-page":"2113","article-title":"Simple and effective zero-shot cross-lingual phoneme recognition","author":"Xu","year":"2021"},{"key":"10.1016\/j.patcog.2026.114499_b49","series-title":"Interspeech","first-page":"2350","article-title":"Fr\u00e9chet audio distance: A metric for evaluating music enhancement algorithms","author":"Kilgour","year":"2018"},{"key":"10.1016\/j.patcog.2026.114499_b50","series-title":"ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"Large-scale contrastive language-audio pretraining with feature fusion and keyword-to-caption augmentation","author":"Wu","year":"2023"},{"key":"10.1016\/j.patcog.2026.114499_b51","article-title":"Feature-space selection with banded ridge regression","volume":"264","author":"La Tour","year":"2022","journal-title":"NeuroImage"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326014639?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326014639?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T13:33:12Z","timestamp":1788183192000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326014639"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":51,"alternative-id":["S0031320326014639"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114499","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Quantization and disentanglement for cross-modal alignment in neural speech reconstruction from brain activity","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114499","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"114499"}}